{"meta":{"query_hash":"028605329201","filters":{"topic":"Student Assessment and Feedback"},"cohort_total":860,"direct_labels_cover":1,"predictions_cover":860,"exported":860,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/028605329201","api":"https://metacan.xera.ac/api/v1/cohort?topic=Student+Assessment+and+Feedback"},"results":[{"id":"W12634517","doi":"10.1097/00001756-200303030-00046","title":"Getting Feedback to Feed Forward: Incorporating revision into upper-year English papers","year":2011,"lang":"en","type":"article","venue":"Teaching Innovation Projects","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Mathematics education; Value (mathematics); Writing process; Academic writing; Scientific writing; Technical writing; Perception; Professional writing; Pedagogy; Computer science; Psychology; Higher education; Linguistics","score_opus":0.041823068904343834,"score_gpt":0.330857381163083,"score_spread":0.28903431225873916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W12634517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6507072,0.000007517141,0.0007738447,0.0005798901,0.0006631064,0.0007403278,8.5484305e-7,0.00039114,0.34613615],"genre_scores_gemma":[0.9529089,0.0000034099355,0.044031978,0.00088888337,0.0007308013,0.000033090128,0.000021517693,0.000032732383,0.0013487117],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9974959,0.00031964114,0.00056977966,0.00044817568,0.00071620557,0.00045031027],"domain_scores_gemma":[0.9986877,0.00011053914,0.00036643998,0.0002535835,0.00048988126,0.00009189176],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0041653086,0.00020977225,0.0002272013,0.00048704704,0.0013746328,0.00024243056,0.00043869737,0.00014851027,0.00018901103],"category_scores_gemma":[0.003137009,0.00021012216,0.00005765125,0.0016812861,0.00008184383,0.0007334105,0.00018966814,0.00046195148,0.0000918415],"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":[0.000053688254,0.00013081786,0.1635075,0.000050884824,0.000039277504,0.0000030236336,0.43347833,0.000003536902,0.004834433,0.32844055,0.0038308762,0.06562709],"study_design_scores_gemma":[0.0032620588,0.00096367276,0.16758281,0.0013618104,0.000118317024,0.0000018617637,0.5674844,0.00021423482,0.00265245,0.0128489975,0.24050136,0.0030080583],"about_ca_topic_score_codex":0.0013170282,"about_ca_topic_score_gemma":0.00014807779,"teacher_disagreement_score":0.34478745,"about_ca_system_score_codex":0.00026657854,"about_ca_system_score_gemma":0.00021118103,"threshold_uncertainty_score":0.99992543},"labels":[],"label_agreement":null},{"id":"W134909854","doi":"10.5206/cie-eci.v36i1.9088","title":"ESL/EFL Instructors’ Beliefs about Assessment and Evaluation","year":2007,"lang":"en","type":"article","venue":"Comparative and International Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University; University of Alberta","funders":"Beijing Foreign Studies University; Social Sciences and Humanities Research Council of Canada; Queen's University","keywords":"Psychology; Humanities; Philosophy","score_opus":0.14118637835775827,"score_gpt":0.5323399088658649,"score_spread":0.39115353050810664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W134909854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84292656,0.0005450622,0.00033412126,0.0009283009,0.0014971418,0.00025130477,0.0000015910385,0.000014533865,0.15350136],"genre_scores_gemma":[0.9942458,0.00020960512,0.001129063,0.00016228622,0.00059107994,0.000024391968,0.000048874183,0.0000031335578,0.0035857286],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990507,0.00007731176,0.0001698214,0.00017680127,0.00040850881,0.00011685583],"domain_scores_gemma":[0.99919456,0.00009881303,0.00010175638,0.00005142407,0.0004754901,0.00007792948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009095378,0.000077449244,0.00008561633,0.00011696561,0.00029562868,0.00014763174,0.00009903195,0.000041415788,0.00031694968],"category_scores_gemma":[0.00004617367,0.0000773624,0.000017271273,0.00008961569,0.00014577876,0.00040451207,0.000031669504,0.0000772182,0.000009865409],"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":[0.00002790904,0.0003045895,0.49691853,0.000006107579,0.0000882293,1.7561669e-7,0.073005944,0.0000028761478,0.0007974723,0.2610564,0.008689019,0.15910275],"study_design_scores_gemma":[0.0002820872,0.00002701131,0.9226312,0.000021146976,0.000015558275,7.2596777e-7,0.017219556,0.00025814373,0.000063493055,0.0042770286,0.05510399,0.000100025354],"about_ca_topic_score_codex":0.00033904685,"about_ca_topic_score_gemma":0.00050845445,"teacher_disagreement_score":0.4257127,"about_ca_system_score_codex":0.0002231991,"about_ca_system_score_gemma":0.00033055915,"threshold_uncertainty_score":0.34703767},"labels":[],"label_agreement":null},{"id":"W134958124","doi":"10.55016/ojs/ajer.v50i3.55088","title":"Teachers' Attitudes Toward Government-Mandated Provincial Testing in Manitoba","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Psychology; Educational research; Mathematics education; Public administration; Political science; Pedagogy","score_opus":0.15520904463095445,"score_gpt":0.4500630955999164,"score_spread":0.294854050968962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W134958124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74725044,0.00013495526,7.844892e-7,0.004305356,0.00026692607,0.00015132439,5.904011e-7,4.649951e-7,0.24788916],"genre_scores_gemma":[0.9826132,0.000055476445,0.00048626412,0.000039423783,0.0005713534,0.000010289585,0.0000010121144,0.0000085108995,0.016214436],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968238,0.0006015318,0.00034665645,0.00013952938,0.0016731488,0.00041533154],"domain_scores_gemma":[0.9899877,0.0091452105,0.00014559926,0.000079569494,0.00047889017,0.00016306074],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003334391,0.00007763611,0.00013822834,0.00016100761,0.00034581198,0.00015777828,0.00042564658,0.00006479319,0.0039256425],"category_scores_gemma":[0.026267102,0.00007118395,0.000049968283,0.00068489945,0.0001985478,0.0003829113,0.000040706884,0.00046233516,0.000110070614],"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":[0.00002383543,0.0004098774,0.96519804,0.0000066878733,0.000025254714,0.0000015057984,0.0071218,0.0000031424163,0.00021510881,0.021733113,0.004740651,0.0005209721],"study_design_scores_gemma":[0.0007236949,0.00016472599,0.9143159,0.000118934615,0.0000134848415,0.000008932066,0.028587746,0.0000032928695,0.000080862636,0.0015575156,0.054268453,0.00015645512],"about_ca_topic_score_codex":0.008133898,"about_ca_topic_score_gemma":0.040266994,"teacher_disagreement_score":0.2353628,"about_ca_system_score_codex":0.00089762785,"about_ca_system_score_gemma":0.0024006984,"threshold_uncertainty_score":0.998471},"labels":[],"label_agreement":null},{"id":"W135797668","doi":"10.1007/978-1-4614-3178-7_12","title":"Assessment for Learning Using Digital Knowledge Maps","year":2013,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Strengths and weaknesses; Computer science; Knowledge management; Knowledge survey; Mathematics education; Psychology; Summative assessment","score_opus":0.06704158551693114,"score_gpt":0.3793630614865653,"score_spread":0.31232147596963417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W135797668","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000075732074,0.00014434307,0.0022341555,0.00010622347,0.0007345165,0.00085740973,0.000013791057,0.00014824537,0.9956856],"genre_scores_gemma":[0.009103203,0.000086528235,0.0033819997,0.000028305667,0.0012479246,0.000025451562,0.00007935486,0.000059628284,0.9859876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998491,0.000019657848,0.0002830302,0.0003695587,0.00043376628,0.00040297236],"domain_scores_gemma":[0.99903524,0.0002535737,0.0001974913,0.00013765435,0.00024090131,0.00013513763],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033401424,0.00027695467,0.00034785984,0.000116597555,0.00067105575,0.0006555875,0.000314849,0.00033667416,0.004745388],"category_scores_gemma":[0.000033215223,0.0002630285,0.00026430807,0.000031691718,0.00016936297,0.00037114162,0.00013912082,0.00029783873,0.0006477912],"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":[0.0000028492398,0.000030369982,0.0007582303,0.000026728027,0.00011994839,0.0000011375048,0.0011750476,0.0000022964607,0.0000075804196,0.9642524,0.016516702,0.017106703],"study_design_scores_gemma":[0.00024102753,0.000052760257,0.000083643456,0.00007014733,0.00006247007,2.3421359e-7,0.0014778025,0.00013101508,4.940639e-7,0.017407442,0.9800766,0.00039637293],"about_ca_topic_score_codex":0.00009481251,"about_ca_topic_score_gemma":0.00011602642,"teacher_disagreement_score":0.96355987,"about_ca_system_score_codex":0.00035453847,"about_ca_system_score_gemma":0.000398931,"threshold_uncertainty_score":0.9999822},"labels":[],"label_agreement":null},{"id":"W1488794702","doi":"10.1002/9781118269558.app5","title":"Appendix 5: Student Survey Questionnaire","year":2007,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Computer science; Medical education; Medicine","score_opus":0.038295680706052666,"score_gpt":0.40104740344103096,"score_spread":0.3627517227349783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1488794702","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004156588,0.00055118673,0.00025264084,0.00010871969,0.0015729808,0.0003854148,0.0000097931215,0.00042496185,0.9966527],"genre_scores_gemma":[0.0038427613,0.0005108298,0.00016668506,0.00013964198,0.0011662153,0.0000072933813,0.00007073869,0.00015227593,0.9939436],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814826,0.00022626197,0.00015866384,0.00027539805,0.0008357596,0.00035564555],"domain_scores_gemma":[0.999458,0.00006264157,0.000118926204,0.00019209547,0.00004526356,0.00012307375],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014514521,0.00017799891,0.00022529322,0.00025781686,0.0001653602,0.00011037203,0.0004667764,0.00033630896,0.05263498],"category_scores_gemma":[0.000049777133,0.00016190928,0.000069330556,0.00031134993,0.00016396977,0.00003717673,0.000072923904,0.00014634393,0.007266451],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016786263,0.000056950583,0.18837848,0.00000415547,0.000042467072,0.0000040906507,0.00082054763,1.3956257e-8,6.5649886e-8,0.014923078,0.79478776,0.0009807198],"study_design_scores_gemma":[0.00011919799,0.000010598698,0.10931415,0.000053318465,0.000012621512,5.8613892e-8,0.0012065853,7.535116e-8,1.5529123e-7,0.00002523376,0.88904744,0.00021058746],"about_ca_topic_score_codex":0.044311885,"about_ca_topic_score_gemma":0.23639874,"teacher_disagreement_score":0.19208686,"about_ca_system_score_codex":0.0001119161,"about_ca_system_score_gemma":0.0001289554,"threshold_uncertainty_score":0.9935065},"labels":[],"label_agreement":null},{"id":"W1489042430","doi":"10.1111/j.1365-2923.2011.04150.x","title":"Influences on medical students’ self‐regulated learning after test completion","year":2012,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McMaster University","funders":"McMaster University","keywords":"Test (biology); Context (archaeology); Psychology; Multiple choice; Educational measurement; Medical education; Medicine; Social psychology; Curriculum; Pedagogy; Significant difference; Internal medicine","score_opus":0.015465468583563952,"score_gpt":0.39028454000698004,"score_spread":0.3748190714234161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489042430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9749304,0.00015448751,0.000021609272,0.010219764,0.0016262451,0.00019045157,2.5890282e-7,0.00014049919,0.012716255],"genre_scores_gemma":[0.99351466,0.000104792074,0.000061516344,0.0030733272,0.0017960706,0.00006724492,0.000019173303,0.000008871115,0.0013543703],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99543226,0.00030622238,0.00023568959,0.00017042863,0.0034818593,0.0003735677],"domain_scores_gemma":[0.99892634,0.0003675867,0.00008014478,0.0000937869,0.00009456472,0.00043759827],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024212596,0.000104477615,0.00013138328,0.00008113548,0.00035560533,0.00010056507,0.00043582928,0.0002166994,0.008251524],"category_scores_gemma":[0.0035714568,0.00009034443,0.00004182138,0.00031149387,0.00020997299,0.00024325901,0.00006735303,0.0003401854,0.000581368],"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":[0.000007694529,0.0012154704,0.9673414,0.000005878212,0.000012515556,7.7282675e-7,0.015186241,1.859196e-7,0.0000030016993,0.0010111756,0.007154858,0.008060802],"study_design_scores_gemma":[0.00020379087,0.000047258218,0.8300935,0.00008643784,0.000015684036,8.660527e-7,0.0035995336,0.000031740718,0.0000027047643,0.000038350998,0.1657731,0.000107040316],"about_ca_topic_score_codex":0.0003599804,"about_ca_topic_score_gemma":0.00015517857,"teacher_disagreement_score":0.15861824,"about_ca_system_score_codex":0.00016854369,"about_ca_system_score_gemma":0.0007633336,"threshold_uncertainty_score":0.99265504},"labels":[],"label_agreement":null},{"id":"W1503706910","doi":"10.22230/ijepl.2010v5n11a202","title":"Saudi National Assessment of Educational Progress (SNAEP)","year":2010,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Extant taxon; Curriculum; National curriculum; Political science; Quality (philosophy); Medical education; Educational assessment; Student achievement; Subject (documents); Mathematics education; Pedagogy; Psychology; Academic achievement; Computer science; Medicine; Library science","score_opus":0.10517672166806506,"score_gpt":0.4794197639325415,"score_spread":0.3742430422644764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503706910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5801832,0.0005346326,0.00005781662,0.27227777,0.0078089195,0.00024767788,0.00001723818,0.000011051184,0.13886167],"genre_scores_gemma":[0.987982,0.000075570344,0.0025906276,0.0008493284,0.0052146474,0.000007461942,0.000009490605,0.000006504404,0.0032643974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99819297,0.00009217364,0.00040300874,0.00010088476,0.0010634528,0.00014753164],"domain_scores_gemma":[0.9972245,0.00041014754,0.00053656375,0.0000554711,0.0016417905,0.0001315195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093768944,0.00008446071,0.00012589969,0.0004733843,0.00012381753,0.000112180736,0.0004248953,0.00008145164,0.00070257875],"category_scores_gemma":[0.00096894335,0.00008129402,0.00008438822,0.00020341022,0.00040590414,0.00044215217,0.00002372079,0.0002641639,0.0000043805167],"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":[0.000023207456,0.000577477,0.2267842,0.00001330878,0.00011318843,3.38997e-7,0.0064123417,0.0000025470524,0.00047267348,0.7498529,0.007607254,0.008140571],"study_design_scores_gemma":[0.0007172537,0.00007810648,0.81093764,0.00010814275,0.000031690095,0.00003926591,0.0147583755,0.000013645675,0.00012800044,0.041174613,0.13182297,0.00019029337],"about_ca_topic_score_codex":0.00018241114,"about_ca_topic_score_gemma":0.00013581311,"teacher_disagreement_score":0.7086783,"about_ca_system_score_codex":0.00016193076,"about_ca_system_score_gemma":0.004778459,"threshold_uncertainty_score":0.8476781},"labels":[],"label_agreement":null},{"id":"W1503949343","doi":"10.22329/celt.v1i0.3171","title":"2. The Map to Curriculum Alignment and Improvement","year":2008,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Process (computing); Mathematics education; Computer science; Curriculum mapping; Curriculum development; Concept map; Pedagogy; Sociology; Psychology","score_opus":0.012278429191304119,"score_gpt":0.29870902779021175,"score_spread":0.2864305985989076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503949343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9192252,0.00014797559,0.00009315621,0.0026160376,0.00024003636,0.0003069631,3.7020584e-7,0.00009911722,0.077271104],"genre_scores_gemma":[0.97844374,0.00027160224,0.00018023097,0.000115636474,0.00014190843,0.00003096487,0.0000011474713,0.000009231421,0.020805562],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872243,0.00027675455,0.00012666934,0.00022524821,0.0003377361,0.00031114143],"domain_scores_gemma":[0.9994327,0.00027931525,0.000053764168,0.000070145856,0.000031029263,0.00013303455],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008322645,0.00010706093,0.00011044301,0.00005529693,0.0058091553,0.00019446254,0.000110653775,0.000044599543,0.000017689235],"category_scores_gemma":[0.00027845014,0.00007948556,0.000023762857,0.00011280228,0.00010857071,0.00005635393,0.0000814653,0.0003324266,0.000012415946],"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":[0.0000936339,0.00030364207,0.64246696,0.000020021336,0.00015915789,0.000028634495,0.14222127,0.00007326414,0.0011919027,0.08046889,0.025845915,0.107126705],"study_design_scores_gemma":[0.0011626212,0.0008837013,0.07181936,0.00010493061,0.0000331543,0.0000038230737,0.05992557,0.000505858,0.000048249498,0.00045585493,0.86455125,0.00050563336],"about_ca_topic_score_codex":0.0006468359,"about_ca_topic_score_gemma":0.00015271158,"teacher_disagreement_score":0.8387053,"about_ca_system_score_codex":0.00007765146,"about_ca_system_score_gemma":0.000042516123,"threshold_uncertainty_score":0.9954851},"labels":[],"label_agreement":null},{"id":"W1518941279","doi":"","title":"Assessment Around the World","year":2006,"lang":"en","type":"article","venue":"Educational leadership","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardized test; Psychology; Tracking (education); Mathematics education; Test (biology); Aptitude; Achievement test; Academic achievement; Advanced Placement; Norm-referenced test; Medical education; Pedagogy; Developmental psychology; Medicine","score_opus":0.1129451474931034,"score_gpt":0.39879403650871376,"score_spread":0.28584888901561034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518941279","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020650964,0.00018024468,0.000028254439,0.25095847,0.0010609385,0.00018750415,0.0000011654452,0.000034142366,0.7268983],"genre_scores_gemma":[0.797843,0.000002489923,0.0005207239,0.0009946987,0.003677888,0.00003884309,0.000016906275,0.0000054311563,0.19690004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99880934,0.00013629228,0.00012203263,0.000144359,0.0005229996,0.00026500798],"domain_scores_gemma":[0.9991484,0.0005664503,0.0000561147,0.00012431851,0.000062549785,0.000042157688],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00060433807,0.00007086548,0.000058398837,0.00005650271,0.00070503494,0.00019040934,0.00030088218,0.0000284411,0.0022432117],"category_scores_gemma":[0.00003526579,0.000055307417,0.000052877516,0.00036257575,0.00026387427,0.00014613358,0.000013255198,0.00013225818,0.00028282718],"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":[0.0000010407664,0.000090180896,0.18197308,0.0000017813198,0.0000074671325,1.324738e-7,0.0012822623,0.000004669594,0.000013049145,0.68261796,0.13384242,0.00016592373],"study_design_scores_gemma":[0.000069554306,0.000003275606,0.6761796,0.0000053015083,0.000008415644,1.5977058e-7,0.019487735,0.000004201304,0.0000033804545,0.015909158,0.28825215,0.00007705203],"about_ca_topic_score_codex":0.0010024476,"about_ca_topic_score_gemma":0.005315667,"teacher_disagreement_score":0.777192,"about_ca_system_score_codex":0.00018576338,"about_ca_system_score_gemma":0.000510249,"threshold_uncertainty_score":0.99866885},"labels":[],"label_agreement":null},{"id":"W1520074575","doi":"10.19173/irrodl.v15i3.1680","title":"Peer assessment for massive open online courses (MOOCs)","year":2014,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":178,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Peer assessment; Computer science; Peer feedback; Credibility; Assessment for learning; Online assessment; Peer evaluation; Open education; Credentialing; Multimedia; Higher education; World Wide Web; Medical education; Mathematics education; Psychology","score_opus":0.15790322565992373,"score_gpt":0.5635018527575003,"score_spread":0.40559862709757655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520074575","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046547685,0.006684458,0.0032982465,0.5230848,0.00066640857,0.008373031,0.00038798238,0.00003127737,0.41092607],"genre_scores_gemma":[0.965138,0.020898366,0.0014951514,0.0005266897,0.00026045332,0.00029760145,0.0005743887,0.000011365835,0.010797943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973372,0.0008137721,0.00027258572,0.00019575958,0.0011359828,0.000244705],"domain_scores_gemma":[0.9968232,0.0018767053,0.00015061011,0.00012391234,0.0009592709,0.00006631918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015301646,0.00006903954,0.00022674073,0.000060029048,0.00042816452,0.0004932071,0.0020423909,0.00003156428,0.00037721053],"category_scores_gemma":[0.0051337467,0.000048689184,0.00004136611,0.00029033868,0.0002473067,0.0002867873,0.0010715384,0.0003306181,0.0000052909204],"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":[0.00020647822,0.0005589129,0.18117215,0.00071068516,0.00015181124,0.000003855546,0.0015135065,0.000066605055,0.000051037623,0.640419,0.08181829,0.093327664],"study_design_scores_gemma":[0.0009254918,0.00011494494,0.02620484,0.0027227416,0.000012097862,4.003177e-7,0.015554217,0.0010735852,0.0000052842825,0.0055405344,0.94775254,0.00009333788],"about_ca_topic_score_codex":0.0018193725,"about_ca_topic_score_gemma":0.0004217518,"teacher_disagreement_score":0.91859037,"about_ca_system_score_codex":0.0001327554,"about_ca_system_score_gemma":0.00032231642,"threshold_uncertainty_score":0.6145945},"labels":[],"label_agreement":null},{"id":"W1521765823","doi":"10.55016/ojs/ajer.v47i3.54877","title":"An Examination of Preservice Teachers' Simulated Classroom Assessment Practices","year":2001,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care; University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Mathematics education; Pedagogy; Educational research","score_opus":0.14166078468908497,"score_gpt":0.536891958466766,"score_spread":0.395231173777681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521765823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7899467,0.0001305147,0.000005100432,0.011399473,0.00019515512,0.00016605691,5.267212e-7,6.808472e-7,0.19815582],"genre_scores_gemma":[0.9762065,0.00038269084,0.00046473197,0.000030674793,0.0006945475,0.0000044237654,0.000009140681,0.000009410092,0.022197928],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995628,0.0015489516,0.00044888793,0.0001543799,0.001902859,0.00031690553],"domain_scores_gemma":[0.98114645,0.015553636,0.00074281474,0.0001823743,0.002157493,0.00021722367],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005615006,0.00007967182,0.0001627618,0.00037246867,0.00039309598,0.00015930003,0.0007650035,0.00009557793,0.009872323],"category_scores_gemma":[0.008456426,0.00007242864,0.000063717045,0.0008431139,0.00020492906,0.0013918097,0.000046451347,0.0004446751,0.00003932647],"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":[0.00011849298,0.0024885861,0.9236775,0.000020483005,0.00016695847,0.0000014677414,0.03426418,0.0001783291,0.0023512754,0.029136717,0.004442799,0.0031531951],"study_design_scores_gemma":[0.0005090886,0.00039019986,0.91515535,0.00005749119,0.000039023787,0.0000050626854,0.032574166,0.0002872639,0.00004326549,0.00094984565,0.04988572,0.00010352045],"about_ca_topic_score_codex":0.0062807086,"about_ca_topic_score_gemma":0.0061343233,"teacher_disagreement_score":0.18625979,"about_ca_system_score_codex":0.00030512706,"about_ca_system_score_gemma":0.0020682034,"threshold_uncertainty_score":0.99989575},"labels":[],"label_agreement":null},{"id":"W1522083394","doi":"10.1007/978-94-6091-506-2_1","title":"Pacific Crystal Centre For Science, Mathematics, And Technology Literacy","year":2011,"lang":"en","type":"book-chapter","venue":"SensePublishers eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Literacy; Engineering research; Mathematics education; Political science; Natural science; Scientific literacy; Engineering; Library science; Science education; Pedagogy; Mathematics; Computer science; Sociology; Physics","score_opus":0.022680609282771973,"score_gpt":0.28479047262353396,"score_spread":0.262109863340762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522083394","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026728606,0.00012379258,0.000028176375,0.0008456863,0.000845036,0.0010127556,0.000044882923,0.0002273897,0.996605],"genre_scores_gemma":[0.007823437,0.000035204557,0.0039143087,0.000056491885,0.0003922951,0.000016887914,0.000018340423,0.00006717703,0.98767585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976191,0.000011793507,0.0003697283,0.00065503403,0.00065725046,0.00068709115],"domain_scores_gemma":[0.9981776,0.00012656896,0.0003193652,0.00040654023,0.0007337523,0.00023619288],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008508939,0.00035165393,0.00043586895,0.00080030115,0.0009227569,0.0010843647,0.0006300474,0.0005605387,0.00035706736],"category_scores_gemma":[0.0001600329,0.0003429335,0.00013060968,0.000101136706,0.0030976501,0.00046449676,0.00022734137,0.00033487074,0.000027301972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009766142,0.000018063589,0.00008750205,0.00004883971,0.000061568775,0.000008069535,0.02069586,2.7467273e-9,0.000057661488,0.9438613,0.018773053,0.016378323],"study_design_scores_gemma":[0.0002904173,0.00004784926,0.000005924925,0.000106611566,0.00007115912,0.000003239182,0.0068609617,0.0000031818122,0.000016534561,0.19573635,0.79646814,0.00038965046],"about_ca_topic_score_codex":0.00003619192,"about_ca_topic_score_gemma":0.00012027708,"teacher_disagreement_score":0.77769506,"about_ca_system_score_codex":0.00015343446,"about_ca_system_score_gemma":0.0005738719,"threshold_uncertainty_score":0.9999526},"labels":[],"label_agreement":null},{"id":"W1523324611","doi":"10.3968/6313","title":"Application of Formative Assessment in College English Teaching","year":2015,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Computer science; Quality (philosophy); College English; Mathematics education; Order (exchange); Key (lock); Psychology","score_opus":0.029651391863191708,"score_gpt":0.4108975659950856,"score_spread":0.3812461741318939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1523324611","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2799719,0.000017353406,0.00009535269,0.0005493719,0.0008884234,0.00030046472,0.0000031536172,0.00001723643,0.71815675],"genre_scores_gemma":[0.9973043,0.0000025517354,0.001144189,0.000042807962,0.00023537624,0.000036005236,0.000002505343,0.0000026985497,0.0012295486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99853,0.00011406077,0.00024413114,0.00014015034,0.0007952602,0.00017641431],"domain_scores_gemma":[0.9990062,0.00005524648,0.00024920568,0.00007849971,0.0005343059,0.00007652533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002158585,0.000054240812,0.00012258739,0.0001529066,0.0002748837,0.000026618787,0.00037438291,0.00004499414,0.000040503266],"category_scores_gemma":[0.00010724969,0.00005658122,0.000025775746,0.0009612086,0.0005843886,0.0006413879,0.000047510097,0.000098422264,0.000002856042],"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":[0.0000029546027,0.00022323584,0.04901694,0.0000044852436,0.0000014888486,1.2442949e-8,0.1156798,0.000001059539,0.0003471824,0.8327073,0.0009255453,0.0010899819],"study_design_scores_gemma":[0.00027032243,0.000032049502,0.80127287,0.000014490349,0.000005911435,1.7417534e-8,0.14126724,0.000019049168,0.00013978817,0.005719449,0.051159464,0.00009937542],"about_ca_topic_score_codex":0.0013004149,"about_ca_topic_score_gemma":0.000035007695,"teacher_disagreement_score":0.82698786,"about_ca_system_score_codex":0.00046915503,"about_ca_system_score_gemma":0.0018587927,"threshold_uncertainty_score":0.32974187},"labels":[],"label_agreement":null},{"id":"W1524578401","doi":"10.1002/9781118411360.wbcla071","title":"Consequences, Impact, and Washback","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Phenomenon; Context (archaeology); Test (biology); Psychology; Set (abstract data type); Empirical research; Scale (ratio); Mathematics education; Pedagogy; Computer science; Epistemology","score_opus":0.026173577142377853,"score_gpt":0.3635325425005921,"score_spread":0.33735896535821425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524578401","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014048259,0.0010399309,0.000010923641,0.00051619206,0.00026585907,0.00030671223,0.000005859207,0.00017009511,0.99754393],"genre_scores_gemma":[0.0015921604,0.0022216656,0.00042857902,0.000119298755,0.0004679328,0.0000106521475,0.0000058130768,0.00007488907,0.995079],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991994,0.000053179556,0.00007786047,0.00017988967,0.00025047912,0.00023920355],"domain_scores_gemma":[0.9996475,0.00003777577,0.00007154627,0.00010340827,0.000016747319,0.00012301395],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00012600192,0.00013429216,0.0001795444,0.000075723445,0.00009324499,0.0001526169,0.00017295755,0.00021156007,0.08924928],"category_scores_gemma":[0.000016345317,0.00009942468,0.000044790027,0.000084381936,0.0005132666,0.000055950433,0.000040524435,0.000080996084,0.0009674399],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9190064e-7,0.000006884364,0.0042278813,0.000004238632,0.000034702374,0.0000013008928,0.00041406485,3.435231e-9,0.0000050584813,0.016815823,0.9774876,0.0010020086],"study_design_scores_gemma":[0.0001004224,0.000013079803,0.00055731006,0.000024461524,0.00001314899,3.35441e-7,0.0012683201,5.011895e-7,8.4196887e-7,0.00033726712,0.9975207,0.00016363618],"about_ca_topic_score_codex":0.0258228,"about_ca_topic_score_gemma":0.0052308864,"teacher_disagreement_score":0.08828184,"about_ca_system_score_codex":0.00003575064,"about_ca_system_score_gemma":0.00012948783,"threshold_uncertainty_score":0.9998104},"labels":[],"label_agreement":null},{"id":"W152593044","doi":"10.1007/0-306-47642-8_21","title":"Teachers’ Sources and Uses of Assessment Information","year":2002,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Information retrieval; Environmental science","score_opus":0.03573563513499994,"score_gpt":0.3168163061912377,"score_spread":0.28108067105623774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W152593044","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007729557,0.00011212322,0.000035846955,0.00026109317,0.00011620164,0.00021621099,0.000005584851,0.000042350082,0.99843764],"genre_scores_gemma":[0.06297175,0.0018029051,0.00079070625,0.00010986878,0.00015811475,0.0000042916254,0.00001578361,0.000010498008,0.9341361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989893,0.000018741532,0.0002535491,0.00009745802,0.000516032,0.00012496128],"domain_scores_gemma":[0.9994622,0.000078578494,0.00023500634,0.00009338361,0.00007522763,0.00005564529],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002811841,0.00013098688,0.00021299397,0.00011069297,0.00015190375,0.00010082296,0.00014284354,0.00019717657,0.002569621],"category_scores_gemma":[0.000012685349,0.00011664012,0.000062997606,0.00002087401,0.00022896212,0.00038064207,0.000059990314,0.00013108976,0.000052760886],"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":[0.0000016904787,0.0000138716605,0.009312987,0.000022121592,0.0000820227,3.9346816e-7,0.019937651,2.7947587e-7,0.0000011079366,0.94504064,0.008635107,0.0169521],"study_design_scores_gemma":[0.0001791828,0.000042812335,0.00547541,0.000050317893,0.000058093225,1.6365198e-7,0.0054207854,0.0000047125977,0.0000018580907,0.002796685,0.98577076,0.00019920166],"about_ca_topic_score_codex":0.00035648723,"about_ca_topic_score_gemma":0.00017084146,"teacher_disagreement_score":0.97713566,"about_ca_system_score_codex":0.000054944663,"about_ca_system_score_gemma":0.000060063223,"threshold_uncertainty_score":0.99834216},"labels":[],"label_agreement":null},{"id":"W1529042430","doi":"10.1177/160940691501400202","title":"Methodological Diversity in Language Assessment Research: The Role of Mixed Methods in Classroom-Based Language Assessment Studies","year":2015,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Context (archaeology); Diversity (politics); Multimethodology; Qualitative research; Educational research; Face (sociological concept); Computer science; Engineering ethics; Psychology; Sociology; Pedagogy; Social science","score_opus":0.8885844506479319,"score_gpt":0.7692516158840498,"score_spread":0.11933283476388212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1529042430","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7464579,0.0038958774,0.22111449,0.0101059135,0.002073602,0.00056850375,0.000019294896,0.000017483453,0.015746986],"genre_scores_gemma":[0.47186255,0.00008212854,0.5277317,0.000073012656,0.00014146251,0.00001156763,0.000001689473,0.0000059136823,0.00008992607],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.914173,0.08169967,0.0010161642,0.00024416856,0.002497629,0.0003693835],"domain_scores_gemma":[0.96749884,0.029713234,0.000732847,0.00015506803,0.0017788839,0.00012110711],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17069864,0.00015775819,0.0006275915,0.0007067688,0.00016214862,0.00006676973,0.0012838853,0.00010882514,0.000076898825],"category_scores_gemma":[0.01619453,0.00010824617,0.00021274385,0.0007912618,0.0008058128,0.0003032879,0.0005958468,0.0009027383,0.0000013037408],"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":[0.0003985339,0.00072971825,0.06860906,0.000014662821,0.00057560037,0.000106340616,0.7659041,0.00023250167,0.007601463,0.059150416,0.0003764972,0.09630106],"study_design_scores_gemma":[0.0013749347,0.00025979217,0.051459774,0.00009538292,0.000027765507,0.000001457372,0.8931501,0.0002401345,0.0019412603,0.050126012,0.0012024356,0.000120958524],"about_ca_topic_score_codex":0.0018828129,"about_ca_topic_score_gemma":0.000963802,"teacher_disagreement_score":0.30661726,"about_ca_system_score_codex":0.0012557035,"about_ca_system_score_gemma":0.0007117453,"threshold_uncertainty_score":0.9920925},"labels":[],"label_agreement":null},{"id":"W1531240630","doi":"10.58680/rte201424579","title":"A Framework for Using Consequential Validity Evidence in Evaluating Large-Scale Writing Assessments: A Canadian Study","year":2014,"lang":"en","type":"article","venue":"Research in the Teaching of English","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Lethbridge","funders":"","keywords":"Scale (ratio); Psychology; Test validity; Mathematics education; Pedagogy; Psychometrics; Developmental psychology; Geography","score_opus":0.50791354546036,"score_gpt":0.5991396042643354,"score_spread":0.09122605880397539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1531240630","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98871803,0.00003881172,0.0014639084,0.00034301338,0.00035955076,0.001653931,0.000004834013,0.00001734121,0.0074005653],"genre_scores_gemma":[0.9908051,0.0000052571286,0.008126366,0.000041466184,0.0008755132,0.000112002155,0.0000017445986,0.000013825714,0.00001874594],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9866157,0.0098478785,0.00045454368,0.0003594405,0.0016923038,0.0010301031],"domain_scores_gemma":[0.9882947,0.01060233,0.00011803571,0.00032021108,0.00053919194,0.00012551855],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09818516,0.000110060166,0.00025290533,0.0004060734,0.0012758762,0.00033552374,0.0009909467,0.000112335394,0.00002251352],"category_scores_gemma":[0.040333565,0.00010007965,0.00006591832,0.0007065354,0.00020014509,0.00040060387,0.000144098,0.0012490031,9.895568e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039492752,0.00039861913,0.74084103,0.000046513087,0.00001437247,0.000004708913,0.22761302,0.000082531,0.00002426313,0.029581472,0.000096547985,0.0012574346],"study_design_scores_gemma":[0.0016024917,0.00070880394,0.07853465,0.0017182572,0.00003617374,2.701991e-7,0.87810934,0.015650475,0.0000074242907,0.022252357,0.0010584374,0.00032133338],"about_ca_topic_score_codex":0.2240594,"about_ca_topic_score_gemma":0.29695344,"teacher_disagreement_score":0.66230637,"about_ca_system_score_codex":0.0006607172,"about_ca_system_score_gemma":0.0008422278,"threshold_uncertainty_score":0.9813137},"labels":[],"label_agreement":null},{"id":"W1544944805","doi":"10.19173/irrodl.v14i1.1394","title":"Peer Portal: Quality enhancement in thesis writing using self-managed peer review on a mass scale","year":2013,"lang":"en","type":"review","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Stockholms Universitet","keywords":"Peer review; Bachelor; Quality (philosophy); Peer feedback; Technical peer review; Computer science; Scale (ratio); Psychology; Medical education; Mathematics education; Multimedia; Medicine; Political science","score_opus":0.27905200290430215,"score_gpt":0.5703756518986821,"score_spread":0.29132364899437996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544944805","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009386496,0.9450984,0.000011302995,0.008889193,0.00008817449,0.003308005,0.00003432897,0.000011330814,0.042465385],"genre_scores_gemma":[0.0004010657,0.9946938,0.00017948441,0.00016477502,0.00010658118,0.00040648383,0.00030433814,0.000019717501,0.0037237294],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.988571,0.0049423804,0.0013745046,0.0005044599,0.004090142,0.00051749876],"domain_scores_gemma":[0.9951795,0.002417414,0.00076344766,0.0003229801,0.0012114603,0.00010520894],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.052128423,0.00026476636,0.0014142637,0.00023955414,0.0003637935,0.000435754,0.0021325152,0.00012194684,0.0010008796],"category_scores_gemma":[0.0080470815,0.00018237851,0.00024060214,0.0012062608,0.00022167827,0.00029958435,0.00084736873,0.0014170299,0.000054115375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020595768,0.00045851353,0.0033221275,0.11643614,0.0002931168,0.000031668893,0.0008834634,0.0000022192755,8.931361e-7,0.0092413435,0.013660326,0.8556496],"study_design_scores_gemma":[0.00016671774,0.000019566949,0.00012483449,0.24867399,0.00006517338,0.0000010545195,0.0023088658,0.000014746706,1.8007263e-7,0.0001086034,0.7483594,0.00015687634],"about_ca_topic_score_codex":0.002580998,"about_ca_topic_score_gemma":0.00014587078,"teacher_disagreement_score":0.8554927,"about_ca_system_score_codex":0.00063840114,"about_ca_system_score_gemma":0.0006026352,"threshold_uncertainty_score":0.9999123},"labels":[],"label_agreement":null},{"id":"W1546018842","doi":"10.7202/1000316ar","title":"La diversité ethnoculturelle dans les programmes français de sciences et technologie de l’Ontario : une analyse comparative entre le programme de 1998 et celui de 2007","year":2010,"lang":"fr","type":"article","venue":"Reflets Revue d’intervention sociale et communautaire","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; University of Ottawa","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.06546275745092044,"score_gpt":0.3931206413774599,"score_spread":0.32765788392653944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546018842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88324,0.0018124708,0.0021132496,0.028185401,0.00053187297,0.00084428355,0.00004494697,0.0003773104,0.082850456],"genre_scores_gemma":[0.97089565,0.00052654196,0.010768976,0.00030394047,0.00016749934,0.00012653951,0.0000691984,0.000034609093,0.017107068],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99409646,0.0026365754,0.0006362565,0.00058747694,0.000595004,0.0014482192],"domain_scores_gemma":[0.9979351,0.0005215602,0.00062726793,0.00039702168,0.0002162717,0.00030274026],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["sts"],"category_scores_codex":[0.00635778,0.00048559695,0.0006669029,0.00018467491,0.002585092,0.00073455326,0.0015752892,0.0010278724,0.00033379282],"category_scores_gemma":[0.00026143048,0.0005130827,0.0008756251,0.001256845,0.0032129502,0.00072718615,0.0006487128,0.0024744181,0.00004748897],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005110722,0.0024617664,0.38693327,0.00017591217,0.00046778866,0.00008257156,0.47615257,0.000083667706,0.0008112233,0.08449643,0.0030977612,0.045185942],"study_design_scores_gemma":[0.0020872718,0.00057961803,0.16598791,0.0010935765,0.0004921042,0.00005507793,0.45274457,0.0005602816,0.00063547795,0.012496217,0.36226052,0.0010073577],"about_ca_topic_score_codex":0.29773226,"about_ca_topic_score_gemma":0.8217783,"teacher_disagreement_score":0.524046,"about_ca_system_score_codex":0.0014161547,"about_ca_system_score_gemma":0.0019111045,"threshold_uncertainty_score":0.9998269},"labels":[],"label_agreement":null},{"id":"W1549299204","doi":"10.1002/9781118411360.wbcla131","title":"Assessing Integrated Skills","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Active listening; Reading (process); Relevance (law); Convention; Test (biology); Psychology; Vocational education; Literacy; Value (mathematics); Cognitive skill; Cognition; Mathematics education; Cognitive psychology; Pedagogy; Computer science; Linguistics; Sociology; Communication","score_opus":0.026527057152858826,"score_gpt":0.3790245025491448,"score_spread":0.352497445396286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1549299204","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003762375,0.00012049198,0.0003245313,0.00023827849,0.0009479046,0.00027829438,0.0000014658068,0.00048765846,0.9975638],"genre_scores_gemma":[0.00050589704,0.00021186809,0.0024835619,0.00016614445,0.0008211091,0.000013780191,0.000018155159,0.00015015644,0.9956293],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897045,0.0000916539,0.000107938744,0.00019953512,0.00036273163,0.00026767034],"domain_scores_gemma":[0.9995974,0.000047258403,0.00010402874,0.00013598424,0.000034624114,0.00008072919],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017784888,0.00014854364,0.00019465208,0.00013240668,0.00012528164,0.0005151059,0.00030260833,0.00030093334,0.1421887],"category_scores_gemma":[0.00003871722,0.00011725572,0.0000623254,0.00020761456,0.0001381186,0.00015573677,0.00003873004,0.00013975654,0.003842816],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.758934e-8,0.00002955746,0.001157652,0.0000028678105,0.000027103986,0.0000010337283,0.00044725908,5.3976454e-9,0.0000023475109,0.0120905815,0.9796586,0.006582905],"study_design_scores_gemma":[0.00007283679,0.0000032005169,0.00047739322,0.00006599522,0.000013141929,3.824815e-8,0.004841223,0.0000015208606,0.0000010674006,0.00007301491,0.9942745,0.00017609705],"about_ca_topic_score_codex":0.0135850245,"about_ca_topic_score_gemma":0.0031078241,"teacher_disagreement_score":0.13834588,"about_ca_system_score_codex":0.0000655937,"about_ca_system_score_gemma":0.00015341767,"threshold_uncertainty_score":0.9969328},"labels":[],"label_agreement":null},{"id":"W1557823848","doi":"","title":"The Evaluation of University Teaching: Exploring the Question of Resistance","year":2000,"lang":"en","type":"article","venue":"Resources for feminist research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ideology; Resistance (ecology); Humanities; Sociology; Context (archaeology); Curriculum; Politics; Documentation; Pedagogy; Political science; Philosophy; Law","score_opus":0.20262336338286807,"score_gpt":0.4708646831618238,"score_spread":0.2682413197789557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1557823848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7582767,0.00021376339,0.0000042651272,0.0013578436,0.000040247247,0.00046218754,0.000004043079,0.000008325285,0.2396326],"genre_scores_gemma":[0.9771604,0.0002998149,0.000049513234,0.0000021300034,0.000117670046,0.000020148675,0.0000011403608,0.0000042388465,0.022344934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959805,0.0019195034,0.00014160585,0.00012395589,0.0015884062,0.0002460441],"domain_scores_gemma":[0.9969771,0.0023437142,0.00006803251,0.00020785541,0.00037052704,0.0000327919],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.023864588,0.000042136213,0.00007541354,0.000050539376,0.002126089,0.000055403467,0.000577086,0.000032482392,0.000056722696],"category_scores_gemma":[0.00094259327,0.000028217246,0.00005887132,0.0003230374,0.00078069686,0.000079441656,0.000041650474,0.00016815677,0.0000034000109],"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":[0.0023321516,0.0002817603,0.023170095,0.00009689109,0.00014261698,9.0221766e-7,0.29643118,0.000098300035,0.0006768162,0.36540645,0.016256418,0.29510644],"study_design_scores_gemma":[0.00028402553,0.000063261,0.0252325,0.000052261385,0.000023170101,4.0185423e-8,0.09994705,0.0001265219,0.00011601688,0.0018849677,0.8722244,0.000045773606],"about_ca_topic_score_codex":0.0007903422,"about_ca_topic_score_gemma":0.0013815574,"teacher_disagreement_score":0.855968,"about_ca_system_score_codex":0.00013821067,"about_ca_system_score_gemma":0.00015306007,"threshold_uncertainty_score":0.999173},"labels":[],"label_agreement":null},{"id":"W1558577420","doi":"","title":"Evaluation Methods: Learner Perceptions of Authentic Assessment Practices","year":2009,"lang":"en","type":"article","venue":"EdMedia: World Conference on Educational Media and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; MacEwan University","funders":"","keywords":"Perception; Psychology; Computer science; Social psychology; Pedagogy; Mathematics education","score_opus":0.10760073386868232,"score_gpt":0.489301490347308,"score_spread":0.38170075647862567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558577420","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082881786,0.00035934197,0.0002523029,0.842821,0.0017041285,0.00062615884,0.0000045130096,0.0000941076,0.07125664],"genre_scores_gemma":[0.9878711,0.00039639178,0.00969573,0.00012310533,0.0003455005,0.000106025545,0.000022878401,0.000004884029,0.0014343598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806917,0.0003903945,0.00025573192,0.000289605,0.00075948116,0.00023559494],"domain_scores_gemma":[0.9978554,0.0008752904,0.00036477347,0.00018734646,0.00062337646,0.000093811694],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018293549,0.00012092492,0.0002031422,0.0005737525,0.00027231537,0.000050616036,0.0002738324,0.00013532168,0.0027978304],"category_scores_gemma":[0.0021934037,0.00011416036,0.000033009346,0.0007546063,0.0005133365,0.00019279847,0.00002821747,0.00029768722,0.000028603032],"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":[0.000004493371,0.00034152812,0.024884077,0.0000036347183,0.000028107903,2.3727246e-7,0.005077409,3.3706374e-7,0.0012643795,0.920421,0.00084013946,0.047134627],"study_design_scores_gemma":[0.00025375563,0.000093811235,0.18610385,0.0000389407,0.00010377415,7.2260434e-7,0.0047657634,0.00015434816,0.00008208858,0.8075532,0.0007206272,0.00012915155],"about_ca_topic_score_codex":0.000056508976,"about_ca_topic_score_gemma":0.0005336059,"teacher_disagreement_score":0.90498936,"about_ca_system_score_codex":0.00011910036,"about_ca_system_score_gemma":0.0012708292,"threshold_uncertainty_score":0.99811375},"labels":[],"label_agreement":null},{"id":"W1565883978","doi":"10.1002/9781118411360.wbcla022","title":"Large‐Scale Assessment","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Scale (ratio); Bureaucracy; Politics; Test (biology); Quality (philosophy); Language assessment; Political science; Public relations; Psychology; Computer science; Mathematics education; Epistemology; Geography; Law","score_opus":0.01975342632826853,"score_gpt":0.3682010653148333,"score_spread":0.3484476389865648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565883978","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019386822,0.00012066056,0.00050722377,0.0006470364,0.0009913035,0.00044801607,0.000007611787,0.00041471163,0.99684405],"genre_scores_gemma":[0.00025603053,0.00040373398,0.0027885854,0.00026253262,0.0011641046,0.0000453684,0.000019912273,0.00015754247,0.9949022],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986337,0.00008230919,0.00011114215,0.00023821922,0.00055441185,0.00038024594],"domain_scores_gemma":[0.9995444,0.000026610856,0.00009323007,0.00020036487,0.0000237446,0.00011165562],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002459376,0.00015336534,0.0002096263,0.00010073327,0.00015912324,0.00014124539,0.0003536571,0.00027657545,0.24881652],"category_scores_gemma":[0.000005554345,0.00013124211,0.000084929066,0.00012761012,0.00008612337,0.00005542549,0.000080635036,0.00013776652,0.0046749534],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3344346e-7,0.000051157895,0.002658071,0.0000043894997,0.000027799277,7.05027e-7,0.00094498217,4.697061e-9,9.729819e-7,0.05044774,0.9455913,0.00027276744],"study_design_scores_gemma":[0.00014661619,0.000007774326,0.0008136892,0.000019887006,0.000016330776,2.6203102e-8,0.008737306,0.0000047445037,1.8843015e-7,0.00011264439,0.9899511,0.00018972307],"about_ca_topic_score_codex":0.0032589964,"about_ca_topic_score_gemma":0.009639765,"teacher_disagreement_score":0.24414156,"about_ca_system_score_codex":0.00007556793,"about_ca_system_score_gemma":0.00013577547,"threshold_uncertainty_score":0.9961},"labels":[],"label_agreement":null},{"id":"W1567910316","doi":"10.18806/tesl.v23i2.55","title":"Professionalism and High-Stakes Tests: Teachers’ Perspectives When Dealing With Educational Change Introduced Through Provincial Exams","year":2006,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; University of Cambridge; McGill University; Yale University","keywords":"Curriculum; Perception; Mathematics education; Psychology; Pedagogy; Professional development; Element (criminal law); Political science","score_opus":0.037744421768051976,"score_gpt":0.3168132509451714,"score_spread":0.2790688291771194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1567910316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9336225,0.009023931,0.00002597992,0.05056843,0.0006642449,0.00041044422,0.000013503075,0.0000301957,0.0056407624],"genre_scores_gemma":[0.9900909,0.000042839136,0.001646702,0.0019289383,0.0046485094,0.000022953589,0.000008067158,0.000016295257,0.0015948118],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99824256,0.000115865325,0.00018854985,0.00021708808,0.0008809312,0.00035498006],"domain_scores_gemma":[0.9992808,0.00013480838,0.00018525006,0.00007413208,0.00021867064,0.00010635309],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040295915,0.00014264912,0.00015670904,0.000049668502,0.0012180557,0.00019440963,0.00019305368,0.00005348971,0.0029674133],"category_scores_gemma":[0.00008855149,0.00011259033,0.00002224713,0.00012415306,0.00019151227,0.00047771155,0.000026576876,0.00029614527,0.0000010118077],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015141892,0.0004905476,0.17457926,0.000026915455,0.00023083927,0.00009834941,0.32757688,0.000007854047,0.0005500445,0.35889187,0.12999791,0.007398096],"study_design_scores_gemma":[0.0014755669,0.000139737,0.7340951,0.00014507743,0.00008972254,0.000057449422,0.17603125,0.000004977941,0.000035756206,0.020610634,0.06670855,0.00060615974],"about_ca_topic_score_codex":0.6343767,"about_ca_topic_score_gemma":0.7241026,"teacher_disagreement_score":0.55951583,"about_ca_system_score_codex":0.000659063,"about_ca_system_score_gemma":0.0025602272,"threshold_uncertainty_score":0.997944},"labels":[],"label_agreement":null},{"id":"W1568000697","doi":"10.5489/cuaj.1007","title":"The importance of feedback","year":2013,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Urological Association","funders":"","keywords":"Psychology","score_opus":0.015825444352469013,"score_gpt":0.26923113101737284,"score_spread":0.2534056866649038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568000697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78047264,0.00027527686,0.000008642546,0.11659986,0.0007241625,0.00021103672,0.000003258198,0.000015258669,0.101689845],"genre_scores_gemma":[0.99408096,0.00019972782,0.00005691884,0.0013776744,0.0004202157,0.000006115141,7.683737e-7,0.0000031537352,0.0038544901],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99859643,0.00022663306,0.00024483673,0.00007196501,0.00043032112,0.00042982146],"domain_scores_gemma":[0.9986091,0.00035965108,0.00029138522,0.000060205784,0.00034059357,0.00033903497],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013795542,0.000055231354,0.000099346806,0.00003758862,0.0010895777,0.0002432096,0.0003278487,0.00011975571,0.0020301808],"category_scores_gemma":[0.0009952919,0.00003679008,0.000080296966,0.0001966279,0.00010331673,0.00016452823,0.00001165857,0.00024851438,0.00015581225],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011662215,0.0000056033487,0.9322562,1.511047e-7,0.000020229485,9.797852e-7,0.00047306655,0.000001086974,0.0000064142155,0.008456356,0.057243314,0.0015354252],"study_design_scores_gemma":[0.000099081575,0.000020336896,0.76022345,9.863769e-7,0.0000055868277,7.604653e-7,0.001563475,0.0000064449464,8.023583e-7,0.0078098415,0.2302239,0.00004535741],"about_ca_topic_score_codex":0.0065646623,"about_ca_topic_score_gemma":0.02079404,"teacher_disagreement_score":0.21360828,"about_ca_system_score_codex":0.0005041338,"about_ca_system_score_gemma":0.00041993705,"threshold_uncertainty_score":0.9988821},"labels":[],"label_agreement":null},{"id":"W1569132542","doi":"10.1186/s40468-015-0020-6","title":"Chinese university students’ perceptions of assessment tasks and classroom assessment environment","year":2015,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Learning environment; Context (archaeology); Perception; Mathematics education; Formative assessment; Scale (ratio); Pedagogy","score_opus":0.028109092519047394,"score_gpt":0.3653477989662329,"score_spread":0.33723870644718545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569132542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9419419,0.00005137185,0.0002485311,0.00020581215,0.00008667508,0.00027220027,0.00000679497,0.000049805247,0.057136897],"genre_scores_gemma":[0.97824585,0.000027115608,0.020577317,0.000016425585,0.00006138612,0.000004238641,0.000008887506,0.00000886621,0.0010499203],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983996,0.00026047515,0.000193727,0.00023836593,0.0006561989,0.00025160247],"domain_scores_gemma":[0.9993121,0.00020936469,0.00012275977,0.00017017771,0.0000404026,0.00014521285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010369428,0.00012500619,0.00020326526,0.00011173711,0.0001617467,0.000052068808,0.00030226546,0.00007039295,0.00013340233],"category_scores_gemma":[0.00012812347,0.0001241186,0.00003318454,0.00032400366,0.00018474406,0.00016649706,0.00021501459,0.00018707944,0.000007998821],"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":[0.0000039356037,0.00020671145,0.97881746,0.000006567232,0.000013543161,0.000027102884,0.018329524,0.000036725978,0.00047793344,0.0006787766,0.00006474539,0.0013369817],"study_design_scores_gemma":[0.00074924243,0.00007007319,0.8975031,0.00002637691,0.000019450987,8.8467317e-7,0.10085373,0.00023987185,0.0000010310321,0.00010820738,0.0003066649,0.00012139339],"about_ca_topic_score_codex":0.002242851,"about_ca_topic_score_gemma":0.0009390415,"teacher_disagreement_score":0.08252421,"about_ca_system_score_codex":0.000412319,"about_ca_system_score_gemma":0.00016235102,"threshold_uncertainty_score":0.50614095},"labels":[],"label_agreement":null},{"id":"W1570879941","doi":"10.22329/celt.v1i0.3191","title":"22. The Writing Development Initiative: A Pilot Project to Help Students Become Proficient Writers","year":2008,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Psychology; Medical education; Teaching assistant; Grant writing; Pedagogy; Mathematics education; Medicine; Library science; Engineering; Computer science","score_opus":0.06557763282669944,"score_gpt":0.37366961149807154,"score_spread":0.3080919786713721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570879941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91202384,0.000040101928,0.00015953448,0.0007149686,0.00013653192,0.0008350064,7.363269e-7,0.0001948942,0.085894376],"genre_scores_gemma":[0.99110967,0.00003011507,0.0008084278,0.0003554001,0.00015846669,0.00013612001,0.000006195162,0.000022636112,0.007372947],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969505,0.00093723694,0.0002937954,0.00039050062,0.0009048446,0.0005230887],"domain_scores_gemma":[0.998991,0.0005653413,0.00012617308,0.000102498954,0.0000932265,0.00012173019],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00191326,0.00020115395,0.00021803801,0.00023801881,0.006973876,0.00036837888,0.00036419943,0.000056519522,0.000039857114],"category_scores_gemma":[0.00076309196,0.00015947392,0.000038848,0.00052439823,0.00013179096,0.00012973085,0.00019692835,0.0007469011,0.000028880815],"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":[0.00010049598,0.000366026,0.7064925,0.0000152259245,0.000090274756,0.00002804569,0.2823344,0.000050175957,0.00012415923,0.0017977884,0.0018767683,0.006724162],"study_design_scores_gemma":[0.0028800075,0.0015873156,0.6252362,0.0005830803,0.000056332494,0.000020151294,0.24051028,0.00031438173,0.00007608658,0.00005293496,0.12750797,0.0011752556],"about_ca_topic_score_codex":0.00024907672,"about_ca_topic_score_gemma":0.00010624526,"teacher_disagreement_score":0.12563121,"about_ca_system_score_codex":0.00025585442,"about_ca_system_score_gemma":0.00027246017,"threshold_uncertainty_score":0.9943189},"labels":[],"label_agreement":null},{"id":"W1577833291","doi":"","title":"Diagnosing L2 Learners' Language Skills Based on the Use of a Web-Based Assessment Tool Called DIALANG","year":2014,"lang":"en","type":"article","venue":"International journal of e-learning & distance education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Active listening; Reading (process); Psychology; Significant difference; Mathematics education; English language; Foreign language; Ranking (information retrieval); English as a foreign language; Pedagogy; Computer science; Linguistics; Mathematics; Artificial intelligence; Communication","score_opus":0.017757784324462636,"score_gpt":0.3534006645869133,"score_spread":0.3356428802624507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577833291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95926934,0.000046677895,0.020793753,0.010613325,0.003035882,0.00021556501,0.0000040903483,0.000023038529,0.0059983204],"genre_scores_gemma":[0.99578816,0.0000340365,0.0019573735,0.0005705387,0.0008851618,0.000011471905,0.000013269537,0.0000118351545,0.0007281854],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977238,0.00053700415,0.00038560445,0.000122012636,0.0010822732,0.0001492729],"domain_scores_gemma":[0.9966371,0.0019068124,0.0007396206,0.000112825284,0.00054758997,0.00005603245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013542011,0.00010295908,0.00016081565,0.00016817244,0.00019633061,0.00024460568,0.00042209454,0.00004826142,0.0003243259],"category_scores_gemma":[0.00248914,0.00008018717,0.00013943191,0.0001709102,0.0001070855,0.0002809597,0.000016702481,0.00030418448,0.000006838487],"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":[0.0002708365,0.0019595437,0.85994565,0.000024019871,0.00017488426,0.000008586097,0.01660422,0.021218466,0.0018955956,0.06034524,0.010522223,0.027030736],"study_design_scores_gemma":[0.0033027318,0.0005547962,0.49417138,0.0020380295,0.00015538473,0.0000023726561,0.032271888,0.03427833,0.00042053327,0.00042586983,0.4317924,0.00058627094],"about_ca_topic_score_codex":0.00015408034,"about_ca_topic_score_gemma":0.000108155684,"teacher_disagreement_score":0.4212702,"about_ca_system_score_codex":0.00032864447,"about_ca_system_score_gemma":0.00077708095,"threshold_uncertainty_score":0.35511413},"labels":[],"label_agreement":null},{"id":"W1578913844","doi":"","title":"What Has Experience Got to Do with It? An Exploration of L1 and L2 Test Takers' Perceptions of Test Performance and Alignment to Classroom Literacy Activities.","year":2011,"lang":"en","type":"article","venue":"ePrints Soton (University of Southampton)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Queen's University","funders":"","keywords":"Test (biology); Graduation (instrument); Literacy; Psychology; Perception; Mathematics education; Scale (ratio); Pedagogy; Engineering","score_opus":0.05434605885297318,"score_gpt":0.29153421959941517,"score_spread":0.237188160746442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578913844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99608076,0.0000052754463,0.00102793,0.00034727508,0.000047330446,0.00036062096,0.000012357378,0.00001316613,0.0021052675],"genre_scores_gemma":[0.99537873,0.00015933957,0.003695499,0.00002462103,0.000013488598,0.0000026826312,0.0000027393294,0.0000052111304,0.00071766827],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9990881,0.000039016697,0.00011846781,0.00026473877,0.00032394825,0.00016574386],"domain_scores_gemma":[0.9993237,0.00006975337,0.000132422,0.00018917369,0.0001238636,0.00016105469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022578311,0.0001039743,0.0001851293,0.00012598382,0.00032461135,0.000060507296,0.00022200117,0.000052248168,0.00048699457],"category_scores_gemma":[0.00002282,0.00011468167,0.00002529889,0.00023153906,0.0005138777,0.002679333,0.00014655857,0.00005703231,0.0000087066865],"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":[0.00006117008,0.00015387249,0.42030317,0.000013861472,0.000008839202,6.2955e-7,0.5749997,0.0000020815764,0.0012716572,0.00012990498,0.000018121753,0.0030369873],"study_design_scores_gemma":[0.00028453284,0.0003654857,0.40376475,0.000118005206,0.000014874046,2.623259e-7,0.59430015,0.000018877066,0.0005855865,0.00003132148,0.00040408972,0.00011204942],"about_ca_topic_score_codex":0.0010588053,"about_ca_topic_score_gemma":0.00095600204,"teacher_disagreement_score":0.019300466,"about_ca_system_score_codex":0.000046956346,"about_ca_system_score_gemma":0.00005620716,"threshold_uncertainty_score":0.53322494},"labels":[],"label_agreement":null},{"id":"W1583411474","doi":"10.18806/tesl.v31i1.1166","title":"The Effect of Self-Assessment on EFL Learners’ Self-Efficacy","year":2014,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Analysis of covariance; Formative assessment; Mathematics education; Humanities; Mathematics; Statistics; Philosophy","score_opus":0.008497245299180027,"score_gpt":0.3039366541429781,"score_spread":0.2954394088437981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1583411474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9194094,0.0007170438,0.000025980306,0.005400528,0.0019563322,0.0003595713,0.0000013467547,0.00006629454,0.072063506],"genre_scores_gemma":[0.99764144,0.00010160817,0.000119426266,0.0011965996,0.0006006828,0.0000038545895,4.3223028e-7,0.000010904596,0.00032502585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997305,0.00066795456,0.00024733847,0.00011955898,0.0012574537,0.00040274105],"domain_scores_gemma":[0.9978838,0.0014445684,0.00023099658,0.00015956153,0.00008309755,0.00019799697],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0026078653,0.00012478707,0.00019510297,0.000039068516,0.0013180127,0.0001573275,0.00050863833,0.000046545236,0.0008593174],"category_scores_gemma":[0.00016365909,0.00007875168,0.00009053322,0.00018252316,0.00006651543,0.00006984097,0.000033263786,0.0003714179,0.0000066296843],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031542167,0.0007826089,0.22089396,0.00007190581,0.0015026903,0.000095706244,0.01619222,0.0003687572,0.00031685122,0.07202229,0.5581828,0.12925477],"study_design_scores_gemma":[0.0025292737,0.0014418963,0.22838596,0.000059127044,0.00016106023,0.000008748934,0.0032612884,0.00025955372,0.0001722597,0.00021797339,0.76315916,0.00034372119],"about_ca_topic_score_codex":0.036588773,"about_ca_topic_score_gemma":0.06841736,"teacher_disagreement_score":0.20497634,"about_ca_system_score_codex":0.00067516224,"about_ca_system_score_gemma":0.0012944165,"threshold_uncertainty_score":0.9999821},"labels":[],"label_agreement":null},{"id":"W1586317966","doi":"","title":"Accountability, Student Assessment, and the Need for a Comprehensive Approach.","year":2005,"lang":"en","type":"article","venue":"International electronic journal for leadership in learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accountability; Psychology; Pedagogy; Sociology; Mathematics education; Political science","score_opus":0.15105256910987522,"score_gpt":0.44048664126366943,"score_spread":0.28943407215379424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586317966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6939996,0.004854221,0.060847364,0.19365342,0.0026968569,0.0053583747,0.0000075414446,0.00019413877,0.038388487],"genre_scores_gemma":[0.9948381,0.00035528757,0.0010597882,0.00053515466,0.0010779008,0.00013330387,0.000007225175,0.000015209134,0.0019780044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9980125,0.00028966437,0.00032211293,0.0002021922,0.0005280368,0.00064549386],"domain_scores_gemma":[0.9981581,0.0012769512,0.00021445595,0.000054220087,0.00024349657,0.000052788135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003654746,0.00012368178,0.00019461835,0.00013155732,0.0007072719,0.00039610217,0.00047977868,0.00007167397,0.000034068566],"category_scores_gemma":[0.00023668111,0.000097472264,0.00014773969,0.00011600441,0.0002559936,0.0003895264,0.000043975935,0.00080177584,0.0000016664662],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009725276,0.00032050212,0.10758281,0.000031245007,0.0005210776,6.312214e-7,0.06392912,0.004088182,0.00011436362,0.8082149,0.0008622483,0.013362416],"study_design_scores_gemma":[0.018882975,0.00039320652,0.032849416,0.000097975826,0.00012332274,0.0000390682,0.5706168,0.031563886,0.000008090058,0.024028575,0.32087818,0.00051856175],"about_ca_topic_score_codex":0.000070654845,"about_ca_topic_score_gemma":0.0005020696,"teacher_disagreement_score":0.7841863,"about_ca_system_score_codex":0.0009188239,"about_ca_system_score_gemma":0.0003325385,"threshold_uncertainty_score":0.5439835},"labels":[],"label_agreement":null},{"id":"W1587603569","doi":"","title":"The Handheld: A Useful Tool to Collect Information in the Process of Authentic Assessment.","year":2008,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mobile device; Process (computing); Computer science; World Wide Web","score_opus":0.06382413120279898,"score_gpt":0.3529445154863502,"score_spread":0.28912038428355125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1587603569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.894139,0.000108636144,0.000017824439,0.026895344,0.00078311877,0.0013721731,0.000005042007,0.00003736833,0.07664148],"genre_scores_gemma":[0.97928476,0.00062968134,0.00008588989,0.00097470183,0.00011484728,0.00027002365,0.000013702803,0.000011062827,0.018615298],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968763,0.0006520357,0.00056680414,0.0002819475,0.001198692,0.00042420125],"domain_scores_gemma":[0.99840707,0.00036782937,0.0006685151,0.0002287624,0.00022360348,0.00010423041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016316413,0.00019436513,0.00025095124,0.00018654604,0.001033204,0.00029522486,0.00042898467,0.00009271276,0.00014974429],"category_scores_gemma":[0.0001620033,0.00014880695,0.000037927868,0.001384407,0.0002006582,0.0004800537,0.000045025165,0.0005572852,0.000024570149],"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":[0.00019928181,0.00033818145,0.7756853,0.00008918446,0.000016238284,0.0000018579847,0.049628187,0.00004505477,0.000013739347,0.15998639,0.0028406116,0.011155961],"study_design_scores_gemma":[0.00048509391,0.0002653105,0.9046501,0.00020329017,0.000008882302,8.9598814e-7,0.033900715,0.000089914065,0.000005939651,0.0024045685,0.0577775,0.00020781063],"about_ca_topic_score_codex":0.0019500873,"about_ca_topic_score_gemma":0.004754462,"teacher_disagreement_score":0.15758182,"about_ca_system_score_codex":0.00046477167,"about_ca_system_score_gemma":0.0016023314,"threshold_uncertainty_score":0.7946674},"labels":[],"label_agreement":null},{"id":"W1590091593","doi":"10.22329/il.v33i3.3774","title":"A Serious Flaw in the Collegiate Learning Assessment [CLA] Test","year":2013,"lang":"en","type":"article","venue":"Informal Logic","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Rendering (computer graphics); Logical reasoning; Psychology; Reliability (semiconductor); Mathematics education; Critical thinking; Test validity; Validity; Computer science; Applied psychology; Artificial intelligence; Psychometrics; Developmental psychology","score_opus":0.022408105744773383,"score_gpt":0.3322505504779639,"score_spread":0.30984244473319056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590091593","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39556503,0.000017796381,0.000015961976,0.002193629,0.00015185444,0.0005120989,5.8330806e-7,0.00005823225,0.60148484],"genre_scores_gemma":[0.9937823,0.0000611184,0.0002468349,0.0011160409,0.00013645107,0.00011117477,0.0000044394824,0.0000043129585,0.004537369],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99864036,0.00013061202,0.00022622109,0.000103996805,0.0004760421,0.00042274134],"domain_scores_gemma":[0.9993763,0.00031160927,0.00009301264,0.00010663869,0.00005855862,0.00005388294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010029403,0.000103463644,0.00012334414,0.000059106962,0.00055139227,0.00036950587,0.00044606288,0.00008821885,0.00084661535],"category_scores_gemma":[0.00013369568,0.000069434675,0.000050965176,0.00039888744,0.00013439983,0.0006293348,0.000078099874,0.00033915092,0.0005830287],"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":[0.000007311731,0.00017334777,0.87404424,0.000010935994,0.000016928248,0.000020527606,0.044879206,0.00018277558,0.00006636634,0.06698169,0.0051342854,0.0084823975],"study_design_scores_gemma":[0.00046737504,0.00018276524,0.8248081,0.0000108228,0.0000066695034,0.0000018021547,0.050412726,0.0004971459,0.0000017395985,0.0009521002,0.12247671,0.0001820292],"about_ca_topic_score_codex":0.001992795,"about_ca_topic_score_gemma":0.0010501896,"teacher_disagreement_score":0.59821725,"about_ca_system_score_codex":0.00007660873,"about_ca_system_score_gemma":0.00012818424,"threshold_uncertainty_score":0.9269844},"labels":[],"label_agreement":null},{"id":"W1590196413","doi":"","title":"Individual Assignments and Student Expectancies: Exploring the Learning Conundrum","year":2007,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Psychology; Social psychology; Mathematics education; Cognitive psychology","score_opus":0.0968097770842884,"score_gpt":0.3817578029481843,"score_spread":0.2849480258638959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590196413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86007565,0.000111204696,0.0003035171,0.0004825823,0.00038484973,0.00017548037,1.5842201e-7,0.00007109856,0.13839544],"genre_scores_gemma":[0.99274504,0.00013588567,0.0001036336,0.0001607829,0.00026108755,0.000017390726,6.6563416e-7,0.0000063521725,0.006569151],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985252,0.000090119465,0.00014530015,0.00015859438,0.0007180981,0.00036271426],"domain_scores_gemma":[0.9994096,0.00034265488,0.000051024494,0.000072533345,0.000035974394,0.00008821364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017904398,0.000082279366,0.000087740606,0.00004411345,0.0010002534,0.0003701965,0.00032216444,0.000029637084,0.00025838948],"category_scores_gemma":[0.000084958585,0.000057766865,0.00002463692,0.00022907923,0.00018223678,0.00035058818,0.00020066854,0.00014539858,0.00002896018],"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":[0.0000058991864,0.000040596326,0.8397365,0.0000012745237,0.000049947965,0.0000044217363,0.13188028,0.0000015038461,0.00010714485,0.018611114,0.0005791605,0.00898214],"study_design_scores_gemma":[0.00020299442,0.000028810355,0.54103214,0.0000052134233,0.000012608683,2.1916559e-7,0.41858342,0.0000012513118,0.00006327441,0.00007920718,0.0399005,0.00009037147],"about_ca_topic_score_codex":0.00022978937,"about_ca_topic_score_gemma":0.0006674934,"teacher_disagreement_score":0.2987044,"about_ca_system_score_codex":0.00006144315,"about_ca_system_score_gemma":0.000032754517,"threshold_uncertainty_score":0.7693242},"labels":[],"label_agreement":null},{"id":"W1599466273","doi":"","title":"The nature and impact of teachers’ formative assessment practices","year":2005,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Accountability; Orchestration; Mathematics education; Psychology; Assessment for learning; Pedagogy; Action research; Process (computing); Medical education; Computer science; Political science; Medicine","score_opus":0.026829701479986,"score_gpt":0.45290406753436335,"score_spread":0.4260743660543774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599466273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64734083,0.0002635713,0.000019784757,0.0049758665,0.000057213838,0.00014821702,9.0385697e-7,0.000016519212,0.3471771],"genre_scores_gemma":[0.99530345,0.0004045767,0.00088696484,0.000059305206,0.000115588926,0.0000041813737,5.7974216e-7,0.000002281974,0.0032230862],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99927443,0.00010790568,0.0001035789,0.000068828536,0.0002942753,0.00015100205],"domain_scores_gemma":[0.9992032,0.0004023181,0.00022194261,0.00007121315,0.000058531277,0.00004279513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087252236,0.000054749988,0.000071746355,0.000017757833,0.0004048364,0.00011913344,0.00015410843,0.00006513888,0.00017512128],"category_scores_gemma":[0.00012753879,0.00002918697,0.000046573892,0.00010134663,0.00015577381,0.0005299231,0.000039335464,0.00017489401,0.000004553778],"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":[0.000030945142,0.0001961014,0.59642994,0.000004182598,0.0003213473,4.6538582e-7,0.16136964,0.0000047521157,0.0002812183,0.14757477,0.030051196,0.06373543],"study_design_scores_gemma":[0.0003383474,0.00011338019,0.7863502,0.0000061888136,0.000028136878,3.83703e-7,0.11531771,0.00014529488,0.00004193329,0.00069317967,0.09685799,0.00010726733],"about_ca_topic_score_codex":0.00072329876,"about_ca_topic_score_gemma":0.0018285966,"teacher_disagreement_score":0.3479626,"about_ca_system_score_codex":0.00008222294,"about_ca_system_score_gemma":0.00012514375,"threshold_uncertainty_score":0.31137154},"labels":[],"label_agreement":null},{"id":"W1599897745","doi":"10.18806/tesl.v23i2.53","title":"Effects of Peer Feedback on EFL Student Writers at Different Levels of English Proficiency: A Japanese Context","year":2006,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Psychology; Context (archaeology); Peer evaluation; Mathematics education; English as a foreign language; Peer group; Higher education; Pedagogy; Social psychology","score_opus":0.015254767070093588,"score_gpt":0.284865287494137,"score_spread":0.2696105204240434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599897745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98741275,0.0013313016,0.0000021931226,0.0005260746,0.001797857,0.0003741332,0.000017652934,0.000012210506,0.008525826],"genre_scores_gemma":[0.9949715,0.000015119606,0.000011282324,0.00075192476,0.0006885882,0.0000065393983,0.0000017160485,0.0000131475745,0.00354018],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99625933,0.0002110226,0.00047743617,0.00018049894,0.0024190382,0.0004526589],"domain_scores_gemma":[0.99811476,0.0004189871,0.00040309824,0.00012770007,0.00075217866,0.00018325628],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005624786,0.00018569265,0.00038209427,0.000100501544,0.0003661317,0.00006440729,0.00047164966,0.000068969544,0.0018626302],"category_scores_gemma":[0.00032155626,0.00014892437,0.00012758038,0.00021995071,0.00019637181,0.00009845271,0.000067275716,0.00023113195,0.000001954499],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005846207,0.0033205668,0.3901051,0.0004204182,0.00067924976,0.00031217278,0.178495,0.00015482421,0.019507403,0.009912883,0.39199674,0.0045110253],"study_design_scores_gemma":[0.0022770446,0.00037136083,0.95914525,0.00019590369,0.0000945178,0.0000025089944,0.020422153,0.0000044829562,0.005220189,0.00007715531,0.011877287,0.0003121451],"about_ca_topic_score_codex":0.10735325,"about_ca_topic_score_gemma":0.24607924,"teacher_disagreement_score":0.5690402,"about_ca_system_score_codex":0.00087002484,"about_ca_system_score_gemma":0.0005463428,"threshold_uncertainty_score":0.9990498},"labels":[],"label_agreement":null},{"id":"W1600384676","doi":"","title":"Teaching to the Test: What Every Educator and Policy-Maker Should Know.","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":125,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardized test; Mathematics education; Test (biology); Curriculum; Psychology; Strengths and weaknesses; Norm (philosophy); Medical education; Pedagogy; Medicine; Social psychology; Political science","score_opus":0.03360182513708301,"score_gpt":0.3962923616583372,"score_spread":0.36269053652125416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600384676","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.312189,0.0005581348,0.000004094878,0.67250013,0.0005096623,0.00013230176,0.000010941761,0.0000020891791,0.014093649],"genre_scores_gemma":[0.9812863,0.00020375343,0.0002449032,0.008492419,0.004649378,0.0000048346083,0.0000029625414,0.0000064509913,0.0051089823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991733,0.00006354595,0.00021696682,0.000097193246,0.00021410969,0.00023489053],"domain_scores_gemma":[0.998552,0.0002885508,0.000112087655,0.00006867346,0.0001352547,0.000843433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046475133,0.00008917863,0.00009449381,0.00030894304,0.0008439271,0.00061825133,0.0001708376,0.000053112493,0.00015292768],"category_scores_gemma":[0.0012889557,0.000072945106,0.00003712855,0.00025622523,0.00017019191,0.0005012964,0.000008240929,0.0001754472,0.000015643092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001060136,0.00009891674,0.039327655,0.000008507594,0.00003568161,0.0000034276043,0.068962514,0.000006863689,0.000038266477,0.85451305,0.024934882,0.012059644],"study_design_scores_gemma":[0.00027701078,0.0001953972,0.20976472,0.0001082051,0.000025547028,0.00010619525,0.035896372,5.6737014e-7,0.000013208989,0.025976067,0.7274441,0.00019261561],"about_ca_topic_score_codex":0.03618321,"about_ca_topic_score_gemma":0.14563306,"teacher_disagreement_score":0.828537,"about_ca_system_score_codex":0.00032169133,"about_ca_system_score_gemma":0.021243444,"threshold_uncertainty_score":0.9843052},"labels":[],"label_agreement":null},{"id":"W1604800422","doi":"10.1002/9781118411360.wbcla142","title":"Mixed Methods Research","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Positivism; Parallels; Context (archaeology); Construct (python library); Field (mathematics); Narrative; Epistemology; Sociology; Engineering ethics; Management science; Computer science; Linguistics; Engineering; Geography","score_opus":0.25637731550061194,"score_gpt":0.5739206860344149,"score_spread":0.317543370533803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1604800422","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023349785,0.00037851802,0.00053595245,0.00074024295,0.0010702963,0.00041242852,8.5101095e-7,0.00022643105,0.99663293],"genre_scores_gemma":[0.00001777924,0.0004988368,0.043569695,0.00004397573,0.0012614859,0.000045019144,0.000003219423,0.00012812269,0.9544319],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973652,0.001167507,0.00008966021,0.00022897036,0.0007338262,0.00041488578],"domain_scores_gemma":[0.99925417,0.00031457806,0.000042292624,0.00021379611,0.00006993043,0.00010520791],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027879465,0.000097044496,0.00017147332,0.0002515147,0.00021397622,0.00015894909,0.0005175891,0.00032115864,0.16458361],"category_scores_gemma":[0.00014854952,0.00007923047,0.00005704526,0.00035134304,0.00032111836,0.000036697897,0.00012704615,0.00024897576,0.0072301757],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.3235334e-7,0.000012626867,0.000090583715,0.000003343265,0.00001968069,4.098544e-7,0.00058657135,8.0711837e-10,0.00000444299,0.13098419,0.85268265,0.015615261],"study_design_scores_gemma":[0.000051421073,0.0000074954514,0.00012843266,0.000015578209,0.000004778158,1.5175003e-8,0.0059179906,8.942304e-7,0.000003809056,0.00091838883,0.992842,0.000109205495],"about_ca_topic_score_codex":0.021551581,"about_ca_topic_score_gemma":0.0048618917,"teacher_disagreement_score":0.15735343,"about_ca_system_score_codex":0.000059150138,"about_ca_system_score_gemma":0.00013291213,"threshold_uncertainty_score":0.9935428},"labels":[],"label_agreement":null},{"id":"W16087079","doi":"10.1053/j.semtcvs.2005.04.002","title":"Assessing for Student Success and a Target Class Average: Balancing two grade-related goals facing university instructors and teaching assistants","year":2012,"lang":"en","type":"article","venue":"Seminars in Thoracic and Cardiovascular Surgery","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Grading (engineering); Mathematics education; The arts; Psychology; Medical education; Computer science; Engineering; Political science; Medicine","score_opus":0.02535534479289702,"score_gpt":0.3408351853130464,"score_spread":0.3154798405201494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W16087079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984273,0.011898119,0.0007959479,0.000048039205,0.00059189874,0.00033992642,0.0000065155227,0.00004998652,0.0019965486],"genre_scores_gemma":[0.9968947,0.00198681,0.00081012974,0.000014911981,0.00013410469,0.0000060296493,0.000009023823,0.000019527037,0.0001247609],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99733305,0.0008492251,0.00028395053,0.00041213378,0.0005236787,0.0005979362],"domain_scores_gemma":[0.99874026,0.000716616,0.00012053038,0.00016945493,0.00004349702,0.00020962734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007131025,0.0002209388,0.00061597966,0.00022921113,0.0009794098,0.00030428445,0.00011862717,0.0001612606,0.0000059585414],"category_scores_gemma":[0.00019413634,0.00023373839,0.00024485428,0.00024173384,0.00023951985,0.0012655188,0.00015898669,0.00029174876,3.6022172e-7],"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":[0.000014545642,0.000033796066,0.93907577,0.000066888846,0.00029651597,0.000026306832,0.010320304,0.000017544846,0.000049274735,0.00069173967,0.000025626921,0.049381673],"study_design_scores_gemma":[0.00096096523,0.000015546435,0.8735054,0.00063961523,0.0004259399,0.000028282635,0.11471103,0.0002202633,0.00007261538,0.00027566013,0.008383878,0.0007607649],"about_ca_topic_score_codex":0.0004392694,"about_ca_topic_score_gemma":0.000055817967,"teacher_disagreement_score":0.104390725,"about_ca_system_score_codex":0.00015397549,"about_ca_system_score_gemma":0.00007610246,"threshold_uncertainty_score":0.95315754},"labels":[],"label_agreement":null},{"id":"W1611061022","doi":"","title":"Att bedöma elevers läsförståelse : En jämförelse mellan svenska och kanadensiska bedömningsdiskurser i grundskolans mellanår","year":2013,"lang":"sv","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.016897596670021057,"score_gpt":0.2931017035423877,"score_spread":0.27620410687236663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1611061022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69878155,0.0004691269,0.000044705615,0.013528741,0.003094081,0.0018197949,0.000034296543,0.00040818274,0.28181952],"genre_scores_gemma":[0.82769716,0.001503772,0.00063739746,0.0014392099,0.0020985783,0.000091083486,0.000051423613,0.00011736852,0.16636398],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99189675,0.0008518695,0.0011703053,0.0015294409,0.0020536222,0.0024980013],"domain_scores_gemma":[0.99598384,0.0008511237,0.00051688915,0.0010241176,0.00048427825,0.0011397669],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011920673,0.0011157867,0.001208206,0.00038247017,0.0015217041,0.00122927,0.0017507921,0.00091572327,0.03485923],"category_scores_gemma":[0.00016747654,0.0010149367,0.0007141456,0.0012467516,0.00083622365,0.0010200567,0.00042872928,0.00075229985,0.015128974],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011877574,0.001193113,0.51379895,0.00010997164,0.0017704755,0.00012941302,0.12953246,0.000029315801,0.0029372966,0.020585855,0.31003973,0.019754633],"study_design_scores_gemma":[0.004344703,0.0011982259,0.22404309,0.00021038164,0.0010557959,0.000024771934,0.21543905,0.0008861866,0.0006901787,0.0028753388,0.54524535,0.003986938],"about_ca_topic_score_codex":0.036141634,"about_ca_topic_score_gemma":0.012741481,"teacher_disagreement_score":0.28975585,"about_ca_system_score_codex":0.00089131633,"about_ca_system_score_gemma":0.00059589354,"threshold_uncertainty_score":0.99980754},"labels":[],"label_agreement":null},{"id":"W1620918562","doi":"10.22329/jtl.v4i1.89","title":"An Alternative Vision for Large-scale Assessment in Canada","year":2006,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Scale (ratio); Test (biology); Set (abstract data type); Sample (material); Quality (philosophy); Achievement test; Educational assessment; Standardized test; Psychology; Mathematics education; Medical education; Computer science; Geography; Medicine; Cartography","score_opus":0.011930447431533972,"score_gpt":0.36058651399949543,"score_spread":0.34865606656796144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1620918562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907193,0.00006811875,0.0030656161,0.0007000198,0.00021148112,0.000055420085,5.7849303e-7,0.000003979883,0.005175466],"genre_scores_gemma":[0.99427515,0.00001503029,0.004868591,0.000039040613,0.00041452577,8.340074e-7,0.0000012563581,0.0000046505884,0.0003809165],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988057,0.0004514185,0.00020068683,0.000072668096,0.00030075753,0.000168759],"domain_scores_gemma":[0.999428,0.00024326934,0.00020589578,0.000023886785,0.000046170073,0.000052781215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003109888,0.000050634946,0.00012738712,0.00006483269,0.00055514515,0.00008779244,0.00010058914,0.000021779646,0.000010409445],"category_scores_gemma":[0.00008184703,0.000043704345,0.000029020595,0.0000397512,0.000010965744,0.0002560752,0.000011190518,0.00059402455,8.169634e-8],"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":[0.000025264688,0.00010730117,0.9633623,0.0000059627105,0.0000127388685,0.000011898562,0.016413625,0.0022774665,0.00041604918,0.0027241795,0.0007342265,0.013909026],"study_design_scores_gemma":[0.0014678348,0.0003418462,0.7733987,0.00011398941,0.000021461741,0.0000031792847,0.13225852,0.011789472,0.0000073283027,0.0007024146,0.07972924,0.00016603801],"about_ca_topic_score_codex":0.6249091,"about_ca_topic_score_gemma":0.76086074,"teacher_disagreement_score":0.18996358,"about_ca_system_score_codex":0.00029130717,"about_ca_system_score_gemma":0.00035181188,"threshold_uncertainty_score":0.42697838},"labels":[],"label_agreement":null},{"id":"W1626448709","doi":"10.18806/tesl.v26i1.129","title":"Teachers' Assessment of ESL Students in Mainstream Classes: Challenges, Strategies, and Decision-Making","year":2008,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mainstream; Psychology; Mathematics education; Work (physics); Pedagogy","score_opus":0.035413551529769056,"score_gpt":0.3662058004315097,"score_spread":0.33079224890174064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1626448709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97381973,0.01035966,0.00007543518,0.00042141255,0.00036155747,0.00016241145,0.0000027069177,0.000009928499,0.014787185],"genre_scores_gemma":[0.99358624,0.003975245,0.0017414499,0.00046806602,0.00016405742,0.000003261678,5.6723246e-7,0.000010051759,0.000051075465],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973118,0.00015840471,0.00041333106,0.0001837308,0.0015387373,0.00039399858],"domain_scores_gemma":[0.99902636,0.0003404115,0.00022951493,0.00011485024,0.00010677473,0.00018207125],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011130153,0.00013861267,0.00027531205,0.00014359913,0.00046131312,0.00014089608,0.00045246707,0.000077789,0.0011046099],"category_scores_gemma":[0.000098152945,0.00013036144,0.000040311417,0.0002251154,0.0001530572,0.000418025,0.00008038381,0.00038978428,3.4261723e-7],"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":[0.000043979293,0.0004930128,0.89316803,0.00002402401,0.00018569654,0.0010204918,0.029619198,0.00011137036,0.00003177109,0.011082674,0.009749678,0.05447004],"study_design_scores_gemma":[0.00087827974,0.00007438502,0.906865,0.00016387114,0.000015402755,0.000039348073,0.08102455,0.000028329783,5.0783956e-7,0.0015084378,0.009221215,0.00018066831],"about_ca_topic_score_codex":0.09261115,"about_ca_topic_score_gemma":0.66432226,"teacher_disagreement_score":0.57171106,"about_ca_system_score_codex":0.00077073433,"about_ca_system_score_gemma":0.0046540326,"threshold_uncertainty_score":0.9998085},"labels":[],"label_agreement":null},{"id":"W1628651023","doi":"","title":"Implementation of Peer Reviews: Online Learning","year":2015,"lang":"en","type":"article","venue":"International Journal of Learning Teaching and Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor; University of Ottawa","funders":"","keywords":"CLARITY; Peer review; Technical peer review; Peer feedback; Computer science; Online course; Online learning; Grammar; Subject (documents); Mathematics education; Psychology; World Wide Web; Political science","score_opus":0.2608650624116684,"score_gpt":0.5989500543172764,"score_spread":0.33808499190560803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1628651023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96487707,0.00092926587,0.00012467263,0.02419336,0.0006953,0.00008506062,0.0000012013239,0.000004859683,0.009089231],"genre_scores_gemma":[0.98284066,0.0007838624,0.0024694744,0.000026248765,0.0014652563,0.0000024354467,0.000017097855,0.0000066678153,0.012388272],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99562716,0.0015691456,0.00041046878,0.0000970044,0.0021231743,0.00017301431],"domain_scores_gemma":[0.9957829,0.0010923485,0.00035432813,0.000036989844,0.00258392,0.00014951511],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015687255,0.000058322974,0.00013941045,0.00038310164,0.00035944916,0.00013608832,0.00036186387,0.00003852579,0.0002812509],"category_scores_gemma":[0.011385874,0.000052735624,0.00005874615,0.00013769724,0.00014143347,0.00034025093,0.000078618694,0.0010625862,0.000012215274],"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":[0.00007661951,0.00024171833,0.78447986,0.000011363943,0.000108304754,0.0000025378342,0.085946046,0.0001536511,0.00028333985,0.021270225,0.019771997,0.08765431],"study_design_scores_gemma":[0.00061784347,0.00025161545,0.09773768,0.00016728377,0.000013717958,0.000013907577,0.19149259,0.000044829503,0.0000122075,0.0020764086,0.70748526,0.00008666394],"about_ca_topic_score_codex":0.0015069484,"about_ca_topic_score_gemma":0.00010533724,"teacher_disagreement_score":0.68771327,"about_ca_system_score_codex":0.00023554666,"about_ca_system_score_gemma":0.0007794997,"threshold_uncertainty_score":0.9969416},"labels":[],"label_agreement":null},{"id":"W1654600664","doi":"10.21432/t2j300","title":"Optional online quizzes: College student use and relationship to achievement","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Academic achievement; Psychology; Mathematics education; Comprehension; Cognition; Class (philosophy); Student achievement; Computer science","score_opus":0.026190919804516488,"score_gpt":0.3202131937309054,"score_spread":0.2940222739263889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1654600664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98363566,0.00037195568,0.000049457576,0.015162181,0.00010369822,0.00007161233,0.0000048470984,0.000012298201,0.0005883048],"genre_scores_gemma":[0.9964231,0.000043433454,0.0013097526,0.000041815518,0.000120825265,0.0000012801548,0.0000018892752,0.000004500729,0.0020533537],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99934614,0.000058887916,0.00017472563,0.00008480626,0.00014334817,0.0001920923],"domain_scores_gemma":[0.99945045,0.00010048557,0.000091515976,0.000032240867,0.00013410201,0.00019120243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003681188,0.000056716155,0.00010935626,0.00047551,0.00052848255,0.00007399566,0.00009848527,0.00009256801,0.000029233131],"category_scores_gemma":[0.0002629631,0.00005620502,0.000016056287,0.00030864935,0.00018741867,0.00009796505,0.000017436767,0.00026196838,0.0000022263314],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024993424,0.000013430175,0.9332398,8.6461716e-7,0.000010806026,0.00002426994,0.0006563631,0.000020399786,0.000019273059,0.06503662,0.0005838186,0.00039182283],"study_design_scores_gemma":[0.0003054799,0.00016631668,0.80920464,0.000028244795,0.00001683031,0.000017603648,0.01843893,0.0000036655665,0.0000019290462,0.0011902807,0.17054766,0.00007842788],"about_ca_topic_score_codex":0.003058867,"about_ca_topic_score_gemma":0.0920893,"teacher_disagreement_score":0.16996385,"about_ca_system_score_codex":0.00010688907,"about_ca_system_score_gemma":0.00030783846,"threshold_uncertainty_score":0.9244777},"labels":[],"label_agreement":null},{"id":"W1655149967","doi":"10.22329/jtl.v9i1.3540","title":"Student Washback from Tertiary Standardized English Proficiency Exit Requirements in Taiwan","year":2013,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; sort; Tertiary level; Higher education; Psychology; Medical education; Political science; Computer science; Medicine","score_opus":0.0208192614809386,"score_gpt":0.34683071652552294,"score_spread":0.32601145504458434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1655149967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98284924,0.00036081692,0.0001301751,0.0008598412,0.00045058006,0.00015522317,3.325583e-7,0.000021427188,0.015172363],"genre_scores_gemma":[0.9970256,0.0001258434,0.0014456316,0.00006889335,0.00054851593,0.0000030808355,8.5127e-7,0.00000935909,0.00077219843],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973498,0.0010510123,0.00043907104,0.00014384885,0.000736041,0.00028020435],"domain_scores_gemma":[0.9991629,0.0001760392,0.00034860772,0.000060924922,0.0001298684,0.000121617995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041491534,0.000106589214,0.00024885082,0.0002116921,0.0006275929,0.00031738073,0.00025533396,0.00006434413,0.00022110829],"category_scores_gemma":[0.0008879804,0.00008774129,0.00006989436,0.00013163021,0.00008595833,0.00071165845,0.000072983334,0.0011509034,0.000006572037],"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":[0.00001622664,0.00009560055,0.82094127,0.0000038720873,0.000035726436,0.000009843244,0.16432853,0.000030772484,0.0006725242,0.00008588443,0.00071674073,0.013062997],"study_design_scores_gemma":[0.001631238,0.00018092242,0.6736182,0.00024687915,0.000033542423,0.0000010117291,0.30561173,0.000066059,0.000011143028,0.00031025178,0.018098708,0.0001902883],"about_ca_topic_score_codex":0.0011254157,"about_ca_topic_score_gemma":0.00006511476,"teacher_disagreement_score":0.14732306,"about_ca_system_score_codex":0.00011333655,"about_ca_system_score_gemma":0.000070728434,"threshold_uncertainty_score":0.5000166},"labels":[],"label_agreement":null},{"id":"W1757897301","doi":"10.29173/cmplct17993","title":"Enmeshing Interruption in Assessment of Teacher Education. Response to Bernard Ricca","year":2014,"lang":"en","type":"article","venue":"Complicity An International Journal of Complexity and Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"License; Publication; Permission; Statement (logic); World Wide Web; Library science; Computer science; Political science; Law","score_opus":0.08673746315053754,"score_gpt":0.4580667957143578,"score_spread":0.3713293325638203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1757897301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805104,0.000021227048,0.0030394234,0.005477866,0.0012301771,0.00013656596,0.000002053608,0.0000066619723,0.009575641],"genre_scores_gemma":[0.99048024,0.000039404706,0.008138877,0.00039712255,0.0006281047,0.000006132848,0.000008749417,0.0000053244967,0.00029603377],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982221,0.00053532823,0.00045947803,0.00012995099,0.00053598505,0.00011712585],"domain_scores_gemma":[0.99854547,0.00017116238,0.0003765453,0.00010289257,0.00066497916,0.00013897211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00224745,0.00008444335,0.00018446725,0.00042335343,0.00012257918,0.00013479439,0.0004768639,0.000049382485,0.00012761685],"category_scores_gemma":[0.0003670128,0.00008929253,0.00005389537,0.0001667817,0.00012177466,0.00064294005,0.000060115366,0.00017916628,0.0000025677036],"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":[0.0007288744,0.0033414077,0.58833003,0.0000212006,0.00006138527,4.34017e-7,0.037385397,0.00011306082,0.005125826,0.29289275,0.0016168862,0.07038272],"study_design_scores_gemma":[0.00029315017,0.00017298301,0.963325,0.00013404588,0.000009459831,0.000004919494,0.009044803,0.00023917969,0.000044993812,0.009887935,0.016745534,0.000097973396],"about_ca_topic_score_codex":0.0011446659,"about_ca_topic_score_gemma":0.00058744,"teacher_disagreement_score":0.37499496,"about_ca_system_score_codex":0.00035020712,"about_ca_system_score_gemma":0.0006315675,"threshold_uncertainty_score":0.3641244},"labels":[],"label_agreement":null},{"id":"W1795761960","doi":"10.3968/j.ccc.1923670020110703.162","title":"The IELTS Preparation Washback on Learning and Teaching Outcomes","year":2011,"lang":"en","type":"article","venue":"Cross-cultural communication","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Economic shortage; Test of English as a Foreign Language; Context (archaeology); Psychology; Language education; Linguistics; Geography","score_opus":0.06037046805975251,"score_gpt":0.43459134305866265,"score_spread":0.37422087499891016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1795761960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.779248,0.0001285474,0.0000035058315,0.00086453225,0.000080114594,0.00016576584,2.443539e-7,0.000078776786,0.21943054],"genre_scores_gemma":[0.99033344,0.00050648145,0.0002977528,0.00005717563,0.000038109025,0.000020383195,0.000010426375,0.00000503867,0.008731217],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989951,0.00036415466,0.00015399388,0.000116613,0.00020860604,0.00016149644],"domain_scores_gemma":[0.9991893,0.00031237566,0.00012193824,0.00022563722,0.00011305534,0.000037658774],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00097294984,0.00008108493,0.00007573958,0.000013354435,0.0042354516,0.00063543627,0.00037016565,0.00005955652,0.000028263225],"category_scores_gemma":[0.0004336857,0.00005143775,0.000037493835,0.000043514956,0.00045331882,0.00061203394,0.000110914596,0.0002732817,0.000041584502],"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":[0.00007266898,0.00006476969,0.565893,0.0000033908004,0.000036788122,1.7098812e-7,0.12163955,0.0000037428124,0.00022835004,0.28390756,0.0006835731,0.027466416],"study_design_scores_gemma":[0.00039515735,0.00010120994,0.7500616,0.000027430364,0.00001760092,3.9934503e-7,0.03471605,0.00009138773,0.0001176945,0.0025973201,0.21166378,0.00021037551],"about_ca_topic_score_codex":0.0005535906,"about_ca_topic_score_gemma":0.00067549216,"teacher_disagreement_score":0.28131026,"about_ca_system_score_codex":0.00005628645,"about_ca_system_score_gemma":0.000013729881,"threshold_uncertainty_score":0.9970609},"labels":[],"label_agreement":null},{"id":"W1797460826","doi":"","title":"Putting Rubrics to the Test: The Effect of Rubric-Referenced Peer Assessment on EFL Learners’ Evaluation of Speaking","year":2013,"lang":"en","type":"article","venue":"Journal of academic and applied studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; Formative assessment; Peer assessment; Psychology; Presupposition; Test (biology); Mathematics education; Peer feedback; Pedagogy; Computer science; Linguistics","score_opus":0.08647179667909898,"score_gpt":0.4307727206229517,"score_spread":0.3443009239438527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1797460826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97861034,0.0005669112,0.00003212805,0.008382608,0.00017552031,0.00059493375,0.0000010069691,0.0000036603265,0.011632867],"genre_scores_gemma":[0.99848354,0.0007010775,0.00020077468,0.00011395601,0.0003370497,0.00002174356,1.4808919e-7,0.0000051609486,0.00013656724],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974374,0.00027946642,0.0004463455,0.000102387756,0.0015554666,0.00017889921],"domain_scores_gemma":[0.99638087,0.0024476773,0.0006585619,0.000077660836,0.00039296813,0.000042242387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007503666,0.00011285716,0.0003264719,0.00006833572,0.00038684547,0.000034107128,0.0003164245,0.00006696191,0.000017386701],"category_scores_gemma":[0.0014465316,0.000053767042,0.000068086534,0.0002557083,0.00019789551,0.00009362892,0.00010720303,0.00045817473,0.000002831277],"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":[0.00015159705,0.00015411335,0.3654803,0.00014515776,0.0013346572,7.6078436e-7,0.23984909,0.0021440533,0.02133068,0.011554204,0.03191891,0.32593647],"study_design_scores_gemma":[0.0029950473,0.0015621498,0.59389025,0.0006794518,0.0012361864,0.0000031540687,0.38160527,0.00041995625,0.0045309477,0.007145797,0.0055624587,0.00036934292],"about_ca_topic_score_codex":0.00002997517,"about_ca_topic_score_gemma":0.000009684816,"teacher_disagreement_score":0.32556713,"about_ca_system_score_codex":0.000071814706,"about_ca_system_score_gemma":0.000067737026,"threshold_uncertainty_score":0.29753417},"labels":[],"label_agreement":null},{"id":"W1838922808","doi":"10.22329/celt.v8i0.4256","title":"Performance, Feedback, and Revision: Metacognitive Approaches to Undergraduate Essay Writing","year":2015,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"Bishop's University","keywords":"Metacognition; Writing process; Mathematics education; Academic writing; Psychology; Plan (archaeology); Professional writing; Perception; Pedagogy; Scientific writing; Process (computing); Computer science; Cognition; Linguistics","score_opus":0.09045564680795112,"score_gpt":0.322857496550097,"score_spread":0.23240184974214587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1838922808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6391206,0.00016634258,0.00020899595,0.0017313188,0.000100780155,0.00025844903,6.69538e-7,0.00014874173,0.35826412],"genre_scores_gemma":[0.98610556,0.00013438998,0.0014062166,0.00011368179,0.0002331828,0.000017751097,0.000006497605,0.000022557555,0.011960143],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99768585,0.000812928,0.00021252547,0.00040952058,0.000469826,0.00040936918],"domain_scores_gemma":[0.9989256,0.00048967527,0.00010111886,0.00007925785,0.00008495167,0.0003193708],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0025539242,0.00019460193,0.0002780179,0.00020635828,0.0022090846,0.00044367774,0.00012585556,0.000098195356,0.000012938638],"category_scores_gemma":[0.0010732317,0.00018179268,0.00003468351,0.00035807953,0.00012576126,0.0002667487,0.00012297924,0.00065504416,0.000023415327],"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":[0.00032503862,0.00022052028,0.3599234,0.00009355163,0.00022254378,0.000018898274,0.16488981,0.00036289237,0.00006792068,0.067429,0.0025992263,0.40384722],"study_design_scores_gemma":[0.009275739,0.0034648546,0.115276225,0.0026434732,0.00055883534,0.00003339003,0.511718,0.02389377,0.000103739774,0.004115619,0.32539314,0.00352321],"about_ca_topic_score_codex":0.00013475848,"about_ca_topic_score_gemma":0.0000436714,"teacher_disagreement_score":0.400324,"about_ca_system_score_codex":0.000110529094,"about_ca_system_score_gemma":0.00013482173,"threshold_uncertainty_score":0.9990899},"labels":[],"label_agreement":null},{"id":"W1855174569","doi":"10.55016/ojs/ajer.v60i2.55920","title":"Making the Invisible of Learning Visible: Pre-service Teachers Identify Connections between the Use of Literacy Strategies and their Content Area Assessment Practices","year":2015,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Literacy; Content (measure theory); Mathematics education; Psychology; Content analysis; Pedagogy; Service (business); Sociology; Social science; Business; Marketing; Mathematics","score_opus":0.5367516268674741,"score_gpt":0.5577969117049367,"score_spread":0.021045284837462597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1855174569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.958572,0.0006419585,0.000030690004,0.033042975,0.00015747156,0.00024669358,0.000001872332,6.554273e-7,0.0073057343],"genre_scores_gemma":[0.9968829,0.00027442756,0.00019947797,0.000042883206,0.00029115766,0.000011178742,0.000003026668,0.00000723208,0.0022877147],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99672014,0.0014138806,0.00046435543,0.000117311436,0.0010546355,0.00022968964],"domain_scores_gemma":[0.9618249,0.034727983,0.00095659954,0.00014756942,0.0022402948,0.000102652826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005140351,0.000086074404,0.00018765806,0.00018672667,0.00063593115,0.0007019275,0.00055406947,0.000050725896,0.00032473783],"category_scores_gemma":[0.011108387,0.000048952435,0.000063774634,0.00067452213,0.00043583018,0.0017311557,0.00013291801,0.00062718574,0.0000024848273],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048968173,0.00017562877,0.87799835,0.000020525042,0.00027009717,1.04628356e-7,0.101587564,0.00019279115,0.0002778796,0.01616863,0.0026150206,0.0006444621],"study_design_scores_gemma":[0.00029624262,0.0001991564,0.6029326,0.0001831213,0.00006599741,0.0000048583497,0.35922188,0.00011999422,0.00002889609,0.0017113993,0.035165425,0.00007045418],"about_ca_topic_score_codex":0.011743255,"about_ca_topic_score_gemma":0.0044673653,"teacher_disagreement_score":0.27506575,"about_ca_system_score_codex":0.000121236786,"about_ca_system_score_gemma":0.002496725,"threshold_uncertainty_score":0.99722147},"labels":[],"label_agreement":null},{"id":"W1858612200","doi":"","title":"The Effect of Self-assessment on Iranian EFL Learners` Reading Comprehension Skill","year":2015,"lang":"en","type":"article","venue":"Journal of academic and applied studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Learner autonomy; Reading comprehension; Autonomy; Test (biology); Psychology; Language assessment; Reading (process); Mathematics education; Comprehension; Self-assessment; Process (computing); Pedagogy; Language education; Computer science; Comprehension approach; Linguistics","score_opus":0.041729942879182816,"score_gpt":0.3929681490143589,"score_spread":0.3512382061351761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1858612200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789277,0.0023279556,0.000008417603,0.001624457,0.0003785796,0.00019069016,2.9144286e-7,0.000012579082,0.016529363],"genre_scores_gemma":[0.9906607,0.008613885,0.00016174039,0.00006324572,0.00038443736,0.0000033003114,9.493147e-8,0.0000059913064,0.00010659475],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9984997,0.00018159342,0.00035971473,0.00009703089,0.00066273485,0.00019922468],"domain_scores_gemma":[0.9983033,0.0010248964,0.00043042164,0.000056868586,0.00008473097,0.00009981098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024263875,0.000116650794,0.00037080533,0.00005616708,0.00048709792,0.000025709698,0.00020913684,0.00008633179,0.0000011101421],"category_scores_gemma":[0.00009518995,0.00006430281,0.00006462332,0.0001298166,0.0002443228,0.00007873768,0.00008085295,0.00046828267,0.0000019089105],"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":[0.002131519,0.0002519809,0.4954558,0.00020721686,0.0027665005,0.000020658854,0.2860542,0.00021926904,0.00688048,0.09463906,0.050570562,0.060802765],"study_design_scores_gemma":[0.011286682,0.005239876,0.13915952,0.00088865054,0.00092473015,0.000017471997,0.74648076,0.00006420691,0.0031680057,0.007061324,0.084941216,0.00076753617],"about_ca_topic_score_codex":0.0000050263,"about_ca_topic_score_gemma":0.0000020201637,"teacher_disagreement_score":0.4604266,"about_ca_system_score_codex":0.00010502754,"about_ca_system_score_gemma":0.000062293184,"threshold_uncertainty_score":0.37464124},"labels":[],"label_agreement":null},{"id":"W1888282162","doi":"10.5539/ies.v8n11p193","title":"Teachers’ Knowledge and Readiness towards Implementation of School Based Assessment in Secondary Schools","year":2015,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Likert scale; Knowledge level; Psychology; Mathematics education; School teachers; Perception; Situated; Scale (ratio); Class (philosophy); Pedagogy; Computer science; Developmental psychology; Geography","score_opus":0.12709263475145594,"score_gpt":0.5309250401396273,"score_spread":0.40383240538817133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888282162","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9147028,0.0012558128,0.00007485581,0.010158854,0.002521162,0.00029686486,0.0000085819065,0.00002235009,0.07095876],"genre_scores_gemma":[0.9956618,0.00020742403,0.0019420742,0.00013426277,0.00022993286,0.000111832196,0.000022460052,0.000005251243,0.001684968],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989572,0.00012150677,0.0002771974,0.00016098362,0.00037197475,0.000111142006],"domain_scores_gemma":[0.99846756,0.00007775916,0.00013736905,0.000065571345,0.0011733499,0.0000783711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090730505,0.000082106984,0.00014154633,0.00022520307,0.00007747358,0.000053070835,0.00015312037,0.000033274944,0.00019491895],"category_scores_gemma":[0.00040364836,0.00008191989,0.000025269812,0.00020682385,0.00009704286,0.00035925585,0.000059769965,0.00012350532,0.000009945842],"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":[0.000010178461,0.00027898225,0.8992829,0.000014197626,0.000092317416,2.8237386e-7,0.034333006,0.000002042884,0.00004387112,0.009425322,0.017461488,0.039055433],"study_design_scores_gemma":[0.00067439716,0.00002634686,0.7130246,0.000044511136,0.000011146233,1.6394708e-7,0.25125375,0.0000087559865,0.000051384788,0.001591803,0.0332278,0.00008532587],"about_ca_topic_score_codex":0.0022163156,"about_ca_topic_score_gemma":0.0024597517,"teacher_disagreement_score":0.21692075,"about_ca_system_score_codex":0.0005774291,"about_ca_system_score_gemma":0.003160538,"threshold_uncertainty_score":0.56066585},"labels":[],"label_agreement":null},{"id":"W1892621048","doi":"10.5539/hes.v5n5p50","title":"Multiple-Choice Testing Using Immediate Feedback—Assessment Technique (IF AT®) Forms: Second-Chance Guessing vs. Second-Chance Learning?","year":2015,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Southern Connecticut State University","keywords":"Multiple choice; Reading (process); Mathematics education; Order (exchange); Computer science; Psychology; Cognitive psychology; Artificial intelligence; Linguistics","score_opus":0.1349722425459681,"score_gpt":0.4323272447495154,"score_spread":0.29735500220354727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1892621048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9431852,0.003743923,0.00018611347,0.0013817541,0.004925927,0.0009703733,0.000006837305,0.00038320944,0.045216627],"genre_scores_gemma":[0.95651895,0.00014970482,0.008714484,0.00048486903,0.0016873949,0.0004299567,0.000016449205,0.00005228383,0.03194593],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99689513,0.00031034302,0.00057649444,0.0006489401,0.0008111731,0.0007579431],"domain_scores_gemma":[0.99651045,0.0010812245,0.0006481127,0.00029419275,0.0012086242,0.00025738426],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0014052104,0.00038454565,0.0005138372,0.00019887666,0.0018223941,0.00023299278,0.00038502656,0.00017039115,0.0003895673],"category_scores_gemma":[0.00056734384,0.00037914343,0.00010051377,0.0008340231,0.00040778416,0.0008838421,0.0003394189,0.00040120413,0.00007182085],"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":[0.00003819281,0.00043416567,0.94614744,0.00018865752,0.00023488674,0.000003706298,0.030310316,0.00010024836,0.0051106038,0.0018518068,0.0142729785,0.0013070065],"study_design_scores_gemma":[0.001380374,0.00017802216,0.4754463,0.00056696456,0.00012584147,0.0000054976167,0.093903944,0.00015729135,0.0008222573,0.0016980618,0.4244508,0.0012646242],"about_ca_topic_score_codex":0.0004378056,"about_ca_topic_score_gemma":0.00070537446,"teacher_disagreement_score":0.47070113,"about_ca_system_score_codex":0.001645186,"about_ca_system_score_gemma":0.0009248538,"threshold_uncertainty_score":0.99986607},"labels":[],"label_agreement":null},{"id":"W1893911515","doi":"10.1017/cbo9780511611186.006","title":"Verbal Reports as Data for Cognitive Diagnostic Assessment","year":2007,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Strengths and weaknesses; Cognition; Distributive property; Test (biology); Cognitive psychology; Cognitive skill; Subject (documents); Scale (ratio); Mathematics education; Social psychology; Computer science; Mathematics","score_opus":0.0876519378095488,"score_gpt":0.3478663010064851,"score_spread":0.26021436319693625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1893911515","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012801684,0.00012977218,0.001293567,0.00004034544,0.0010561999,0.0018012283,0.0009066983,0.0001519527,0.99449223],"genre_scores_gemma":[0.0048189205,0.00030811442,0.00026064238,0.00012072309,0.00075567263,0.0000035983992,0.0010808732,0.00005057299,0.99260086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973119,0.000066856024,0.00030536004,0.00093657704,0.00084568927,0.00053361716],"domain_scores_gemma":[0.99655265,0.0014841048,0.00047722852,0.0007760274,0.00041774227,0.000292226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00085669203,0.0003783389,0.0004691475,0.00016958761,0.00082784897,0.00014712816,0.0009883767,0.0004982628,0.000042478372],"category_scores_gemma":[0.00028153777,0.00047505533,0.0002144901,0.000016377935,0.0005860561,0.00025874673,0.00087842386,0.00042500117,0.000017719361],"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":[0.000098496035,0.000038756323,0.000116381336,0.00004593069,0.00037887713,0.0013406388,0.00038487744,1.2702665e-7,0.00000123006,0.9102406,0.084816664,0.0025374468],"study_design_scores_gemma":[0.0006784715,0.000088384935,0.0001887747,0.00023845547,0.0008036508,0.0000068225336,0.001438309,0.000007161304,0.0000058793603,0.00007048243,0.99591917,0.00055442954],"about_ca_topic_score_codex":0.0010018661,"about_ca_topic_score_gemma":0.00014240698,"teacher_disagreement_score":0.91110253,"about_ca_system_score_codex":0.00046650614,"about_ca_system_score_gemma":0.00084105495,"threshold_uncertainty_score":0.9997701},"labels":[],"label_agreement":null},{"id":"W1893952289","doi":"10.18296/am.0079","title":"Assessment for learning as a participative pedagogy","year":2010,"lang":"en","type":"article","venue":"Assessment Matters","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Victoria Park","funders":"","keywords":"Computer science; Psychology; Pedagogy; Mathematics education","score_opus":0.0329168317974783,"score_gpt":0.46042971779549835,"score_spread":0.42751288599802006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1893952289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7033298,0.000009004061,0.009810407,0.04434057,0.0030045006,0.0018611758,0.000009775994,0.00039168898,0.2372431],"genre_scores_gemma":[0.97452384,0.000021172329,0.014277594,0.0026338242,0.00042212367,0.00054547074,0.00003174381,0.000037367907,0.007506882],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750924,0.00023795576,0.0003280191,0.00044340707,0.00072843,0.0007529339],"domain_scores_gemma":[0.9985061,0.00062712084,0.00021880005,0.00023685281,0.00017532181,0.00023575377],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014764345,0.0002263789,0.00028867545,0.00011983252,0.0010616216,0.00034051604,0.00042462623,0.00013453509,0.002251415],"category_scores_gemma":[0.0001159225,0.00022759933,0.00016967786,0.00022599813,0.00026374092,0.0003955069,0.00009678309,0.0005313048,0.00014220923],"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":[0.000042358308,0.0005650228,0.5171442,0.00004468415,0.00030103544,0.000014514689,0.017590769,0.000045232133,0.01769679,0.40818557,0.027482579,0.0108872205],"study_design_scores_gemma":[0.002205999,0.00051719806,0.32855666,0.00003503971,0.00020149855,0.0000014085804,0.045485083,0.0007720165,0.00023495089,0.010339889,0.6107634,0.0008869259],"about_ca_topic_score_codex":0.0010355235,"about_ca_topic_score_gemma":0.0014654256,"teacher_disagreement_score":0.58328074,"about_ca_system_score_codex":0.00017231716,"about_ca_system_score_gemma":0.0006424806,"threshold_uncertainty_score":0.9986607},"labels":[],"label_agreement":null},{"id":"W1916237854","doi":"10.24908/pceea.v0i0.5778","title":"Using Student Focus Groups to Support the Validation of Rubrics for Large Scale Undergraduate Independent Research Projects","year":2015,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Rubric; Capstone; Focus group; Scale (ratio); Psychology; Focus (optics); Medical education; Computer science; Mathematics education; Sociology; Medicine","score_opus":0.0932519063745481,"score_gpt":0.39171820876125646,"score_spread":0.29846630238670835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1916237854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97613823,0.000025057801,0.00012977199,0.013714214,0.0014913486,0.0019092811,0.000024297959,0.000028740553,0.006539057],"genre_scores_gemma":[0.9969308,0.0000050047,0.0007713762,0.000067142464,0.00030354926,0.00011296171,0.0000051511342,0.000018712813,0.0017853342],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99789,0.000038326252,0.00027545754,0.00017096712,0.0011961473,0.00042910877],"domain_scores_gemma":[0.9971228,0.00012494955,0.00029071863,0.00009283382,0.002143934,0.00022472293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004849566,0.00009354758,0.00013827204,0.00030861446,0.00047839974,0.0001887432,0.0005179899,0.00011024965,0.0000060044904],"category_scores_gemma":[0.0019620983,0.00008148047,0.00006900647,0.0010440013,0.000026439422,0.00023875458,0.00006587894,0.00016707223,0.0000035735225],"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":[0.000013420422,0.00027800986,0.7175593,0.00012484523,0.00013966743,4.1992145e-8,0.124799185,0.0006778915,0.0015398756,0.09555819,0.05894585,0.00036372413],"study_design_scores_gemma":[0.002355052,0.0004393279,0.51921326,0.0004905816,0.00040109258,0.0000019494332,0.2981144,0.0026742823,0.01325234,0.011247119,0.15066423,0.0011463765],"about_ca_topic_score_codex":0.015840618,"about_ca_topic_score_gemma":0.03613048,"teacher_disagreement_score":0.19834603,"about_ca_system_score_codex":0.0036808914,"about_ca_system_score_gemma":0.0022955313,"threshold_uncertainty_score":0.990713},"labels":[],"label_agreement":null},{"id":"W1928825815","doi":"10.22329/celt.v5i0.3423","title":"12. Undergraduate Essay Writing: Online and Face-to-Face Peer Reviews","year":2012,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Peer review; Peer feedback; Face-to-face; Peer evaluation; Face (sociological concept); Computer science; Psychology; Mathematics education; Online discussion; Peer instruction; Web application; Medical education; Multimedia; World Wide Web; Higher education; Sociology; Chemistry; Medicine; Social science","score_opus":0.03992110082034801,"score_gpt":0.36285928733884043,"score_spread":0.32293818651849243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1928825815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75792104,0.0019491455,0.0010062845,0.009294003,0.0004170577,0.0006957032,0.0000042036963,0.00032446618,0.22838812],"genre_scores_gemma":[0.9176538,0.0006386486,0.0009662867,0.0002453712,0.0003856216,0.000016350066,0.000014549669,0.000024191828,0.08005516],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99733526,0.0010433473,0.00026596524,0.0003203605,0.00045643258,0.000578669],"domain_scores_gemma":[0.99887526,0.0005083875,0.00013427789,0.000108257045,0.00005374008,0.00032005296],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002889387,0.00021254015,0.0003278257,0.00015096672,0.0022258745,0.0003055321,0.00014950355,0.00011489624,0.000046841484],"category_scores_gemma":[0.0019210553,0.00019541277,0.000050863506,0.00019296896,0.00009346299,0.00024012476,0.00010923727,0.0008173066,0.000038086455],"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":[0.000090353686,0.0005123931,0.6032405,0.00009548878,0.00011949195,0.0000062413287,0.20384671,0.00008371217,0.0006940494,0.04651029,0.016218903,0.1285819],"study_design_scores_gemma":[0.0007832374,0.00018214721,0.04655789,0.00031855365,0.000065730615,0.0000032027617,0.030674187,0.00031840068,0.000007645679,0.00024075629,0.9203228,0.00052545464],"about_ca_topic_score_codex":0.00025724986,"about_ca_topic_score_gemma":0.00021941778,"teacher_disagreement_score":0.9041039,"about_ca_system_score_codex":0.000103492916,"about_ca_system_score_gemma":0.000053944117,"threshold_uncertainty_score":0.9990731},"labels":[],"label_agreement":null},{"id":"W1929426705","doi":"10.26522/brocked.v15i2.74","title":"Principles for Effective ClassroomAssessment","year":2006,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Variety (cybernetics); Zeitgeist; Service (business); Psychology; Mathematics education; Computer science; Engineering ethics; Political science; Engineering; Artificial intelligence","score_opus":0.022251610050161026,"score_gpt":0.3689551073058239,"score_spread":0.3467034972556629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1929426705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5697957,0.0008716189,0.01728004,0.011162022,0.009160794,0.0023533811,0.000005620492,0.00012898883,0.38924178],"genre_scores_gemma":[0.9423391,0.00004987439,0.0066418448,0.00018395697,0.005204001,0.00017138003,0.000009842934,0.000012916024,0.045387063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901986,0.000102450154,0.00021743277,0.00011403797,0.00030934712,0.00023686036],"domain_scores_gemma":[0.9991909,0.00015022003,0.00018520374,0.000061240324,0.0002914018,0.00012098775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033945774,0.00007590785,0.00008973568,0.00008339654,0.0008849025,0.00025910852,0.00017196462,0.000049950406,0.00019054473],"category_scores_gemma":[0.000137747,0.00007111172,0.000087615554,0.00013337833,0.000038484035,0.0002367416,0.000013047389,0.00010100749,0.000021937458],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005415916,0.0012026104,0.28244463,0.00002451897,0.000072204195,7.646362e-7,0.004872919,0.00006562953,0.0011350769,0.298791,0.36276186,0.04857465],"study_design_scores_gemma":[0.0003133469,0.00004813613,0.21347117,0.00001868915,0.000022365428,0.0000039168513,0.0078280475,0.000006543655,0.000062784035,0.00778106,0.7703411,0.00010283963],"about_ca_topic_score_codex":0.00010529115,"about_ca_topic_score_gemma":0.00026574355,"teacher_disagreement_score":0.40757924,"about_ca_system_score_codex":0.0003104214,"about_ca_system_score_gemma":0.0011007342,"threshold_uncertainty_score":0.6806044},"labels":[],"label_agreement":null},{"id":"W1951727650","doi":"10.3968/j.hess.1927024020110102.010","title":"Alternative Assessment in the Post-Method Era: Pedagogic Implications","year":2011,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Operationalization; Context (archaeology); Mathematics education; Process (computing); Summative assessment; Psychology; Engineering ethics; Computer science; Pedagogy; Epistemology; Engineering","score_opus":0.10639265693083012,"score_gpt":0.48971712777315773,"score_spread":0.3833244708423276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951727650","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11474796,0.000019165152,0.00014736113,0.005483563,0.0007998808,0.00036901658,0.0000027518336,0.000017754031,0.87841254],"genre_scores_gemma":[0.9931957,0.000010806881,0.0037477808,0.00060085306,0.00028018132,0.00008407038,0.0000021469946,0.0000033346437,0.0020751238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984581,0.00023576728,0.00019742908,0.00022035361,0.0006340384,0.00025432714],"domain_scores_gemma":[0.9991321,0.00011927653,0.00017620857,0.00014159725,0.00037851048,0.00005229308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018928916,0.00007139856,0.00009518371,0.00013395757,0.0007958613,0.00007582445,0.00093465904,0.000041073665,0.00078836695],"category_scores_gemma":[0.00004485555,0.00005679639,0.000045235185,0.0013152835,0.0007511098,0.0004143831,0.00005167821,0.00013630884,0.000015947899],"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":[0.0000015341029,0.00026430143,0.038537934,0.0000012684303,0.0000021086864,5.5251288e-8,0.09219598,8.821814e-8,0.00041755283,0.8665196,0.0002687665,0.0017908318],"study_design_scores_gemma":[0.000066864995,0.0000217302,0.9440675,0.0000036178776,0.000007023171,1.1237721e-7,0.029665481,7.614698e-7,0.000034147484,0.01759029,0.008472353,0.00007014576],"about_ca_topic_score_codex":0.005253665,"about_ca_topic_score_gemma":0.000107208805,"teacher_disagreement_score":0.90552956,"about_ca_system_score_codex":0.00021682569,"about_ca_system_score_gemma":0.0015556196,"threshold_uncertainty_score":0.86320657},"labels":[],"label_agreement":null},{"id":"W1953748391","doi":"10.5539/elt.v8n12p27","title":"Toward Differentiated Assessment in a Public College in Oman","year":2015,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Differentiated instruction; Psychology; Alternative assessment; Mathematics education; Pedagogy; Medical education","score_opus":0.05231859139052725,"score_gpt":0.3578362767086905,"score_spread":0.30551768531816326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1953748391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78681105,0.00007331218,0.000033530054,0.00055886956,0.0004929848,0.0002534681,0.0000047194694,0.00014141276,0.21163064],"genre_scores_gemma":[0.99792284,0.0000059632225,0.0005368416,0.00009077484,0.00036482184,0.000034006167,0.000024120296,0.000016179949,0.0010044764],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9975988,0.0007823741,0.00027136583,0.00026498787,0.00058067124,0.0005017746],"domain_scores_gemma":[0.99941975,0.00013783576,0.0000707755,0.00016141358,0.00003716503,0.00017308808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026561846,0.00013920836,0.00023137456,0.00029222117,0.00013350183,0.00019456468,0.00039699912,0.000107535656,0.00016001619],"category_scores_gemma":[0.00097424985,0.00013894033,0.000047451587,0.0004515449,0.00005326782,0.0005004245,0.00012462297,0.00062309654,0.0000090301355],"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":[0.0000064343008,0.00026863115,0.34122318,0.000005240742,0.000010816591,0.00010431561,0.6233333,0.0000038182307,0.00002823225,0.032844134,0.0008342311,0.0013376524],"study_design_scores_gemma":[0.0019521973,0.000035039437,0.08711125,0.000046733385,0.0000066721996,3.3847485e-7,0.9005794,0.00030264596,0.0000046038344,0.0003511854,0.009330341,0.00027960676],"about_ca_topic_score_codex":0.0056956443,"about_ca_topic_score_gemma":0.015826473,"teacher_disagreement_score":0.2772461,"about_ca_system_score_codex":0.0005984148,"about_ca_system_score_gemma":0.00024126122,"threshold_uncertainty_score":0.8831544},"labels":[],"label_agreement":null},{"id":"W1961884281","doi":"10.24908/pceea.v0i0.5908","title":"Peer Review as an Active Learning Strategy in a Large First Year Course","year":2015,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Rubric; CLARITY; Peer feedback; Mathematics education; Critical thinking; Presentation (obstetrics); Competence (human resources); Class (philosophy); Discipline; Peer assessment; Psychology; Constructive criticism; Active learning (machine learning); Computer science; Criticism; Pedagogy; Medicine; Sociology","score_opus":0.0216094110134129,"score_gpt":0.3225431984446856,"score_spread":0.3009337874312727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1961884281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7250151,0.00068117277,0.0000017535814,0.06745449,0.0016842055,0.0012357678,0.000019693007,0.00012599186,0.20378181],"genre_scores_gemma":[0.98116136,0.00011046874,0.00006165531,0.00020468887,0.00020214794,0.000037414597,0.000011236257,0.000014534674,0.018196516],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986621,0.000020155052,0.00016971679,0.00013400592,0.0007212235,0.00029277557],"domain_scores_gemma":[0.9982046,0.00003110239,0.00022025901,0.00004771998,0.0012479872,0.00024833647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019270099,0.000086052656,0.00013355934,0.000115946226,0.00019572169,0.000109631044,0.0002725758,0.0001065758,0.00008245675],"category_scores_gemma":[0.0035647296,0.0000899501,0.000042425567,0.00056068646,0.000014504921,0.00041123407,0.000015766665,0.00023485937,0.00002345101],"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":[0.0000039198812,0.00017091226,0.80065316,0.00015809093,0.00005340285,1.5782369e-7,0.034069087,0.00019927569,0.00002015843,0.04076927,0.12329481,0.0006077782],"study_design_scores_gemma":[0.00046330437,0.000043896118,0.5034011,0.00061177346,0.00006926212,4.7894935e-7,0.049429387,0.00030692553,0.00003256161,0.0005475206,0.44475588,0.00033790915],"about_ca_topic_score_codex":0.026100792,"about_ca_topic_score_gemma":0.11821136,"teacher_disagreement_score":0.32146108,"about_ca_system_score_codex":0.0023538396,"about_ca_system_score_gemma":0.001804261,"threshold_uncertainty_score":0.98038447},"labels":[],"label_agreement":null},{"id":"W1963737077","doi":"10.3138/cmlr.1705.415","title":"Adapting the CEFR for the Classroom Assessment of Young Learners’ Writing","year":2013,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Literacy; Assessment for learning; Mathematics education; Scale (ratio); Psychology; Pedagogy; Computer science; Formative assessment; Geography","score_opus":0.027825998353215798,"score_gpt":0.309119495218328,"score_spread":0.2812934968651122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963737077","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78105533,0.13509701,0.0019045433,0.018346496,0.0007016746,0.0057753865,0.00034240392,0.00013604459,0.056641094],"genre_scores_gemma":[0.9879216,0.006909588,0.0011700587,0.00082182814,0.00050618086,0.00030102913,0.00003764068,0.00004281462,0.0022892386],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9978344,0.00032916764,0.00043070057,0.00030122796,0.00019181584,0.0009126739],"domain_scores_gemma":[0.9973788,0.0012277781,0.0002495734,0.000457381,0.00029539753,0.0003910521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019512702,0.00022293629,0.00039789214,0.000092405804,0.0009644077,0.00018289972,0.0008649448,0.000094016934,0.0003109563],"category_scores_gemma":[0.0010091172,0.00015137161,0.00023424874,0.00035564008,0.0004296703,0.00021147581,0.00005203312,0.00025853264,0.000010652092],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009088396,0.00008347882,0.09640813,0.004359743,0.0008514463,0.0001765582,0.33285746,0.00009314512,0.006874702,0.075305775,0.022623155,0.4603573],"study_design_scores_gemma":[0.00095040415,0.00016618958,0.22145343,0.0074090343,0.0009770343,0.00008847416,0.5299326,0.015142108,0.00003239363,0.0024309838,0.21982795,0.0015893569],"about_ca_topic_score_codex":0.5232076,"about_ca_topic_score_gemma":0.81963354,"teacher_disagreement_score":0.45876795,"about_ca_system_score_codex":0.0005305623,"about_ca_system_score_gemma":0.00045258267,"threshold_uncertainty_score":0.7417542},"labels":[],"label_agreement":null},{"id":"W1965935538","doi":"10.1021/ed8000107","title":"Constructing the Components of a Lab Report Using Peer Review","year":2009,"lang":"en","type":"article","venue":"Journal of Chemical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Island University; University of Victoria","funders":"","keywords":"Protocol (science); Workload; Class (philosophy); Style (visual arts); Computer science; Process (computing); Mathematics education; Peer evaluation; Quality (philosophy); Multimedia; Psychology; Higher education; Programming language; Medicine; Artificial intelligence; Operating system; Physics","score_opus":0.07177206871327357,"score_gpt":0.44168495173929634,"score_spread":0.36991288302602277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965935538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96225536,0.001572345,0.000018681201,0.023312712,0.00049652875,0.00009171708,2.1749113e-7,0.0000024801097,0.0122499745],"genre_scores_gemma":[0.99690723,0.00017874554,0.0017867528,0.00038072382,0.00049586286,2.570252e-7,0.000002068833,0.0000016623092,0.00024668817],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988471,0.00005709612,0.0003734505,0.000040318864,0.000610184,0.00007183925],"domain_scores_gemma":[0.9984568,0.00006490889,0.00065393676,0.00006012281,0.00072316156,0.000041120886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013948075,0.000036079742,0.00014088687,0.000027747179,0.000054765547,0.000020202206,0.00015287849,0.000027173344,0.00005962737],"category_scores_gemma":[0.0010302644,0.000024933306,0.00007596314,0.00019516968,0.0000740708,0.00012424178,0.0000078475605,0.00011472487,6.0992625e-7],"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":[0.00011852781,0.0023918103,0.18799426,0.00047559428,0.00029331766,0.000026602522,0.03714575,0.000002675477,0.32207137,0.023870215,0.21275279,0.21285708],"study_design_scores_gemma":[0.0028513186,0.00038674643,0.1292316,0.023412636,0.002811648,0.0033493584,0.15786172,0.00013841678,0.07321937,0.045065872,0.56002265,0.0016486539],"about_ca_topic_score_codex":0.00003747507,"about_ca_topic_score_gemma":5.580005e-7,"teacher_disagreement_score":0.34726986,"about_ca_system_score_codex":0.00010036453,"about_ca_system_score_gemma":0.00036317058,"threshold_uncertainty_score":0.12333971},"labels":[],"label_agreement":null},{"id":"W1969883013","doi":"10.1145/2676723.2677278","title":"Mechanical TA","year":2015,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Class (philosophy); Computer science; Process (computing); Mechanical design; Quality (philosophy); Human–computer interaction; Mathematics education; Multimedia; Psychology; Artificial intelligence; Engineering; Mechanical engineering; Programming language; Physics","score_opus":0.0998424434789948,"score_gpt":0.4038429837962849,"score_spread":0.3040005403172901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969883013","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028868722,0.000011898146,0.00037985595,0.0033036645,0.0003801784,0.000055219167,1.0527863e-7,0.000081241116,0.9669191],"genre_scores_gemma":[0.96326196,0.000006316646,0.0010809671,0.00027758427,0.00025160468,0.0000021711576,4.1912583e-7,0.0000019607057,0.03511702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99948335,0.000034363016,0.000042398548,0.00005993608,0.00026549818,0.000114463735],"domain_scores_gemma":[0.9997779,0.000021099451,0.000008836736,0.00004772552,0.000035929257,0.000108505],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003913005,0.00002364097,0.00003727495,0.000010401806,0.000072065646,0.000037620463,0.00012254843,0.000028649767,0.0009381362],"category_scores_gemma":[0.00006716468,0.0000194082,0.000016904249,0.00008551622,0.000032603217,0.00007842248,0.000028655813,0.000025975907,0.0006040181],"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":[0.0000035623302,0.00003201508,0.009064434,2.0175489e-7,0.000005035604,0.0000015806526,0.0043033836,1.2173878e-7,0.000036313384,0.8726172,0.112295955,0.0016401993],"study_design_scores_gemma":[0.0003319384,0.000034208933,0.0020080945,0.000001263962,0.000005664842,1.3033277e-7,0.026128018,0.000026885855,0.000053042426,0.016934352,0.9543753,0.0001010529],"about_ca_topic_score_codex":0.00053927244,"about_ca_topic_score_gemma":0.00064744544,"teacher_disagreement_score":0.9343932,"about_ca_system_score_codex":0.000028707662,"about_ca_system_score_gemma":0.00007110145,"threshold_uncertainty_score":0.99997514},"labels":[],"label_agreement":null},{"id":"W1975230259","doi":"10.1080/1360144042000277900","title":"A Learning‐centred Faculty Certificate Programme on University Teaching","year":2003,"lang":"en","type":"article","venue":"The International Journal for Academic Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pedagogy; Certificate; Higher education; Sociology; Faculty development; Mathematics education; Professional development; Psychology; Political science; Computer science","score_opus":0.19423080715050173,"score_gpt":0.39890678247484423,"score_spread":0.2046759753243425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975230259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85689837,0.00011499171,0.002248644,0.034118466,0.006068409,0.0010728278,0.000007549611,0.00017551194,0.099295214],"genre_scores_gemma":[0.9405113,0.00014731238,0.0017500409,0.0003244547,0.00036246824,0.000006118844,0.000011620831,0.000010075324,0.05687661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983726,0.00018682143,0.00020659258,0.00013377158,0.0007857949,0.00031442882],"domain_scores_gemma":[0.9993273,0.00017536862,0.000187523,0.000037427002,0.0001648375,0.000107530796],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0017651366,0.000093721166,0.00008057757,0.00008082523,0.0014178151,0.00013954606,0.0007948198,0.00007253046,0.00009586929],"category_scores_gemma":[0.0004973269,0.000069903894,0.000078533194,0.000069430695,0.00006466622,0.00014272203,0.000045028963,0.00071916054,0.00005114008],"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":[0.0007411346,0.00042483475,0.054247554,0.0000070428246,0.0012667862,0.000053731463,0.22612791,0.00038797557,0.00080558745,0.39410558,0.0775307,0.24430117],"study_design_scores_gemma":[0.00053155515,0.000020419766,0.002769815,0.000028258944,0.000010804231,0.000007625831,0.021218227,0.00001722102,0.00015403464,0.0010835093,0.97405535,0.000103168946],"about_ca_topic_score_codex":0.000024222845,"about_ca_topic_score_gemma":0.00001724433,"teacher_disagreement_score":0.89652467,"about_ca_system_score_codex":0.0006891401,"about_ca_system_score_gemma":0.0003552126,"threshold_uncertainty_score":0.9998822},"labels":[],"label_agreement":null},{"id":"W1975314479","doi":"10.3138/cmlr.64.1.199","title":"Assessment for Learning: Integrating Assessment, Teaching, and Learning in the ESL/EFL Writing Classroom","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Assessment for learning; Mathematics education; Writing assessment; Pedagogy; Psychology; Computer science; Formative assessment","score_opus":0.02022232402502297,"score_gpt":0.33829144772885,"score_spread":0.318069123703827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975314479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86759555,0.022448078,0.0039985976,0.0027234217,0.0001996424,0.0018085594,0.0000366318,0.0001353617,0.10105414],"genre_scores_gemma":[0.98504394,0.0026792753,0.0087120915,0.0010037343,0.00044151407,0.0001035845,0.00011915795,0.000052710675,0.0018439861],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99625957,0.00124012,0.000533979,0.00048658648,0.0002195978,0.001260136],"domain_scores_gemma":[0.9966921,0.0021798585,0.00024705235,0.00024326949,0.00012471904,0.00051300647],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.011205886,0.00030776928,0.0004978601,0.00029088216,0.0016541462,0.00032153624,0.00054366764,0.00015219986,0.000055795794],"category_scores_gemma":[0.0027930527,0.0002671605,0.00014825507,0.00037800794,0.00024163308,0.0002617735,0.000047813028,0.0013773713,0.000002277324],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074824984,0.00006183634,0.25741336,0.0016591778,0.00010756023,0.0006914184,0.25323048,0.000017148419,0.0017172109,0.04319862,0.0007673794,0.44112834],"study_design_scores_gemma":[0.0008406452,0.00022250322,0.25870153,0.0053854985,0.00021863331,0.00009860351,0.45818543,0.0030120236,0.0000033137057,0.001017962,0.27124324,0.0010706224],"about_ca_topic_score_codex":0.21227394,"about_ca_topic_score_gemma":0.8421261,"teacher_disagreement_score":0.6298521,"about_ca_system_score_codex":0.0009754366,"about_ca_system_score_gemma":0.0004094025,"threshold_uncertainty_score":0.99997807},"labels":[],"label_agreement":null},{"id":"W1975403746","doi":"10.3138/cmlr.64.1.181","title":"<i>Auto-évaluation</i> : Daily Self-Assessment in the FSL Classroom","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Mathematics education; Computer science; Psychology; Economics","score_opus":0.020349828938382594,"score_gpt":0.30909300046608384,"score_spread":0.28874317152770124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975403746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8036728,0.05353184,0.0005121945,0.006264081,0.00052774395,0.00216951,0.000112345806,0.00017967832,0.13302983],"genre_scores_gemma":[0.9824183,0.010293104,0.0017229057,0.003726439,0.0005196648,0.00009175898,0.00011912815,0.000046247984,0.0010624393],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966739,0.00065945333,0.00053117884,0.00045223784,0.00035751218,0.0013257243],"domain_scores_gemma":[0.99783367,0.0006275445,0.00016682339,0.0005498064,0.00015912754,0.00066301634],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0057817,0.00029936878,0.0004512529,0.00030525884,0.00056324666,0.00017834334,0.00096944167,0.00015851868,0.00027537986],"category_scores_gemma":[0.00040990915,0.00025491873,0.00017265137,0.0009416856,0.00022156477,0.00025848023,0.00003794607,0.0004330036,0.000044826225],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013315415,0.00022490129,0.11646101,0.0015631515,0.00020994325,0.004334986,0.64449877,0.000009654426,0.0014141423,0.034547802,0.013787991,0.18293433],"study_design_scores_gemma":[0.0008134685,0.00008554509,0.41151553,0.0025744673,0.0002922849,0.000110423054,0.10377899,0.0004522044,0.000008044667,0.0019804444,0.47727472,0.0011138857],"about_ca_topic_score_codex":0.33674273,"about_ca_topic_score_gemma":0.96205163,"teacher_disagreement_score":0.6253089,"about_ca_system_score_codex":0.0017187105,"about_ca_system_score_gemma":0.0009991585,"threshold_uncertainty_score":0.9999903},"labels":[],"label_agreement":null},{"id":"W1975472233","doi":"10.5539/ies.v7n9p69","title":"Exploring Primary School Teachers’ Conceptions of “Assessment for Learning”","year":2014,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Brunei Darussalam","keywords":"Assessment for learning; Government (linguistics); Mathematics education; Pedagogy; Psychology; Educational assessment; Primary education; Qualitative research; Data collection; Christian ministry; Qualitative property; Semi-structured interview; Formative assessment; Sociology; Political science; Social science","score_opus":0.22290386212218646,"score_gpt":0.49012126253713956,"score_spread":0.2672174004149531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975472233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7967501,0.0003558369,0.0041958774,0.008146784,0.00787702,0.00044410655,0.0000048473166,0.00008701174,0.18213838],"genre_scores_gemma":[0.9755222,0.00066649605,0.0071712728,0.000178419,0.0009414655,0.00045053507,0.000021464337,0.000007211292,0.015040913],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911684,0.00007909095,0.00020707493,0.00013801958,0.00034771013,0.000111251764],"domain_scores_gemma":[0.99821943,0.00036511512,0.00015472303,0.000061479215,0.0011569072,0.00004234091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058146456,0.000067119596,0.0001267814,0.000097739205,0.00030894016,0.000038365575,0.00018224258,0.00002073502,0.00013414309],"category_scores_gemma":[0.00123308,0.000067673,0.00006626422,0.000095081465,0.00014752755,0.00032483652,0.000042789758,0.00007480017,0.0000156446],"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":[0.000023249428,0.0007457701,0.5452659,0.000048093865,0.0006342448,5.0543704e-8,0.08364773,0.00011205628,0.00078413,0.2667063,0.031135432,0.07089706],"study_design_scores_gemma":[0.0003609423,0.000054508353,0.22883767,0.000060985873,0.00003039565,1.0005366e-7,0.130415,0.000023111137,0.000033613127,0.0027626168,0.6372959,0.00012515103],"about_ca_topic_score_codex":0.00010542775,"about_ca_topic_score_gemma":0.000036983267,"teacher_disagreement_score":0.6061605,"about_ca_system_score_codex":0.00028620748,"about_ca_system_score_gemma":0.00029972632,"threshold_uncertainty_score":0.27596247},"labels":[],"label_agreement":null},{"id":"W1975565019","doi":"10.1002/bmb.20592","title":"Peer review in class: Metrics and variations in a senior course","year":2012,"lang":"en","type":"article","venue":"Biochemistry and Molecular Biology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Class (philosophy); Peer review; Peer assessment; Peer evaluation; Technical peer review; Peer feedback; Psychology; Medical education; Peer group; Quality (philosophy); Mathematics education; Computer science; Higher education; Social psychology; Medicine; Biology; Artificial intelligence; Political science","score_opus":0.019947783361024384,"score_gpt":0.3982574906643874,"score_spread":0.37830970730336305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975565019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9314964,0.0406879,0.00007012597,0.01804838,0.00024487037,0.00025472027,0.0000031728084,0.000008897144,0.009185563],"genre_scores_gemma":[0.99451864,0.0036151481,0.0004038128,0.0005826946,0.00008551065,0.000035158315,0.000046189383,0.00000223646,0.0007106194],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99948615,0.00008398309,0.000099870485,0.00011224612,0.000079766054,0.0001379623],"domain_scores_gemma":[0.9997381,0.000037646092,0.000040190695,0.000060003706,0.00006756867,0.000056483954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073144643,0.00005145142,0.00007899383,0.000038821567,0.00004861285,0.00001166075,0.00004618951,0.00010389388,0.000019218702],"category_scores_gemma":[0.00047930644,0.000052305455,0.000011565223,0.00024914,0.00007477038,0.000045238536,0.000018697783,0.00006385675,0.0000014878094],"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":[0.000004286818,0.00048472907,0.93799156,0.00013182283,0.000016772003,5.4802763e-7,0.0038270652,2.1800737e-8,0.020815162,0.02092558,0.0046353806,0.011167057],"study_design_scores_gemma":[0.001088709,0.000052260653,0.6242058,0.000573771,0.00020217743,0.000010881825,0.019199826,0.000011527257,0.00705304,0.0030930003,0.3437232,0.00078573864],"about_ca_topic_score_codex":0.00019370757,"about_ca_topic_score_gemma":0.000036034424,"teacher_disagreement_score":0.33908784,"about_ca_system_score_codex":0.000038938015,"about_ca_system_score_gemma":0.0001742742,"threshold_uncertainty_score":0.21329546},"labels":[],"label_agreement":null},{"id":"W1976878455","doi":"10.5206/cjsotl-rcacea.2013.1.5","title":"Enhancing Assessment in Teacher Education Courses","year":2013,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"University of Lethbridge","keywords":"Pedagogy; Valuation (finance); Higher education; Teacher education; Sociology; Political science; Library science; Psychology; Computer science","score_opus":0.033269992751195306,"score_gpt":0.37327392627960093,"score_spread":0.34000393352840563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976878455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.976028,0.0008298931,0.0001318937,0.011122199,0.0005126051,0.0002968382,2.581262e-7,0.000006810262,0.0110714855],"genre_scores_gemma":[0.99094677,0.000031007123,0.0005926958,0.00015711966,0.00034718652,0.000016811477,6.4929844e-7,0.000008899786,0.007898883],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99814016,0.0010915532,0.00018206607,0.0000798936,0.00021173467,0.00029460358],"domain_scores_gemma":[0.9988532,0.0006651974,0.00014752657,0.00007498264,0.00009302966,0.0001660589],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.010236333,0.00007180133,0.000098605226,0.00011256493,0.005266524,0.00065991346,0.00032517454,0.000054066542,0.00014398759],"category_scores_gemma":[0.0015210502,0.00004568691,0.000051345763,0.00008576734,0.0001456788,0.0003678069,0.000011999201,0.002029665,0.0000031068912],"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":[0.0000054741213,0.000029974344,0.7444994,0.000012189378,0.00004722134,5.993587e-7,0.07685361,0.00019608409,0.00034751702,0.020557903,0.00084211875,0.1566079],"study_design_scores_gemma":[0.000297809,0.00006254954,0.72016555,0.00022358571,0.000053005908,0.000008700938,0.21014288,0.0001895901,0.0000085081465,0.006576347,0.06210876,0.0001626898],"about_ca_topic_score_codex":0.10985387,"about_ca_topic_score_gemma":0.14536881,"teacher_disagreement_score":0.1564452,"about_ca_system_score_codex":0.00020023843,"about_ca_system_score_gemma":0.0012183845,"threshold_uncertainty_score":0.9960285},"labels":[],"label_agreement":null},{"id":"W1978227392","doi":"10.1080/09695940903565362","title":"Teacher beliefs about the cognitive diagnostic information of classroom‐ versus large‐scale tests: implications for assessment literacy","year":2010,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Smiths Detection (Canada); University of Alberta","funders":"","keywords":"Test (biology); Mathematics education; Scale (ratio); Psychology; Literacy; Pedagogy","score_opus":0.05055241862711323,"score_gpt":0.48032179247732004,"score_spread":0.4297693738502068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978227392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5479867,0.0002252819,0.0029292104,0.13558571,0.0021999879,0.004179873,0.00020594547,0.00008172852,0.3066056],"genre_scores_gemma":[0.9870275,0.0009119121,0.008294825,0.0012657661,0.00073431357,0.0010304033,0.00016990969,0.000011854519,0.0005534856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99816674,0.000408867,0.00052377436,0.00021660984,0.00033671284,0.00034729743],"domain_scores_gemma":[0.9828265,0.015529485,0.0006018049,0.00027129258,0.0006609694,0.00011000382],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027666062,0.00015615515,0.00016991807,0.00020733166,0.0006982924,0.00033642448,0.00030344652,0.00013199972,0.00006552644],"category_scores_gemma":[0.011352784,0.00013744291,0.000057922847,0.0005444637,0.00020565982,0.0023316594,0.00009863017,0.00044524262,0.000006438774],"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":[0.00008061616,0.0013515892,0.1726081,0.00004318819,0.00006532221,5.765668e-8,0.05189255,0.000003925003,0.00007360176,0.7408808,0.0008353708,0.032164864],"study_design_scores_gemma":[0.00082891027,0.000075227545,0.6145263,0.000035050558,0.000082542734,0.000001276393,0.058297753,0.000048117894,0.0000042124298,0.0024003126,0.32356888,0.00013145478],"about_ca_topic_score_codex":0.0015376091,"about_ca_topic_score_gemma":0.002459566,"teacher_disagreement_score":0.7384805,"about_ca_system_score_codex":0.00021921612,"about_ca_system_score_gemma":0.0028076798,"threshold_uncertainty_score":0.996975},"labels":[],"label_agreement":null},{"id":"W1978294241","doi":"10.1108/02621710010322580","title":"Receptivity to assessment‐based feedback for management development","year":2000,"lang":"en","type":"article","venue":"Journal of Management Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Receptivity; Psychology; Congruence (geometry); Social psychology; Positive feedback","score_opus":0.0340642683330416,"score_gpt":0.35440362098786893,"score_spread":0.3203393526548273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978294241","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2877342,0.0001400973,0.07440869,0.009515555,0.0030489715,0.006337141,0.0000063096836,0.00022655749,0.6185825],"genre_scores_gemma":[0.19238535,0.00030282247,0.73402506,0.0018993848,0.00042214082,0.00034420172,0.000019411367,0.00006161345,0.070539996],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954661,0.00016459815,0.0011799029,0.00044064998,0.0019066918,0.00084206054],"domain_scores_gemma":[0.9984845,0.00011839252,0.00042155836,0.0002647595,0.00029421924,0.0004165559],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003782463,0.0003579118,0.000486485,0.00057944725,0.0009242448,0.0003033818,0.001017751,0.00009477554,0.0020801097],"category_scores_gemma":[0.00001812882,0.00034432404,0.00020802651,0.00070811453,0.000069374226,0.00036898427,0.0001533566,0.00018695589,0.00026406336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004753195,0.0011498914,0.006831024,0.00023786047,0.0011749043,0.000094513234,0.007923694,0.00048062176,0.000030104144,0.0053028986,0.044556558,0.9317426],"study_design_scores_gemma":[0.0019961768,0.00010856019,0.1292281,0.00022173034,0.00009518816,8.557128e-7,0.0034467557,0.000011904996,0.0001196672,0.00015128369,0.8641926,0.00042719275],"about_ca_topic_score_codex":0.000006627735,"about_ca_topic_score_gemma":0.0000727333,"teacher_disagreement_score":0.9313154,"about_ca_system_score_codex":0.0012881052,"about_ca_system_score_gemma":0.00046238583,"threshold_uncertainty_score":0.9999009},"labels":[],"label_agreement":null},{"id":"W1982497397","doi":"10.1016/s0191-491x(02)00014-7","title":"Matching the grade 8 TIMSS item pool to the Ontario curriculum","year":2002,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Lakehead University","funders":"","keywords":"Mathematics education; Curriculum; Matching (statistics); Secondary education; Psychology; Pedagogy; Mathematics; Statistics","score_opus":0.1656116291663467,"score_gpt":0.46858849052707463,"score_spread":0.30297686136072793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982497397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8436687,0.0011877294,0.0000096810545,0.11455798,0.0029890847,0.0010912141,0.0000010218475,0.000013712783,0.03648089],"genre_scores_gemma":[0.99041015,0.00013058596,0.00016609175,0.0007760128,0.0010187597,0.0004442054,0.0000052932696,0.0000046174528,0.0070443125],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9980574,0.00035439822,0.00019531502,0.00017319631,0.0010152132,0.00020447937],"domain_scores_gemma":[0.9988517,0.0006296581,0.00007524994,0.00014142739,0.0002733558,0.000028601477],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002452534,0.000084366424,0.00008634964,0.000053433847,0.001055732,0.00007504377,0.0003132552,0.000025261437,0.0012303342],"category_scores_gemma":[0.00066354516,0.000052288546,0.000039463222,0.00044004456,0.00014160557,0.00015020985,0.00006780592,0.00013418341,0.00025685865],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002029562,0.00020446152,0.09309825,0.0000032020166,0.00006308185,1.09156225e-7,0.7985937,0.00066096795,0.0000030204667,0.02902945,0.07384103,0.004500731],"study_design_scores_gemma":[0.00024271724,0.000021334703,0.59274167,0.00004426318,0.0000656798,5.644851e-7,0.30244815,0.0004367595,0.000001139861,0.027635746,0.07619528,0.00016667909],"about_ca_topic_score_codex":0.013748722,"about_ca_topic_score_gemma":0.22927839,"teacher_disagreement_score":0.49964345,"about_ca_system_score_codex":0.0009908624,"about_ca_system_score_gemma":0.0002079393,"threshold_uncertainty_score":0.99968266},"labels":[],"label_agreement":null},{"id":"W1986967177","doi":"10.3109/0142159x.2010.486063","title":"Assessment steers learning down the right road: Impact of progress testing on licensing examination performance","year":2010,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Formative assessment; Test (biology); Curriculum; Psychology; Medicine; Medical education; Mathematics education; Pedagogy","score_opus":0.02780155950402934,"score_gpt":0.3811736229013911,"score_spread":0.35337206339736177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986967177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86817414,0.000010587899,0.000013989059,0.0005715039,0.00026335535,0.0001830477,1.1036363e-7,0.000051489664,0.1307318],"genre_scores_gemma":[0.99761444,0.000007531216,0.00024337259,0.000020607544,0.0005083873,0.000011203552,0.0000024355365,0.000009662216,0.0015823499],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976656,0.0003575294,0.00020368265,0.00016656944,0.0013089917,0.00029765462],"domain_scores_gemma":[0.99924403,0.00024530748,0.00015642059,0.00013027644,0.00010156117,0.00012238856],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038537565,0.0001057026,0.00014159545,0.000048733207,0.0005301847,0.00007418874,0.00031503267,0.00013806626,0.0016864836],"category_scores_gemma":[0.0010459431,0.00006294251,0.00006732045,0.00029173502,0.00046190034,0.00014096344,0.00005274032,0.00087183353,0.000016242082],"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":[0.0000035222101,0.00011577975,0.78885055,0.00000476341,0.000023247661,0.0000018656842,0.004602669,0.0000068918293,0.000112741815,0.0004188263,0.00014065315,0.20571849],"study_design_scores_gemma":[0.0002525103,0.00015562502,0.9850033,0.000055508157,0.000013584774,8.035344e-7,0.0017337339,0.010806403,0.000012903786,0.000010713454,0.0018598295,0.00009508433],"about_ca_topic_score_codex":0.00032878647,"about_ca_topic_score_gemma":0.000114987546,"teacher_disagreement_score":0.2056234,"about_ca_system_score_codex":0.000104958424,"about_ca_system_score_gemma":0.00022508354,"threshold_uncertainty_score":0.9992261},"labels":[],"label_agreement":null},{"id":"W198737285","doi":"10.1007/978-94-007-1727-5_5","title":"Fair and Ethical Student Assessment Practices","year":2011,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Engineering ethics; Best practice; Process (computing); Ethical issues; Pedagogy; Psychology; Political science; Public relations; Sociology; Computer science; Engineering; Law","score_opus":0.11087441878626461,"score_gpt":0.44903393319752816,"score_spread":0.3381595144112636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W198737285","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014633214,0.00025459606,0.000054835946,0.00407616,0.00056198234,0.00048186482,0.000003146948,0.000118961296,0.9943021],"genre_scores_gemma":[0.03446366,0.0039353124,0.0011121948,0.0008551754,0.0006578518,0.000017654069,0.0000079255,0.000033724365,0.9589165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976915,0.0000994551,0.00030268176,0.00047207918,0.001132858,0.00030141053],"domain_scores_gemma":[0.9985204,0.0003618969,0.00055138924,0.00022550936,0.00013856067,0.00020226146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001287667,0.00027536944,0.00035915922,0.00008994292,0.0004452668,0.00028436896,0.000415362,0.0008876527,0.009436613],"category_scores_gemma":[0.000059166632,0.00023821951,0.000107245025,0.00002391675,0.0004483751,0.00014414027,0.00029418027,0.0010832538,0.00024351146],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005632023,0.000030342208,0.0032971005,0.000010193723,0.0001300853,0.000014218333,0.0044444622,7.0143744e-9,0.0000012795417,0.98129606,0.008402491,0.0023681098],"study_design_scores_gemma":[0.00022121631,0.0001038806,0.00946775,0.00004913224,0.00016905693,8.8580333e-7,0.0032988733,4.9642153e-7,4.0832523e-7,0.035340216,0.9509494,0.0003986973],"about_ca_topic_score_codex":0.0007691776,"about_ca_topic_score_gemma":0.0024700693,"teacher_disagreement_score":0.9459559,"about_ca_system_score_codex":0.00013179863,"about_ca_system_score_gemma":0.0003264288,"threshold_uncertainty_score":0.9914689},"labels":[],"label_agreement":null},{"id":"W1994264241","doi":"10.24908/eoe-ese-rse.v11i0.2526","title":"The Capacity of Assessment in Arts Education","year":2010,"lang":"en","type":"article","venue":"Encounters in Theory and History of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive reframing; Creativity; The arts; Accountability; Psychology; Standards-based assessment; Pedagogy; Educational assessment; Engineering ethics; Political science; Engineering; Social psychology","score_opus":0.018926907092902484,"score_gpt":0.3412857423962693,"score_spread":0.32235883530336684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994264241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87373734,0.0003888224,0.000008320187,0.0002632843,0.0038215425,0.00013631553,3.2116915e-7,0.00000267944,0.12164135],"genre_scores_gemma":[0.9966926,0.00012716498,0.00018492574,0.000046792975,0.000083275,0.000025202195,0.0000012772762,0.000002383734,0.0028363545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99933314,0.00018328762,0.0001762861,0.00008719674,0.0001398353,0.000080246544],"domain_scores_gemma":[0.99941665,0.00026992426,0.00013246782,0.00010278837,0.000056407483,0.000021744845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021878306,0.000043903532,0.0000760226,0.000102135506,0.000075811084,0.000007924523,0.0001271864,0.00004497621,0.00008807689],"category_scores_gemma":[0.00014116426,0.00003915872,0.000018202807,0.00008110119,0.00049725716,0.0001409957,0.000009261149,0.00014059393,6.065091e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002950797,0.0004178299,0.083949566,0.000017539896,0.000003791772,2.5824656e-8,0.1022881,3.9375456e-7,0.002492373,0.7922811,0.0021751428,0.016344622],"study_design_scores_gemma":[0.00023460908,0.00004660012,0.52798915,0.00010410643,0.000013695285,3.4001033e-7,0.16861695,0.000005900816,0.00008534144,0.08946517,0.21329236,0.00014579532],"about_ca_topic_score_codex":0.0014245785,"about_ca_topic_score_gemma":0.007188897,"teacher_disagreement_score":0.70281595,"about_ca_system_score_codex":0.00030684404,"about_ca_system_score_gemma":0.0013350312,"threshold_uncertainty_score":0.40115732},"labels":[],"label_agreement":null},{"id":"W1995272993","doi":"10.4018/jicthd.2010100104","title":"Leveraging Technology to Promote Assessment for Learning in Higher Education","year":2010,"lang":"en","type":"article","venue":"International Journal of Information Communication Technologies and Human Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Peer assessment; Higher education; Computer science; Medical education; Institution; Process (computing); Service (business); Mathematics education; Engineering management; Knowledge management; Psychology; Sociology; Engineering; Political science; Business; Marketing; Medicine","score_opus":0.03263258367176606,"score_gpt":0.38530118750130593,"score_spread":0.35266860382953985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995272993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9496912,0.00005265252,0.0017302645,0.036530137,0.0005703921,0.0004668216,4.6540336e-7,0.0001365775,0.010821523],"genre_scores_gemma":[0.92126334,0.00009160129,0.07809767,0.00011341988,0.0000334206,0.0000619936,0.000010566288,0.0000031826557,0.00032478286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990212,0.00001804954,0.0004960115,0.000055422126,0.0002967931,0.00011256742],"domain_scores_gemma":[0.998715,0.000046482473,0.00039801354,0.00010245281,0.00071197184,0.00002609611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087041187,0.000069153575,0.0001071168,0.0008794142,0.0003259911,0.00019551383,0.0007219572,0.000103293314,0.00004400702],"category_scores_gemma":[0.00018050581,0.00006797964,0.000018712146,0.00019814246,0.00008255413,0.0006630533,0.00019127036,0.0003457938,0.000002814639],"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":[0.000016910557,0.00011736354,0.040553965,0.000008278359,0.00004097785,2.2327629e-7,0.0099575985,0.000019750672,0.0006164056,0.3530977,0.0006948034,0.594876],"study_design_scores_gemma":[0.0007194704,0.00008727599,0.07874049,0.00012201722,0.000004610222,0.0000035030423,0.0241835,0.000017292019,0.0004958459,0.016464269,0.8790107,0.00015107734],"about_ca_topic_score_codex":0.000019076631,"about_ca_topic_score_gemma":0.00008797164,"teacher_disagreement_score":0.87831587,"about_ca_system_score_codex":0.00021572312,"about_ca_system_score_gemma":0.00030928265,"threshold_uncertainty_score":0.27721295},"labels":[],"label_agreement":null},{"id":"W1996030827","doi":"10.1016/j.asw.2010.05.003","title":"Assessing and providing feedback for student writing in Canadian classrooms","year":2010,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Advanced Education; University of Toronto","funders":"","keywords":"Mathematics education; Peer feedback; Psychology; Pedagogy; Medical education; Computer science; Medicine","score_opus":0.04316665126083148,"score_gpt":0.410534152827318,"score_spread":0.3673675015664865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996030827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93742454,0.000103317114,0.00020992238,0.0025418145,0.0006905478,0.00060090824,0.0000024687745,0.000107845044,0.05831863],"genre_scores_gemma":[0.98590386,0.00001573422,0.012481201,0.00024366833,0.0010094442,0.00006776099,0.000008889858,0.000044937333,0.00022449491],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969491,0.00016561273,0.0005567601,0.00054179237,0.00047696262,0.0013097782],"domain_scores_gemma":[0.99807525,0.0009692833,0.00021293636,0.0001708622,0.00016969998,0.00040198985],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004376092,0.00023577853,0.00032221957,0.0003246737,0.0021959648,0.00400315,0.00035645475,0.00024259486,0.00006695133],"category_scores_gemma":[0.0007781438,0.0002732557,0.00007549206,0.0004308061,0.00023050334,0.0016627075,0.00009871266,0.0006035622,0.000005809702],"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":[0.0000020452349,0.000047043715,0.9230515,0.000048025497,0.000014696463,0.000017815335,0.0063116467,0.0000025583513,0.003776687,0.015276434,0.00007939413,0.05137218],"study_design_scores_gemma":[0.0013117508,0.000029024324,0.76877505,0.0005744871,0.000047616217,0.000007736356,0.20455028,0.0012297899,0.0001012952,0.0008962824,0.021704178,0.0007725395],"about_ca_topic_score_codex":0.080971695,"about_ca_topic_score_gemma":0.41958252,"teacher_disagreement_score":0.33861083,"about_ca_system_score_codex":0.0003707083,"about_ca_system_score_gemma":0.00081679213,"threshold_uncertainty_score":0.999972},"labels":[],"label_agreement":null},{"id":"W1996435010","doi":"10.1080/09695940701272773","title":"Did we take the same test? Differing accounts of the Ontario Secondary School Literacy Test by first and second language test‐takers","year":2007,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; Carleton University","funders":"","keywords":"Test (biology); Graduation (instrument); Psychology; Context (archaeology); Construct (python library); Literacy; Construct validity; Mathematics education; Fidelity; Test score; Standardized test; Pedagogy; Developmental psychology; Computer science; Psychometrics; Mathematics","score_opus":0.02100229501179931,"score_gpt":0.38458132868967815,"score_spread":0.36357903367787886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996435010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8785336,0.000717962,0.000005737945,0.034860212,0.00031700765,0.00059514266,0.000033167224,0.000018015502,0.08491918],"genre_scores_gemma":[0.9832307,0.0009199142,0.000621495,0.0022710848,0.00033128657,0.000041993328,0.000010528142,0.0000138339165,0.012559129],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983174,0.00020501834,0.00041820566,0.00028080062,0.00042656527,0.00035197084],"domain_scores_gemma":[0.98928136,0.009708045,0.00045431653,0.00031190016,0.00011228265,0.00013211933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023889581,0.00017869049,0.00017318923,0.00010971424,0.00065773784,0.00038412272,0.0003783061,0.00009920697,0.00032712225],"category_scores_gemma":[0.004567929,0.0001313146,0.000039379753,0.0004546433,0.00025203513,0.0011842834,0.00017918301,0.00057698775,0.000004157873],"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":[0.00001662022,0.0006631211,0.8745536,0.000048685935,0.000027200562,9.822992e-7,0.11140535,5.882509e-7,0.00062398415,0.0032286532,0.0015691731,0.007861994],"study_design_scores_gemma":[0.00023520064,0.000034070967,0.6397342,0.00005857932,0.000026704723,0.000005609869,0.047297895,0.0000037640793,0.000049076192,0.00022760947,0.3122129,0.00011435258],"about_ca_topic_score_codex":0.04493859,"about_ca_topic_score_gemma":0.113942124,"teacher_disagreement_score":0.31064373,"about_ca_system_score_codex":0.0005247691,"about_ca_system_score_gemma":0.0020187004,"threshold_uncertainty_score":0.96142125},"labels":[],"label_agreement":null},{"id":"W1996477132","doi":"10.1177/0741088310371635","title":"Undergraduate Writing Assignments: An Analysis of Syllabi at One Canadian College","year":2010,"lang":"en","type":"article","venue":"Written Communication","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University; University of Alberta","funders":"","keywords":"Syllabus; Mathematics education; Curriculum; Higher education; Task (project management); Academic writing; Psychology; Computer science; Pedagogy; Engineering","score_opus":0.03217846521966579,"score_gpt":0.3400945437894142,"score_spread":0.30791607856974845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996477132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8906112,0.000046573765,0.000015689837,0.006540043,0.000067305584,0.00020499177,0.000035732246,0.00003667664,0.102441795],"genre_scores_gemma":[0.9965639,0.00014389225,0.0016687728,0.00013053388,0.00004011327,0.000015300899,0.00016519653,0.00000831409,0.0012639491],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986742,0.00030819807,0.00025828535,0.00014675672,0.00037271026,0.00023982703],"domain_scores_gemma":[0.99861974,0.00017589211,0.0001652319,0.00068130216,0.0001780167,0.0001798363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011011896,0.0000759697,0.00018750798,0.00025809233,0.0009023706,0.00006274137,0.0007197179,0.00010298873,0.0004729163],"category_scores_gemma":[0.00007413554,0.00008854166,0.00007156444,0.0009009136,0.00021452292,0.00025737236,0.000099790916,0.00016576918,0.000021857866],"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":[0.000010672926,0.00023882951,0.78928506,0.0000053631934,0.0005469159,8.179559e-7,0.00834503,0.00001590562,0.0065565216,0.1918674,0.0008663748,0.0022611183],"study_design_scores_gemma":[0.0004094799,0.0000369225,0.95307225,0.000021443133,0.0006829528,1.7900295e-7,0.020015188,0.0016731542,0.00017315132,0.0018561486,0.021767246,0.00029186314],"about_ca_topic_score_codex":0.2421239,"about_ca_topic_score_gemma":0.9324702,"teacher_disagreement_score":0.6903463,"about_ca_system_score_codex":0.0002714451,"about_ca_system_score_gemma":0.00017030809,"threshold_uncertainty_score":0.7629229},"labels":[],"label_agreement":null},{"id":"W1996479287","doi":"10.1080/09585176.2014.964276","title":"System leaders using assessment for learning as both the change and the change process: developing theory from practice","year":2014,"lang":"en","type":"article","venue":"The Curriculum Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Fredericton; University of New Brunswick","funders":"","keywords":"Process (computing); Theory of change; Political science; Qualitative property; Qualitative research; Public relations; Pedagogy; Psychology; Sociology; Computer science; Social science","score_opus":0.0998659927114753,"score_gpt":0.40928048173368875,"score_spread":0.30941448902221347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996479287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69546807,0.01060747,0.06738764,0.1677627,0.006073316,0.0071823676,0.0000065483714,0.00028746572,0.04522441],"genre_scores_gemma":[0.9921082,0.00055471476,0.0010928535,0.0017904338,0.0041671447,0.00015494139,0.000001213692,0.00002178241,0.00010868173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99613535,0.0022647132,0.00027185903,0.0001869864,0.0007001795,0.0004409137],"domain_scores_gemma":[0.99674195,0.0022351253,0.00057422934,0.00013712142,0.00023432929,0.00007725229],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.010441833,0.00017108035,0.00022834871,0.00003947729,0.0046281964,0.0007041343,0.00062741485,0.00007127795,0.00002350828],"category_scores_gemma":[0.00081447436,0.000077869765,0.00010091935,0.00023717734,0.0005044196,0.0006792952,0.000099395,0.0005817099,0.000006364959],"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":[0.00020109484,0.000079228514,0.018063854,0.0000840754,0.0005216619,0.0000060730326,0.40089902,0.00004445436,0.000028329825,0.55619514,0.00047569495,0.023401363],"study_design_scores_gemma":[0.0017603777,0.00008655776,0.003813777,0.0004779894,0.0005474204,0.000058626225,0.9317264,0.008190097,0.0000047832273,0.012510812,0.040508643,0.00031453735],"about_ca_topic_score_codex":0.0012106086,"about_ca_topic_score_gemma":0.00008098244,"teacher_disagreement_score":0.5436843,"about_ca_system_score_codex":0.00019543353,"about_ca_system_score_gemma":0.00017441333,"threshold_uncertainty_score":0.9966676},"labels":[],"label_agreement":null},{"id":"W1996719374","doi":"10.3138/jvme.0714-067r1","title":"Assessment Literacy: Definition, Implementation, and Implications","year":2014,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Higher Education Academy","keywords":"Preparedness; Medical education; Curriculum; Cohort; Psychology; Session (web analytics); Literacy; Intervention (counseling); Formative assessment; Mathematics education; Pedagogy; Medicine; Computer science; Political science","score_opus":0.07582813055538377,"score_gpt":0.4954959922101246,"score_spread":0.4196678616547408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996719374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94640285,0.00019726074,0.0033030636,0.029954672,0.0011564372,0.00013720985,0.0000011682581,0.000014233044,0.018833082],"genre_scores_gemma":[0.9915238,0.0005712966,0.0058828173,0.0010433084,0.0008764891,0.0000122607125,0.000009307203,0.000004733772,0.00007597404],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986609,0.00024068603,0.00036686845,0.0000852268,0.0005211775,0.00012509826],"domain_scores_gemma":[0.99887776,0.00018315656,0.00027100675,0.00007343596,0.0003410109,0.00025365487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014942012,0.000059670376,0.00011263666,0.00010631614,0.0002671969,0.00009216247,0.00016514135,0.000052803818,0.0007141673],"category_scores_gemma":[0.00034818982,0.00005408037,0.000040330935,0.00014738042,0.00010422654,0.0003968283,0.00002674611,0.00013227071,0.0000046373866],"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":[0.00002183883,0.00064402836,0.24061407,0.000031463445,0.00005034259,0.000002452914,0.012826749,1.7630822e-7,0.00041828054,0.21914254,0.025849087,0.50039893],"study_design_scores_gemma":[0.0004157253,0.00033300137,0.74362385,0.00005315361,0.000029216995,0.000058680613,0.005915186,0.000006514584,0.0000018072078,0.009987575,0.23949827,0.000077028366],"about_ca_topic_score_codex":0.00005862388,"about_ca_topic_score_gemma":0.0000223759,"teacher_disagreement_score":0.50300974,"about_ca_system_score_codex":0.00009547031,"about_ca_system_score_gemma":0.0012089129,"threshold_uncertainty_score":0.7819631},"labels":[],"label_agreement":null},{"id":"W1996728665","doi":"10.1080/08878730.2012.760024","title":"Pedagogies for Preservice Assessment Education: Supporting Teacher Candidates' Assessment Literacy Development","year":2013,"lang":"en","type":"article","venue":"The Teacher Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Praxis; Accountability; Teacher education; Literacy; Pedagogy; Psychology; Mathematics education; Perspective (graphical); Political science","score_opus":0.038888458072460504,"score_gpt":0.44715132300627947,"score_spread":0.40826286493381897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996728665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8630193,0.00032167198,0.0002482549,0.025514087,0.0018604703,0.0028891987,0.0000034550221,0.00021005118,0.10593353],"genre_scores_gemma":[0.8715669,0.000022570044,0.015564734,0.00076269027,0.0018416477,0.0029487887,0.00006211134,0.000046834168,0.10718373],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99695367,0.00038771037,0.0005745394,0.00047557906,0.00075347,0.0008550379],"domain_scores_gemma":[0.99811053,0.00034251588,0.00034904838,0.00053801725,0.00039264088,0.00026722488],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022106469,0.0003106249,0.0002934245,0.0001013771,0.0014838338,0.00091063936,0.0011147162,0.00012209374,0.0062979725],"category_scores_gemma":[0.00013182616,0.00023240951,0.00012961132,0.00030101847,0.0001688559,0.0007889031,0.000212549,0.0003724695,0.00025460828],"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":[0.000013927111,0.001775664,0.4913778,0.00009082542,0.00024797942,3.4577826e-7,0.20741983,0.0000014011463,0.00018721067,0.008826475,0.21163772,0.078420825],"study_design_scores_gemma":[0.00032520128,0.00003690456,0.3329954,0.00004297244,0.00007303208,7.74341e-7,0.14084071,0.00007603928,0.00003823042,0.0013541377,0.5238052,0.0004113851],"about_ca_topic_score_codex":0.003970104,"about_ca_topic_score_gemma":0.00042092128,"teacher_disagreement_score":0.31216747,"about_ca_system_score_codex":0.00075357663,"about_ca_system_score_gemma":0.0054556117,"threshold_uncertainty_score":0.9998161},"labels":[],"label_agreement":null},{"id":"W1997129769","doi":"10.7202/019859ar","title":"Plan-based Translation Assessment An Alternative to the Standard-based cut-the-feet-to-fit-the-shoes Style of Assessment","year":2009,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Computer science; Style (visual arts); Process (computing); sort; Mathematics education; Psychology","score_opus":0.09318539283418599,"score_gpt":0.39662914757635004,"score_spread":0.30344375474216406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997129769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73125285,0.0019206523,0.14943802,0.10992566,0.0015153202,0.0025484737,0.00014034887,0.000090047695,0.0031686416],"genre_scores_gemma":[0.98673874,0.00031203977,0.01055141,0.0016566273,0.00053288596,0.000041662388,0.00000874061,0.000022323573,0.00013554547],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948493,0.0016501991,0.0006069712,0.00031795146,0.002023753,0.00055180717],"domain_scores_gemma":[0.99793065,0.0005981421,0.00037077072,0.00040225568,0.00038679698,0.00031139384],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005041993,0.00029351638,0.0004512833,0.00019805896,0.0016802305,0.0006041929,0.0013301285,0.00006214548,0.0002633908],"category_scores_gemma":[0.000090561494,0.00015577603,0.00035494368,0.0008584504,0.00032365057,0.0004093214,0.00001651516,0.00049933366,0.0000063354055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021076647,0.0036095474,0.036305085,0.00006251662,0.0040325676,0.000098671466,0.08215565,0.09869303,0.016189355,0.04445076,0.013459567,0.69883555],"study_design_scores_gemma":[0.0046560327,0.0063894074,0.5075978,0.00021902888,0.0034158665,0.000015496129,0.022936437,0.006153186,0.0053626737,0.01350594,0.42835325,0.0013948706],"about_ca_topic_score_codex":0.00026329688,"about_ca_topic_score_gemma":0.0017093432,"teacher_disagreement_score":0.6974407,"about_ca_system_score_codex":0.00030297373,"about_ca_system_score_gemma":0.0006277984,"threshold_uncertainty_score":0.9996194},"labels":[],"label_agreement":null},{"id":"W1999929076","doi":"10.1080/10627197.2011.584042","title":"Voices From Test-Takers: Further Evidence for Language Assessment Validation and Use","year":2011,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Guangdong University of Foreign Studies; Ministry of Education, India; Ministry of Earth Sciences","keywords":"Test (biology); Language assessment; Psychology; Test validity; Scale (ratio); Coding (social sciences); Test score; Computer science; Psychometrics; Mathematics education; Standardized test; Developmental psychology","score_opus":0.14416238535195033,"score_gpt":0.4552257976525222,"score_spread":0.3110634123005719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999929076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97403026,0.00030018852,0.0015928847,0.010550683,0.0011033136,0.001072566,0.00007065481,0.00007311721,0.011206351],"genre_scores_gemma":[0.94155943,0.00015377358,0.05300405,0.00026791875,0.000772633,0.00033142228,0.0001056562,0.000016937325,0.0037881832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99835074,0.000155092,0.0002588482,0.00039361944,0.0005638489,0.0002778464],"domain_scores_gemma":[0.996206,0.0030606699,0.00019156748,0.0001979789,0.00020477736,0.00013903186],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007981853,0.00015677555,0.0001553686,0.00007561059,0.00041121343,0.00031899475,0.00025587875,0.000075164746,0.0019312112],"category_scores_gemma":[0.0004854253,0.00015149346,0.0000648942,0.00015313749,0.00013188836,0.0010562473,0.0000540769,0.000103133236,0.000024136674],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001592754,0.0005150101,0.9355121,0.000013006553,0.00007642732,4.885773e-7,0.032213062,8.068428e-7,0.00094858604,0.024442112,0.0037961684,0.0024662935],"study_design_scores_gemma":[0.00031712864,0.00007924424,0.9670038,0.00006335666,0.000074931115,2.0413238e-7,0.02250137,0.0000601529,0.00010872531,0.005017477,0.004552266,0.00022130254],"about_ca_topic_score_codex":0.004590329,"about_ca_topic_score_gemma":0.00073400576,"teacher_disagreement_score":0.051411163,"about_ca_system_score_codex":0.00027462622,"about_ca_system_score_gemma":0.0007396631,"threshold_uncertainty_score":0.9989812},"labels":[],"label_agreement":null},{"id":"W2000242929","doi":"10.1007/s11092-014-9195-0","title":"Navigating dilemmas in transforming assessment practices: experiences of mathematics teachers in Ontario, Canada","year":2014,"lang":"en","type":"article","venue":"Educational Assessment Evaluation and Accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Situated; Accountability; Judgement; Pedagogy; Assessment for learning; Curriculum; Best practice; Mathematics education; Faculty development; Professional development; Psychology; Formative assessment; Political science; Computer science","score_opus":0.0639113308409666,"score_gpt":0.4511814897350099,"score_spread":0.38727015889404326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000242929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820801,0.000021264545,0.00006413774,0.0023525753,0.00034637155,0.0007457044,0.0000013863945,0.000005854846,0.014382607],"genre_scores_gemma":[0.9953084,0.000008397139,0.0041297656,0.00007143129,0.000065250635,0.00032869953,0.00003082077,0.000005344497,0.000051894196],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99689734,0.00050486514,0.0006190287,0.00030942092,0.0014279217,0.00024142735],"domain_scores_gemma":[0.99795455,0.0011103676,0.00049010187,0.00014311139,0.00023275484,0.00006909706],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007483715,0.00013237714,0.00023646276,0.000049487146,0.00021417985,0.000091235015,0.0001902647,0.000062207735,0.0016756454],"category_scores_gemma":[0.00062791025,0.00013230642,0.000030273017,0.0002912103,0.00014097209,0.0006708196,0.000026118303,0.00033522802,4.2397306e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002206206,0.0003801483,0.8405382,0.000020336744,0.0000064913806,4.6397556e-8,0.15126696,0.00004699335,0.000036690657,0.0046778126,0.000021149406,0.0030029512],"study_design_scores_gemma":[0.0003766728,0.000015716629,0.7005319,0.00006494693,0.0000134469765,1.4524126e-7,0.29464707,0.0018410666,0.000006590236,0.0018271178,0.0005634249,0.00011188592],"about_ca_topic_score_codex":0.9363547,"about_ca_topic_score_gemma":0.99399436,"teacher_disagreement_score":0.1433801,"about_ca_system_score_codex":0.002408778,"about_ca_system_score_gemma":0.007218331,"threshold_uncertainty_score":0.99923694},"labels":[],"label_agreement":null},{"id":"W2001609584","doi":"10.3138/jvme.0912-081r","title":"Experiences with Audio Feedback in a Veterinary Curriculum","year":2013,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Edinburgh","keywords":"Helpfulness; Peer feedback; Curriculum; Class (philosophy); Medical education; Psychology; Audio feedback; Test (biology); Multimedia; Computer science; Medicine; Pedagogy; Social psychology","score_opus":0.04294143203618296,"score_gpt":0.39723376888913586,"score_spread":0.3542923368529529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001609584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9885327,0.0002946605,0.000024417903,0.0047024773,0.0013760254,0.00018068161,6.831881e-8,0.000010061758,0.004878864],"genre_scores_gemma":[0.9973706,0.00020983459,0.0009236479,0.00032085698,0.00077126746,0.000056774326,8.4601174e-7,0.000007334082,0.00033885546],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9979325,0.00024831557,0.00040893236,0.00012642816,0.001026825,0.00025701392],"domain_scores_gemma":[0.99901205,0.00008918407,0.00026949338,0.00008883683,0.000215018,0.0003254336],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080971624,0.00010519612,0.00020668468,0.00016926833,0.0001277825,0.000088276596,0.0004108323,0.000097704986,0.0033388324],"category_scores_gemma":[0.00037628642,0.00007730931,0.000057200832,0.00037315505,0.0002587,0.0008057984,0.000041240033,0.00026298448,0.000040280942],"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":[0.00046299314,0.0059719994,0.23576644,0.0001189054,0.000114428425,0.00051123486,0.4933469,0.0000035478063,0.00095162715,0.00091263914,0.055734627,0.20610464],"study_design_scores_gemma":[0.001335034,0.0037118117,0.28174174,0.00079820474,0.000020794716,0.00052803115,0.64260113,0.000054229942,0.000007662819,0.00024913732,0.068615004,0.00033722],"about_ca_topic_score_codex":0.00067801826,"about_ca_topic_score_gemma":0.000041328527,"teacher_disagreement_score":0.20576741,"about_ca_system_score_codex":0.0001638867,"about_ca_system_score_gemma":0.0015194213,"threshold_uncertainty_score":0.99757224},"labels":[],"label_agreement":null},{"id":"W2005092513","doi":"10.5539/ies.v3n3p126","title":"Business Students' Views of Peer Assessment on Class Participation","year":2010,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer assessment; Class (philosophy); Psychology; Peer evaluation; Peer feedback; Sample (material); Student engagement; Mathematics education; Process (computing); Self-assessment; Medical education; Pedagogy; Higher education; Computer science","score_opus":0.12892178434258825,"score_gpt":0.5537282949083048,"score_spread":0.4248065105657165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005092513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8789411,0.000050708943,0.000053881642,0.013441768,0.012218407,0.00022395956,0.0000048639877,0.000029438626,0.09503585],"genre_scores_gemma":[0.9824083,0.00017947925,0.00078274135,0.00036573847,0.0007694457,0.00014259972,0.000020519688,0.0000070951282,0.015324069],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99796605,0.00007245822,0.00030777868,0.00018344,0.0013346554,0.00013562778],"domain_scores_gemma":[0.99540335,0.00020942118,0.00022902407,0.00013550815,0.003975801,0.000046916266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008394402,0.00009894409,0.00015416094,0.00014341061,0.00022169457,0.00008510817,0.0003778628,0.00004934547,0.0004784504],"category_scores_gemma":[0.0011759195,0.00008925724,0.0000517685,0.00024736158,0.00019154519,0.000226723,0.00007193265,0.00013318528,0.00006053932],"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":[0.000028384324,0.0024766426,0.69672287,0.000017247528,0.00035201883,4.179912e-7,0.022504624,0.000015425197,0.0009235545,0.21375546,0.049665328,0.013538053],"study_design_scores_gemma":[0.00020224447,0.00001988492,0.6535968,0.000029218705,0.000021262085,1.0709815e-7,0.01230495,0.0000050980498,0.00008472056,0.0013642206,0.33227777,0.00009371583],"about_ca_topic_score_codex":0.00018941247,"about_ca_topic_score_gemma":0.00069231406,"teacher_disagreement_score":0.28261244,"about_ca_system_score_codex":0.00014242227,"about_ca_system_score_gemma":0.00032585172,"threshold_uncertainty_score":0.52386963},"labels":[],"label_agreement":null},{"id":"W2006092868","doi":"10.1016/j.asw.2008.10.004","title":"Harming not helping: The impact of a Canadian standardized writing assessment on curriculum and pedagogy","year":2008,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Curriculum; Writing assessment; Pedagogy; Sociology; Psychology; Political science","score_opus":0.06685673604162803,"score_gpt":0.43576278137128316,"score_spread":0.3689060453296551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006092868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9267267,0.00011833255,0.000102469545,0.0015548135,0.00014510613,0.00026149955,0.000009241053,0.000055260472,0.0710266],"genre_scores_gemma":[0.9974539,0.00018057194,0.0016597862,0.00013200453,0.00043445244,0.000013291754,0.0000048981715,0.000024541387,0.00009649894],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973892,0.00038319637,0.00044470423,0.00032514601,0.00072626834,0.0007314864],"domain_scores_gemma":[0.99832886,0.0007059657,0.00029383283,0.00019099795,0.00023362134,0.00024668814],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021688563,0.00021090673,0.00034893252,0.0003633111,0.0030779236,0.0004496031,0.00029255258,0.000101597114,0.0000829389],"category_scores_gemma":[0.00035827482,0.00016783908,0.00016392661,0.00072782143,0.00039080234,0.00047502294,0.00007529297,0.0003753738,0.0000027739602],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007877985,0.000071273986,0.96614444,0.000019845855,0.000092206035,0.00005880836,0.013068873,0.00004693269,0.0017208131,0.006507233,0.0006039818,0.011657686],"study_design_scores_gemma":[0.0009911158,0.00012729588,0.89727974,0.0004861708,0.000054170105,0.000025599435,0.09737131,0.0013168587,0.00018348999,0.000108765824,0.0016051991,0.00045030305],"about_ca_topic_score_codex":0.22080065,"about_ca_topic_score_gemma":0.016103903,"teacher_disagreement_score":0.20469674,"about_ca_system_score_codex":0.0004742387,"about_ca_system_score_gemma":0.0017430246,"threshold_uncertainty_score":0.9982199},"labels":[],"label_agreement":null},{"id":"W2006287358","doi":"10.1111/medu.12111","title":"Standardised versus individualised assessment: related problems divided by a common language","year":2013,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Board of Medical Examiners","keywords":"Presentation (obstetrics); Population; Representation (politics); Psychology; Sample (material); Medical education; Politics; Medicine; Law; Political science","score_opus":0.013357299823821727,"score_gpt":0.3821863485403805,"score_spread":0.3688290487165588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006287358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8220528,0.00035023346,0.00005925255,0.025170447,0.0021376277,0.0009811225,0.000008820068,0.00019012686,0.1490496],"genre_scores_gemma":[0.9944127,0.00008446048,0.00015721227,0.0008312392,0.0002174549,0.00021694457,0.00026366708,0.00001357005,0.0038027274],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974459,0.00031902097,0.00028522767,0.00021888272,0.001409517,0.00032145026],"domain_scores_gemma":[0.99912745,0.00021528723,0.00012658852,0.00016688339,0.0001014794,0.00026234158],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009895373,0.00011390875,0.00016804317,0.00006436416,0.00035127922,0.00019350072,0.0003630457,0.0001859799,0.010175568],"category_scores_gemma":[0.0006342409,0.0001036078,0.000053047042,0.00036876503,0.00021263711,0.00033823273,0.000051604315,0.00026160074,0.00019144462],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015916095,0.001163647,0.083735295,0.00003017631,0.00012245057,0.0000011943835,0.075441286,4.388008e-7,0.0002420616,0.0063077314,0.73611456,0.09682524],"study_design_scores_gemma":[0.009732026,0.00037975403,0.305583,0.00034695247,0.0002149125,0.0000010659445,0.13721812,0.00040434074,0.00006380921,0.0047144,0.54021436,0.0011272696],"about_ca_topic_score_codex":0.0044916193,"about_ca_topic_score_gemma":0.00047754313,"teacher_disagreement_score":0.22184771,"about_ca_system_score_codex":0.0002448665,"about_ca_system_score_gemma":0.0013477508,"threshold_uncertainty_score":0.9907293},"labels":[],"label_agreement":null},{"id":"W2009280762","doi":"10.1007/s11135-011-9457-6","title":"The need for documenting validation transactions: a qualitative component of the testing validation process","year":2011,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Champlain Regional College","funders":"","keywords":"Validator; Computer science; Documentation; Test (biology); Process (computing); Component (thermodynamics); Argument (complex analysis); Data science; Process management; Knowledge management; Software engineering; World Wide Web; Programming language; Business","score_opus":0.27900089821310037,"score_gpt":0.4818244700823256,"score_spread":0.20282357186922523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009280762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.976824,0.00002620164,0.016895913,0.0008750444,0.00044378106,0.0010346267,0.000014052622,0.000056160123,0.003830246],"genre_scores_gemma":[0.99807,0.000010350942,0.0014782448,0.000026755979,0.000061907835,0.00008660862,0.000005037975,0.000007421965,0.00025365356],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9972294,0.0012185137,0.00052122265,0.00018666935,0.00059587095,0.0002483405],"domain_scores_gemma":[0.99691886,0.0017598076,0.0005881455,0.00019563577,0.0005020014,0.0000355628],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006813724,0.00010036847,0.0001646312,0.000028931921,0.0017742128,0.00010998189,0.00039405227,0.000059316142,0.00003611115],"category_scores_gemma":[0.0014313705,0.00006861508,0.00013601895,0.00046478424,0.00033442833,0.00040894552,0.000018547886,0.000107236396,0.00000376872],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018821436,0.0005086918,0.14817858,0.00020272068,0.00016671418,7.047212e-8,0.6173115,0.00003293224,0.0026011905,0.22644804,0.00009083963,0.0042704986],"study_design_scores_gemma":[0.0013865464,0.00015825423,0.2147366,0.00016623407,0.0002455689,2.5264174e-7,0.68402314,0.00043035182,0.024375865,0.072707124,0.0012621211,0.0005079394],"about_ca_topic_score_codex":0.0069920644,"about_ca_topic_score_gemma":0.0014956222,"teacher_disagreement_score":0.15374093,"about_ca_system_score_codex":0.00007071148,"about_ca_system_score_gemma":0.00014818489,"threshold_uncertainty_score":0.99962044},"labels":[],"label_agreement":null},{"id":"W2011625643","doi":"10.5430/wjel.v3n4p11","title":"In Search for Implementing Learning-Oriented Assessment in an EFL Setting","year":2013,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Portfolio; Peer assessment; Computer science; Curriculum; Mathematics education; Assessment for learning; Psychology; Pedagogy; Formative assessment","score_opus":0.019598698348010837,"score_gpt":0.3814233614119601,"score_spread":0.3618246630639493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011625643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98179984,0.00010559083,0.00004727312,0.00047269455,0.00048208743,0.00036351834,0.0000010543465,0.00001479723,0.016713157],"genre_scores_gemma":[0.9944408,0.000016409303,0.0030115745,0.00007845176,0.0011800724,0.000016747721,0.000004723731,0.00001381439,0.0012374076],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99802524,0.00033598518,0.00049251475,0.00013742295,0.00048552005,0.00052333216],"domain_scores_gemma":[0.9988377,0.00031202624,0.0002389369,0.00007424995,0.00042329082,0.000113792965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036348975,0.00009667007,0.00021969015,0.00037456816,0.0001797564,0.00018507098,0.00027828474,0.000040020605,0.00073554885],"category_scores_gemma":[0.00044940697,0.00009205928,0.00008075983,0.0005574679,0.00003870076,0.0009161532,0.00005731777,0.0005155048,0.0000026054843],"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":[0.00001883584,0.00017071565,0.7831878,0.000015918053,0.000018976281,0.0000307038,0.20199007,0.00007916673,0.00081959966,0.0024185919,0.0009169224,0.010332697],"study_design_scores_gemma":[0.0029887846,0.00023889999,0.17023379,0.000164972,0.000018468823,6.164131e-7,0.78353053,0.0005175223,0.00019102386,0.00011994396,0.041716754,0.00027871397],"about_ca_topic_score_codex":0.0010259117,"about_ca_topic_score_gemma":0.0059997356,"teacher_disagreement_score":0.612954,"about_ca_system_score_codex":0.00023359424,"about_ca_system_score_gemma":0.00015584963,"threshold_uncertainty_score":0.8053744},"labels":[],"label_agreement":null},{"id":"W2012525493","doi":"10.1016/j.jmathb.2015.01.004","title":"The assessment of mathematical literacy of linguistic minority students: Results of a multi-method investigation","year":2015,"lang":"en","type":"article","venue":"The Journal of Mathematical Behavior","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of British Columbia; University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Differential item functioning; Psychology; Test (biology); Mathematics education; Literacy; Think aloud protocol; Language proficiency; Language assessment; Pedagogy; Item response theory; Developmental psychology; Computer science; Psychometrics","score_opus":0.10903136226057507,"score_gpt":0.4817575674014773,"score_spread":0.3727262051409022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012525493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98777413,0.00009670506,0.00830119,0.0006933635,0.00024144056,0.0006063661,0.0000119034785,0.000008157875,0.0022667642],"genre_scores_gemma":[0.93683374,0.000034955752,0.062581316,0.0000103169905,0.00011595176,0.000007896837,7.1078875e-7,0.000009441724,0.00040569215],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99490416,0.0010277447,0.0017051012,0.00009415949,0.0020453625,0.00022349878],"domain_scores_gemma":[0.9931171,0.0034015502,0.0016831815,0.0003290865,0.0012881383,0.00018093476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013344735,0.00014105832,0.0005549676,0.00007990074,0.00014372218,0.000055789595,0.0010317205,0.000091152004,0.000037645317],"category_scores_gemma":[0.0050228722,0.00007614056,0.00019570076,0.00028869498,0.00070249324,0.00014420897,0.00015255538,0.00030142005,0.0000037045747],"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":[0.0011306058,0.01414469,0.19832504,0.0009733897,0.00081059564,0.000037437403,0.4960099,0.00004643721,0.011534489,0.26749793,0.0018369774,0.00765253],"study_design_scores_gemma":[0.018636584,0.00463657,0.49680686,0.0034833315,0.007590387,0.00011987267,0.13881911,0.005439709,0.008808947,0.31336614,0.0011726833,0.0011198136],"about_ca_topic_score_codex":0.000055949124,"about_ca_topic_score_gemma":0.000014415347,"teacher_disagreement_score":0.3571908,"about_ca_system_score_codex":0.000092518334,"about_ca_system_score_gemma":0.00033789276,"threshold_uncertainty_score":0.601321},"labels":[],"label_agreement":null},{"id":"W2013464569","doi":"10.1080/0969594x.2013.776943","title":"Fair and equitable assessment practices for all students","year":2013,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University; University of Lethbridge; University of Alberta; University of Calgary","funders":"","keywords":"Intrusiveness; Equity (law); Psychology; Public relations; Best practice; Medical education; Applied psychology; Pedagogy; Social psychology; Political science; Medicine","score_opus":0.10231687439942877,"score_gpt":0.5279200270248844,"score_spread":0.4256031526254556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013464569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46493626,0.0006306556,0.0005220761,0.13636775,0.0010223944,0.004128053,0.000010650142,0.000100410936,0.39228174],"genre_scores_gemma":[0.94570065,0.004114734,0.03419917,0.0039670034,0.0007121699,0.001296294,0.000034549594,0.000024730723,0.009950678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997134,0.00069686555,0.00044538258,0.00046513675,0.000657997,0.0006006595],"domain_scores_gemma":[0.99436396,0.004074993,0.00076985866,0.00023613211,0.00031386153,0.0002411873],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004179651,0.0002085413,0.00023710544,0.0002521336,0.00064258976,0.0011841076,0.0003592938,0.00013295797,0.00014068041],"category_scores_gemma":[0.0031734009,0.00021186711,0.000036221198,0.00034648326,0.00015327988,0.0034884426,0.00026249912,0.0002812839,0.000014772481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042749958,0.0018428091,0.22291036,0.00009676772,0.0001433305,8.5242425e-7,0.018040108,0.000005288103,0.00023544098,0.7311828,0.0038199974,0.021679504],"study_design_scores_gemma":[0.0006782885,0.00012184947,0.2919045,0.000035385823,0.00008289351,0.000004646491,0.08186039,0.00009393153,0.0000036730048,0.007085557,0.6178655,0.00026338428],"about_ca_topic_score_codex":0.019623796,"about_ca_topic_score_gemma":0.0012149833,"teacher_disagreement_score":0.72409725,"about_ca_system_score_codex":0.00046339657,"about_ca_system_score_gemma":0.0021814776,"threshold_uncertainty_score":0.9998528},"labels":[],"label_agreement":null},{"id":"W2013836468","doi":"10.1080/09500790.2010.490875","title":"Assessment use, self-efficacy and mathematics achievement: comparative analysis of PISA 2003 data of Finland, Canada and the USA","year":2010,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Division of Mathematical Sciences","keywords":"Student achievement; Mathematics education; Academic achievement; Psychology; Test (biology); Achievement test; Standardized test; Pedagogy","score_opus":0.27445317848692796,"score_gpt":0.5499734689545585,"score_spread":0.2755202904676305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013836468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928948,0.00006547527,0.000017999277,0.0017847428,0.00013459088,0.0010003843,0.00001734194,0.0000014508355,0.004083178],"genre_scores_gemma":[0.996965,0.00018690998,0.0023876557,0.00001706957,0.000038517603,0.000056892786,0.000082343075,0.0000020796767,0.00026353172],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968417,0.0010273593,0.00029617277,0.00018518747,0.0015016766,0.00014786406],"domain_scores_gemma":[0.99686074,0.0014208201,0.00017528802,0.00034107442,0.0011501199,0.000051963347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011580428,0.00005610737,0.00018942398,0.00024932722,0.00021182052,0.00008319369,0.00029665156,0.000034966128,0.00021211742],"category_scores_gemma":[0.0011453219,0.000042913067,0.000009314172,0.0018425072,0.00034404284,0.00025075383,0.000106395426,0.00019007885,6.710512e-7],"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":[0.000031130512,0.0012119007,0.8807703,0.00003992162,0.00038843995,6.104295e-8,0.044249635,0.00005675967,0.0002637191,0.062019393,0.00412392,0.0068447976],"study_design_scores_gemma":[0.0005699018,0.000015628511,0.9640101,0.000013732543,0.0001777702,3.438608e-8,0.016390882,0.016013406,0.000009377681,0.00052878645,0.0022261858,0.000044148546],"about_ca_topic_score_codex":0.37347364,"about_ca_topic_score_gemma":0.8909272,"teacher_disagreement_score":0.51745355,"about_ca_system_score_codex":0.00013788702,"about_ca_system_score_gemma":0.0040447824,"threshold_uncertainty_score":0.717527},"labels":[],"label_agreement":null},{"id":"W2015223621","doi":"10.1080/15434303.2014.981334","title":"Interpreting the Impact of the Ontario Secondary School Literacy Test on Second Language Students Within an Argument-Based Validation Framework","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Literacy; Context (archaeology); Mathematics education; Test (biology); Curriculum; Reading (process); Ell; Language proficiency; Empirical research; Psychology; Pedagogy; Language assessment; Linguistics; Teaching method; Mathematics","score_opus":0.016460365348475472,"score_gpt":0.3890332495887422,"score_spread":0.37257288424026674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015223621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859685,0.000040822077,0.00015857891,0.00032602434,0.0005758933,0.00080301164,0.0000351297,0.0000722697,0.012019774],"genre_scores_gemma":[0.99618423,3.5618834e-7,0.0008259438,0.00048217253,0.00029143973,0.000052465384,0.00004822072,0.000027237502,0.0020879274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99657845,0.0007991931,0.00048390598,0.00036914388,0.0013109886,0.0004583026],"domain_scores_gemma":[0.9977991,0.00056095794,0.00049451157,0.00075849897,0.00015495328,0.00023198761],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021565882,0.0002811441,0.0002830522,0.000096956406,0.00043607363,0.0007812304,0.0012597785,0.00013808391,0.0022242996],"category_scores_gemma":[0.00020229367,0.0001712414,0.00022500812,0.00037080614,0.0001524563,0.0006747794,0.00007754562,0.000809064,0.000038037633],"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":[0.00004974287,0.00057281245,0.5438338,0.000008453961,0.00009432029,0.0000107441465,0.4514106,0.000049905557,0.0008062328,0.00023366115,0.00060540007,0.0023243693],"study_design_scores_gemma":[0.0015062449,0.0020713834,0.7565621,0.00027438148,0.00007929908,0.0000013213473,0.23761442,0.00028561972,0.00048600757,0.0005585418,0.0001667983,0.00039389348],"about_ca_topic_score_codex":0.031859588,"about_ca_topic_score_gemma":0.03417153,"teacher_disagreement_score":0.21379615,"about_ca_system_score_codex":0.0009341819,"about_ca_system_score_gemma":0.0011939552,"threshold_uncertainty_score":0.9986878},"labels":[],"label_agreement":null},{"id":"W2015457266","doi":"10.1016/j.system.2013.07.010","title":"Putting testing researchers to the test: An exploratory study on the TOEFL iBT","year":2013,"lang":"en","type":"article","venue":"System","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Saint Vincent University; Carleton University; Queen's University","funders":"","keywords":"Test of English as a Foreign Language; Computer science; Context (archaeology); Construct (python library); Test (biology); Exploratory research; Variance (accounting); Focus group; Psychology; Construct validity; Language assessment; Mathematics education; Psychometrics; Sociology; Developmental psychology; Programming language","score_opus":0.24683390530327248,"score_gpt":0.4152035437005829,"score_spread":0.1683696383973104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015457266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91603774,0.0000129566915,0.0000067754477,0.004814158,0.0002625439,0.0020262138,8.014131e-7,0.00013858697,0.07670022],"genre_scores_gemma":[0.9973331,3.0326356e-7,0.00007781402,0.00019087111,0.0006747076,0.00036876264,1.5569992e-7,0.000013115859,0.0013411458],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99735826,0.0010010629,0.00017717593,0.00022870685,0.0008501651,0.00038462473],"domain_scores_gemma":[0.9974251,0.0018223014,0.0000693697,0.0003723893,0.0001860394,0.000124821],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004578231,0.00009572165,0.00010520074,0.000039555514,0.0014818761,0.00051409396,0.00076946546,0.000032393895,0.00005110963],"category_scores_gemma":[0.0015249876,0.000051081184,0.000028080232,0.00058432145,0.00006953815,0.0002130571,0.0001240843,0.00017683633,0.0009978964],"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":[0.0000053009267,0.00030158838,0.4821432,0.00001862837,0.000049006823,0.0000096990925,0.48306268,0.000022383305,0.00072916946,0.005692454,0.016290836,0.011675053],"study_design_scores_gemma":[0.0000954268,0.00023896314,0.08288997,0.000061021477,0.000006282732,1.5935112e-7,0.9145845,0.00011344637,0.000013361565,0.0000650464,0.0018441243,0.000087698674],"about_ca_topic_score_codex":0.001870495,"about_ca_topic_score_gemma":0.0011528888,"teacher_disagreement_score":0.4315218,"about_ca_system_score_codex":0.00016016433,"about_ca_system_score_gemma":0.00009326054,"threshold_uncertainty_score":0.9998181},"labels":[],"label_agreement":null},{"id":"W2017217841","doi":"10.1080/00220973.2013.795127","title":"The “None of the Above” Option in Multiple-Choice Testing: An Experimental Study","year":2013,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Multiple choice; Test (biology); Incentive; Actuarial science; Psychology; Social psychology; Economics; Statistics; Mathematics; Significant difference; Microeconomics","score_opus":0.06713802323590551,"score_gpt":0.41460810319018354,"score_spread":0.34747007995427803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017217841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945312,0.00087322475,0.0000011893527,0.0006721889,0.001098615,0.0007501912,1.951967e-7,0.0000047894755,0.0020683687],"genre_scores_gemma":[0.99907017,0.000018727695,0.00009479665,0.00006038756,0.00040101903,0.00003596951,3.1950506e-7,0.0000081683975,0.00031045862],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99816114,0.0006049947,0.00041001115,0.00007950999,0.00057628413,0.00016804661],"domain_scores_gemma":[0.99851865,0.00057066284,0.00047911133,0.00019895914,0.00017459187,0.000058024096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011670018,0.00009449516,0.00011618852,0.000046706853,0.0006329976,0.00010566362,0.00065791735,0.00003139783,0.0000769732],"category_scores_gemma":[0.0003178297,0.00004922003,0.000052353047,0.0002997528,0.00023813633,0.00055162166,0.0000658018,0.00016664433,0.000005711296],"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":[0.0001019721,0.0068968935,0.38735816,0.0000016686528,0.000036800753,1.7162584e-7,0.26603302,0.00003163016,0.33579618,0.0006726721,0.00086788187,0.0022029583],"study_design_scores_gemma":[0.0005033895,0.00040900652,0.41624194,0.00002334324,0.000013196896,0.000002219643,0.56721467,0.000045596364,0.015169061,0.00009068561,0.0002236711,0.000063223866],"about_ca_topic_score_codex":0.0056610927,"about_ca_topic_score_gemma":0.00046491812,"teacher_disagreement_score":0.3206271,"about_ca_system_score_codex":0.00024665325,"about_ca_system_score_gemma":0.00026120475,"threshold_uncertainty_score":0.8557916},"labels":[],"label_agreement":null},{"id":"W2021788015","doi":"10.1080/14926150409556629","title":"Between student observation and student assessment: A critical reflection","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Active listening; Mathematics education; Psychology; Reflection (computer programming); Pedagogy; Computer science; Communication","score_opus":0.043190057674966746,"score_gpt":0.42379406979282436,"score_spread":0.3806040121178576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021788015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824013,0.00020268129,0.0006146418,0.014090669,0.00046607386,0.00014423455,5.7156444e-7,0.0000099247045,0.0020699014],"genre_scores_gemma":[0.98375523,0.00008357122,0.015947154,0.000045912035,0.000116959236,0.0000050873664,3.0700423e-7,0.0000037754364,0.00004199183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9990024,0.000014491685,0.00025899638,0.00012693048,0.0003641433,0.00023304748],"domain_scores_gemma":[0.9989184,0.00005298557,0.00016431547,0.00008320786,0.0004940716,0.00028698271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013373834,0.00006856514,0.00013294784,0.00070576166,0.0009767822,0.00027795008,0.00028019957,0.0000832207,0.00001006268],"category_scores_gemma":[0.0003743315,0.00006426311,0.000014286011,0.0008632126,0.0016978618,0.000457083,0.000023782713,0.00016868341,0.0000011337444],"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":[2.7886966e-7,0.0000921372,0.39312777,0.000012416354,0.000011311499,0.0000020665518,0.020212745,6.3271773e-7,0.0004642833,0.5782254,0.000033631823,0.007817367],"study_design_scores_gemma":[0.0003125328,0.00023522857,0.6178852,0.00019095906,0.000077673205,0.000034110817,0.16040052,0.0000064590095,0.00013919607,0.21896265,0.0015857741,0.00016972465],"about_ca_topic_score_codex":0.00068833126,"about_ca_topic_score_gemma":0.0029695828,"teacher_disagreement_score":0.3592627,"about_ca_system_score_codex":0.00045517937,"about_ca_system_score_gemma":0.0038865209,"threshold_uncertainty_score":0.7512718},"labels":[],"label_agreement":null},{"id":"W2023466828","doi":"10.1111/j.0965-075x.2005.00307.x","title":"Who Will Evaluate Me? Rater Selection in Multi‐Source Assessment Contexts","year":2005,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute; Concordia University","funders":"","keywords":"Psychology; Preference; Affect (linguistics); Selection (genetic algorithm); Inter-rater reliability; Social psychology; Performance appraisal; Applied psychology; Developmental psychology; Rating scale; Statistics; Computer science; Communication","score_opus":0.03028675750328179,"score_gpt":0.4241642399649722,"score_spread":0.3938774824616904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023466828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95611185,0.00018782406,0.023147546,0.011628427,0.0012744342,0.00034090082,0.0000021039455,0.000038454426,0.007268462],"genre_scores_gemma":[0.9883273,0.00085683475,0.006715229,0.00038822886,0.0008362373,0.000010790738,0.0000023986834,0.000012654201,0.0028503288],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974731,0.00032865696,0.0005939282,0.00020129129,0.0011506649,0.00025231528],"domain_scores_gemma":[0.99853075,0.00010194761,0.0004362368,0.00003471163,0.00077078235,0.00012560126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017721276,0.00014790251,0.00024164216,0.00041274674,0.00021754733,0.00031160197,0.00025192866,0.00009108653,0.00060795655],"category_scores_gemma":[0.00004970931,0.00014062863,0.00009696204,0.000256012,0.00006491081,0.0010402611,0.000043700824,0.00042748218,0.000006140276],"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":[0.00021679388,0.0012416071,0.8069745,0.000008863414,0.00052668806,0.000016583934,0.0061414135,0.0026603278,0.012027509,0.008073498,0.0023395226,0.15977271],"study_design_scores_gemma":[0.0053459876,0.00035826914,0.79116654,0.00020087324,0.00007186007,0.00006479411,0.003976132,0.028524358,0.00048030895,0.00037326978,0.16906393,0.0003736577],"about_ca_topic_score_codex":0.00026432346,"about_ca_topic_score_gemma":0.001947342,"teacher_disagreement_score":0.16672441,"about_ca_system_score_codex":0.0010842724,"about_ca_system_score_gemma":0.0004463065,"threshold_uncertainty_score":0.6656698},"labels":[],"label_agreement":null},{"id":"W2024930517","doi":"10.5430/ijhe.v1n1p2","title":"Multi-disciplinary Peer-mark Moderation of Group Work","year":2012,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Loughborough University; Joint Information Systems Committee; Higher Education Academy","keywords":"Moderation; Transparency (behavior); Peer review; Psychology; Computer science; Peer assessment; World Wide Web; Social psychology; Mathematics education; Political science; Computer security","score_opus":0.04742055874931791,"score_gpt":0.4274911673045354,"score_spread":0.3800706085552175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024930517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94967866,0.0012359646,0.0011446007,0.010129346,0.018716212,0.00014107778,0.0000025456438,0.000012907152,0.018938687],"genre_scores_gemma":[0.9821984,0.0000565888,0.0055448087,0.00009950659,0.0037248633,0.0000038919125,0.000010958956,0.000006470136,0.00835449],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99849844,0.00009360655,0.00033774917,0.000057851536,0.00089026074,0.00012211461],"domain_scores_gemma":[0.9984473,0.000078443445,0.00043528993,0.00005493662,0.00090072624,0.00008332284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007368207,0.00006371375,0.00009863312,0.000160965,0.000086934444,0.000060008748,0.0003125325,0.000055231547,0.00054899167],"category_scores_gemma":[0.000064409185,0.000058732963,0.000086508764,0.00013807032,0.000058909984,0.00083326513,0.000029931458,0.00010192482,0.000018131897],"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":[0.00022099931,0.0030959544,0.8406416,0.000008088517,0.00030400034,0.0000014714292,0.044699807,0.00005593412,0.0026549269,0.04464347,0.049682483,0.013991245],"study_design_scores_gemma":[0.0003935011,0.00003501717,0.9381801,0.00006294366,0.000036114805,0.0000025211423,0.003592446,0.000007465961,0.000092701,0.0010612891,0.056441236,0.000094691924],"about_ca_topic_score_codex":0.00006774657,"about_ca_topic_score_gemma":0.000011731401,"teacher_disagreement_score":0.09753845,"about_ca_system_score_codex":0.00020147278,"about_ca_system_score_gemma":0.00018411104,"threshold_uncertainty_score":0.6011074},"labels":[],"label_agreement":null},{"id":"W2025703093","doi":"10.1007/s10459-004-8740-x","title":"Does Blueprint Publication Affect Students’ Perception of Validity of the Evaluation Process?","year":2005,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Affect (linguistics); Blueprint; Perception; Psychology; Process (computing); Medical education; Computer science; Applied psychology; Medicine; Engineering; Communication","score_opus":0.06317850139397954,"score_gpt":0.5164379696194489,"score_spread":0.45325946822546936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025703093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9845681,0.00038820982,0.00006106939,0.007441868,0.0011350258,0.001228321,0.0000011920323,0.000013052237,0.0051631257],"genre_scores_gemma":[0.9973428,0.0012064894,0.00084835006,0.00015910101,0.00019138756,0.00012608133,0.000003660099,0.0000026958467,0.00011943932],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99694693,0.00060805026,0.00048676832,0.00026038155,0.001480856,0.00021702568],"domain_scores_gemma":[0.9984983,0.0001589291,0.0006735645,0.00017684832,0.00044490176,0.000047446323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074617704,0.00007320471,0.00013436384,0.00015528708,0.00041296077,0.000043542583,0.000632201,0.000039910024,0.00014080692],"category_scores_gemma":[0.00070231146,0.000045212546,0.000039080227,0.0012202356,0.00048433433,0.0012548603,0.000038422837,0.000080517675,0.000003667907],"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":[0.0000035745281,0.00028252887,0.88690424,0.00006587943,9.281772e-7,7.7265516e-10,0.017773801,0.0004281698,0.00003887326,0.0031661026,0.00003935364,0.09129656],"study_design_scores_gemma":[0.00014922573,0.000063563435,0.95968264,0.00014408721,0.0000061877868,6.1122044e-8,0.03202512,0.00039630724,0.00016260655,0.00443892,0.0028602434,0.000071026945],"about_ca_topic_score_codex":0.00087661104,"about_ca_topic_score_gemma":0.0035224592,"teacher_disagreement_score":0.091225535,"about_ca_system_score_codex":0.00042199314,"about_ca_system_score_gemma":0.0017270674,"threshold_uncertainty_score":0.31762022},"labels":[],"label_agreement":null},{"id":"W2026630819","doi":"10.1080/14926150609556699","title":"Junior secondary science teachers’ understanding and practice of alternative assessment in Hong Kong: Implications for teacher professional development","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Professional development; Mathematics education; Alternative assessment; Science education; Medical education; Science learning; Pedagogy; Psychology; Formative assessment; Medicine","score_opus":0.04644577135039397,"score_gpt":0.393949517339641,"score_spread":0.34750374598924705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026630819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782091,0.00015962482,0.0019095921,0.011754759,0.00036417972,0.0003277959,0.0000014360827,0.0000038442504,0.0072697],"genre_scores_gemma":[0.9515597,0.0000146894035,0.04820626,0.000017180791,0.000029024312,0.000012317824,4.1797077e-7,0.000003011057,0.00015738296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9990951,0.000017694267,0.00029470262,0.00013350761,0.0002303842,0.00022862256],"domain_scores_gemma":[0.99879557,0.00015320755,0.0003717897,0.00006889269,0.00048273365,0.00012781614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032495414,0.000059607257,0.00011522496,0.0010901229,0.00084810174,0.00010280852,0.0003142541,0.000051818388,0.000006205789],"category_scores_gemma":[0.00069032895,0.000054553588,0.000009867168,0.0009970985,0.0026160218,0.0005908099,0.000027748365,0.00015245062,9.233098e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013232117,0.00017367235,0.10170536,0.000017605063,0.0000071302597,4.230845e-7,0.029578602,0.0000011315327,0.0030938133,0.856233,0.00015831931,0.009029629],"study_design_scores_gemma":[0.00047081185,0.00008605893,0.27824315,0.0002827832,0.00003251731,0.00003978002,0.47154135,0.000107734246,0.0005957311,0.24552774,0.0028721918,0.00020015717],"about_ca_topic_score_codex":0.00059989974,"about_ca_topic_score_gemma":0.0037935306,"teacher_disagreement_score":0.61070526,"about_ca_system_score_codex":0.0007623813,"about_ca_system_score_gemma":0.013134758,"threshold_uncertainty_score":0.99245983},"labels":[],"label_agreement":null},{"id":"W2036552474","doi":"10.1007/s10459-005-2327-z","title":"Using a Sampling Strategy to Address Psychometric Challenges in Tutorial-Based Assessments","year":2006,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sampling (signal processing); Medical education; Computer science; Educational measurement; Medical physics; Psychology; Data science; Medicine; Curriculum; Pedagogy","score_opus":0.22663524795726642,"score_gpt":0.5530907750885159,"score_spread":0.3264555271312495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036552474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8867594,0.033048987,0.001905738,0.0054937797,0.010066297,0.0022962017,0.0000043004857,0.000095435484,0.06032989],"genre_scores_gemma":[0.9790921,0.0028439004,0.017006772,0.0002219659,0.0006690136,0.00009833502,0.0000039194156,0.0000072499847,0.000056735556],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99728477,0.00029790096,0.00051345094,0.0005068111,0.0007589438,0.0006381443],"domain_scores_gemma":[0.9990983,0.00030866536,0.00024605406,0.00013545746,0.00008530826,0.00012622397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030550214,0.00013047102,0.00021285572,0.0010598899,0.00051187375,0.00015042021,0.0004280843,0.00006107033,0.00003145406],"category_scores_gemma":[0.0001511107,0.0001365883,0.000025372396,0.003988095,0.00016186073,0.0009872658,0.000021306161,0.00012627884,0.0000058051005],"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":[0.000026479653,0.0009040429,0.65482694,0.00014691596,0.0000013389064,4.088809e-7,0.0042909808,0.04230682,0.000035503344,0.05795266,0.000082413135,0.23942548],"study_design_scores_gemma":[0.0011537616,0.00073791586,0.8142114,0.0011261466,0.0000058435357,6.543168e-7,0.06156416,0.002584984,0.000018767838,0.027880764,0.089875944,0.00083965616],"about_ca_topic_score_codex":0.0144778,"about_ca_topic_score_gemma":0.02863886,"teacher_disagreement_score":0.23858583,"about_ca_system_score_codex":0.00084092864,"about_ca_system_score_gemma":0.0024700598,"threshold_uncertainty_score":0.99208486},"labels":[],"label_agreement":null},{"id":"W2038816208","doi":"10.5539/hes.v1n2p107","title":"Fairness of IELTS Test Scores in University Admission","year":2011,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Context (archaeology); Language proficiency; Psychology; Language assessment; Interpretation (philosophy); Empirical research; Medical education; Mathematics education; Applied psychology; Medicine; Computer science; Statistics","score_opus":0.11572440948171929,"score_gpt":0.3958591156896718,"score_spread":0.2801347062079525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038816208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88353807,0.00068695424,9.733327e-7,0.0005637364,0.00084053754,0.000097727876,7.953055e-7,0.000019506735,0.11425171],"genre_scores_gemma":[0.9770831,0.00045264902,0.00018080835,0.000026059402,0.00007471812,0.0000028055606,7.0535293e-7,0.000002340982,0.0221768],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995089,0.00005386213,0.00009200403,0.00010221925,0.00014449822,0.00009849593],"domain_scores_gemma":[0.99955904,0.00010189267,0.00006785239,0.00006790651,0.00017070411,0.00003257397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014873866,0.000049340048,0.00010214313,0.00008653036,0.00013225722,0.00000464505,0.000120321696,0.00002973927,0.00041028394],"category_scores_gemma":[0.00003474929,0.00004643317,0.000021398677,0.00031767655,0.00015348195,0.00013481449,0.00004133474,0.000033326185,0.000015923526],"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":[0.000008872671,0.0003596725,0.9336359,0.000011879036,0.000012746497,4.5118608e-7,0.031145858,3.4743945e-8,0.000026387987,0.029268155,0.005210741,0.00031932586],"study_design_scores_gemma":[0.00010892888,0.00001573436,0.8861148,0.000040071278,0.000008664788,1.6114694e-8,0.08407332,3.8176456e-8,0.00005440713,0.00071715453,0.028814385,0.000052505336],"about_ca_topic_score_codex":0.0015341637,"about_ca_topic_score_gemma":0.0005882817,"teacher_disagreement_score":0.09354506,"about_ca_system_score_codex":0.00007590156,"about_ca_system_score_gemma":0.00016529392,"threshold_uncertainty_score":0.44923216},"labels":[],"label_agreement":null},{"id":"W2039255653","doi":"10.7202/039179ar","title":"Student Choice between Computer and Traditional Paper-and-Pencil University Tests: What Predicts Preference and Performance?","year":2009,"lang":"en","type":"article","venue":"Revue internationale des technologies en pédagogie universitaire","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Pencil (optics); Multiple choice; Preference; Test (biology); Psychology; Significant difference; Mathematics education; Cognition; Computer science; Statistics; Mathematics; Engineering","score_opus":0.0694845535592559,"score_gpt":0.290109193583946,"score_spread":0.2206246400246901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039255653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98929846,0.0004696575,0.00009121401,0.0057745557,0.000075770215,0.00020710184,0.000014168263,0.00029846854,0.0037705898],"genre_scores_gemma":[0.9819036,0.013539049,0.0010322954,0.000034377743,0.00008983608,9.00782e-7,0.000013145861,0.0000039748957,0.0033827862],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99904776,0.00004310232,0.00010811919,0.00030909336,0.00028794768,0.00020397366],"domain_scores_gemma":[0.99929136,0.00035448623,0.00007691746,0.00010598829,0.00010980487,0.000061445775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015624372,0.00013589555,0.00015640758,0.00017517076,0.0005063125,0.00016076291,0.00045736996,0.00015260097,0.000017549815],"category_scores_gemma":[0.00006769563,0.00014921441,0.000028928267,0.00018262115,0.00059213274,0.0017647706,0.00026697956,0.00018955611,0.0000027209196],"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":[0.000010629812,0.000056795365,0.5920531,0.000022075588,0.00007156713,0.000021170496,0.0052894307,0.000004396121,0.00001810987,0.012883436,0.00020020505,0.38936907],"study_design_scores_gemma":[0.0004637716,0.00029215481,0.9398258,0.00020206318,0.00004264987,0.0000063353355,0.039009165,0.00009366957,0.000010118324,0.0010473891,0.018823234,0.00018367262],"about_ca_topic_score_codex":0.00004630662,"about_ca_topic_score_gemma":0.00017754527,"teacher_disagreement_score":0.3891854,"about_ca_system_score_codex":0.00033442274,"about_ca_system_score_gemma":0.00005835278,"threshold_uncertainty_score":0.60847867},"labels":[],"label_agreement":null},{"id":"W2043035035","doi":"10.3200/jexe.77.4.311-338","title":"Grading Scheme, Test Difficulty, and the Immediate Feedback Assessment Technique","year":2009,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Brock University","keywords":"Grading (engineering); Scheme (mathematics); Multiple choice; Test (biology); Classification scheme; Mathematics education; Psychology; Machine learning; Computer science; Significant difference; Mathematics; Statistics; Engineering","score_opus":0.015571283466485277,"score_gpt":0.3774555524268169,"score_spread":0.3618842689603316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043035035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.946436,0.0027248054,0.00009852963,0.019086387,0.00081553933,0.000664401,5.126671e-7,0.00001657283,0.030157275],"genre_scores_gemma":[0.9969073,0.00062238687,0.001133625,0.0004100755,0.00052952755,0.000012456769,8.62586e-7,0.0000049690493,0.0003787901],"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","domain_scores_codex":[0.99888396,0.00021969042,0.00026453997,0.000066567176,0.0004128201,0.0001524031],"domain_scores_gemma":[0.99914795,0.00026865382,0.00031627607,0.00009860756,0.00009647806,0.000072053925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015560549,0.000092111906,0.000134782,0.000050199527,0.0005648315,0.00012915488,0.00032022,0.00003726952,0.00005777784],"category_scores_gemma":[0.00009085482,0.00004988147,0.00006116223,0.00017201107,0.0002845362,0.00027609323,0.000029992747,0.00019683797,0.0000028931588],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029355104,0.0023686755,0.015891638,0.000006346241,0.00009150386,0.0000016540848,0.13544577,0.0000020601926,0.7497276,0.06706474,0.018700961,0.010405475],"study_design_scores_gemma":[0.005598745,0.0012315058,0.3095335,0.00031834297,0.00025701712,0.00013905186,0.57963526,0.00007311132,0.07442816,0.014212555,0.013908289,0.0006644456],"about_ca_topic_score_codex":0.00010630443,"about_ca_topic_score_gemma":0.0000049344535,"teacher_disagreement_score":0.67529947,"about_ca_system_score_codex":0.00018132503,"about_ca_system_score_gemma":0.00024299658,"threshold_uncertainty_score":0.4344284},"labels":[],"label_agreement":null},{"id":"W2043393508","doi":"10.5296/ije.v2i2.490","title":"Pre-service Teachers’ Thinking about Student Assessment Issues","year":2010,"lang":"en","type":"article","venue":"International Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Context (archaeology); Psychology; Critical thinking; Introspection; Think aloud protocol; Pedagogy; Computer science","score_opus":0.022617865469250563,"score_gpt":0.4615424663876334,"score_spread":0.43892460091838287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043393508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93650055,0.00011524065,0.00014283754,0.018036712,0.012932691,0.00011108746,8.1541987e-7,0.000014569653,0.03214547],"genre_scores_gemma":[0.9869646,0.00015655674,0.005418047,0.0006707691,0.0044598114,0.0000061622627,0.0000052400064,0.000007862935,0.0023109661],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980346,0.00008738212,0.0003438178,0.00009813473,0.0013097096,0.00012635723],"domain_scores_gemma":[0.9980974,0.000092785514,0.0004401447,0.000087337496,0.0011919376,0.000090354464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001240537,0.00007921065,0.000105394436,0.00016372255,0.00017674883,0.00038234377,0.00090922,0.00006694601,0.0007772791],"category_scores_gemma":[0.00013659694,0.00007300255,0.00007691588,0.000120861165,0.00004674717,0.0006095139,0.00005362792,0.00035085002,0.000021691409],"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":[0.000024160667,0.0011661572,0.6878705,0.0000035693308,0.00025156856,0.000004429747,0.19463508,0.0000148162935,0.0042436756,0.05978395,0.011295835,0.040706288],"study_design_scores_gemma":[0.00028524332,0.00003138936,0.74975365,0.0000590734,0.000030104822,0.0000064659594,0.032732688,0.0000066356547,0.00007721445,0.003972562,0.21294431,0.00010062707],"about_ca_topic_score_codex":0.00072521885,"about_ca_topic_score_gemma":0.0012587182,"teacher_disagreement_score":0.20164849,"about_ca_system_score_codex":0.0002353881,"about_ca_system_score_gemma":0.0009107196,"threshold_uncertainty_score":0.85106605},"labels":[],"label_agreement":null},{"id":"W2044712612","doi":"10.5539/ies.v7n5p68","title":"EFL Primary School Teachers’ Attitudes, Knowledge and Skills in Alternative Assessment","year":2014,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics education; Christian ministry; Test (biology); Alternative assessment; School teachers; Descriptive statistics; Focus group; Knowledge level; Preference; Medical education; Qualitative property; Pedagogy","score_opus":0.042832997362448305,"score_gpt":0.47056223708406836,"score_spread":0.42772923972162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044712612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69667864,0.0017303614,0.00013555169,0.005237631,0.0046705166,0.00028210465,0.0000024648077,0.000043957814,0.2912188],"genre_scores_gemma":[0.9715876,0.0016981524,0.0017215942,0.0005023368,0.0008602437,0.00012498257,0.000012485402,0.000008098924,0.023484483],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987969,0.00017404195,0.00022867118,0.00025334564,0.00038486873,0.00016217529],"domain_scores_gemma":[0.99881697,0.0003501271,0.000108953864,0.00008297736,0.0005678596,0.00007313587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008218651,0.00011314564,0.00016727766,0.00018827713,0.00020428862,0.00010416371,0.0002412833,0.00004116329,0.00014165473],"category_scores_gemma":[0.0006620371,0.00010958871,0.00003281336,0.00014824163,0.00018843067,0.00033501277,0.0001300885,0.00014007762,0.000056413584],"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":[0.000003556928,0.0006417273,0.90065455,0.000009782884,0.00013627973,2.925163e-7,0.024789883,0.0000025458799,0.000026995176,0.041166566,0.010004427,0.022563417],"study_design_scores_gemma":[0.00033351083,0.000016890202,0.8077798,0.00007833437,0.000008949574,3.1726208e-7,0.012102743,0.000009360295,0.0000044982307,0.0032206282,0.17632444,0.00012051638],"about_ca_topic_score_codex":0.0004307914,"about_ca_topic_score_gemma":0.0008682277,"teacher_disagreement_score":0.274909,"about_ca_system_score_codex":0.00071677903,"about_ca_system_score_gemma":0.00037005835,"threshold_uncertainty_score":0.44688982},"labels":[],"label_agreement":null},{"id":"W2049433997","doi":"10.3200/joeb.79.3.176-178","title":"Using Professional Teaching Assistants to Support Large Group Business Communication Classes","year":2004,"lang":"en","type":"article","venue":"Journal of Education for Business","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Grading (engineering); Mathematics education; Business communication; Computer science; Teaching method; Teaching assistant; Pedagogy; Psychology; Engineering","score_opus":0.07617504651563431,"score_gpt":0.45510638266963066,"score_spread":0.3789313361539963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049433997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9536992,0.00014040606,0.021620233,0.012882213,0.006040889,0.00059691136,0.000009094013,0.000024631328,0.004986474],"genre_scores_gemma":[0.9714624,0.00004308485,0.02609347,0.00042876505,0.0010577647,0.00001682174,0.000028803683,0.00001930354,0.00084954995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9983791,0.00013028906,0.0005052402,0.00013032174,0.00057613524,0.00027889857],"domain_scores_gemma":[0.9969628,0.00013080324,0.0006227736,0.00016211592,0.00198095,0.00014059589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018323609,0.00012313316,0.0002262384,0.00027995068,0.0011426306,0.00021043679,0.00047621355,0.00009402806,0.00007769191],"category_scores_gemma":[0.00076173985,0.00011176292,0.00007920573,0.0007346143,0.00005914335,0.0010647391,0.000060444327,0.00018431779,0.0000068244567],"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":[0.0012381631,0.018078595,0.3477733,0.0006118936,0.0004422938,0.000010207096,0.10972263,0.0011885237,0.018144632,0.37767938,0.07621753,0.048892833],"study_design_scores_gemma":[0.0019296062,0.0000977423,0.75392747,0.0008972792,0.00014419621,0.000020061318,0.03703638,0.000008761655,0.00006930101,0.006707827,0.19876058,0.00040077989],"about_ca_topic_score_codex":0.00024668104,"about_ca_topic_score_gemma":0.0003633148,"teacher_disagreement_score":0.40615416,"about_ca_system_score_codex":0.0005181138,"about_ca_system_score_gemma":0.002696528,"threshold_uncertainty_score":0.8788307},"labels":[],"label_agreement":null},{"id":"W20496686","doi":"","title":"ASSESSING CANADA’S STUDENT AID NEED ASSESSMENT POLICIES","year":2003,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.04076856405110143,"score_gpt":0.4061012720258114,"score_spread":0.36533270797471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W20496686","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30637664,0.00003684492,0.00020736008,0.0027444619,0.0007511225,0.00019135872,6.7861237e-7,0.00006962252,0.6896219],"genre_scores_gemma":[0.9795331,0.00003357438,0.0019762958,0.0009856424,0.00017337802,0.000013696865,0.000002190377,0.000011706392,0.017270433],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976093,0.0002647088,0.0002378542,0.00022356241,0.0011232907,0.0005412812],"domain_scores_gemma":[0.9993039,0.00014577177,0.00008347098,0.00017455855,0.00010455109,0.00018776473],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008074199,0.00014634793,0.00018776703,0.000060433802,0.00086652144,0.0005872914,0.00031588238,0.00005889393,0.0013678165],"category_scores_gemma":[0.00007045093,0.00013206595,0.000056084285,0.00030870776,0.000103007995,0.0004069639,0.00004881359,0.00013375243,0.000017018327],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.660422e-7,0.00011417137,0.53499687,0.0000030125398,0.000048706966,0.00000843928,0.0042767464,0.000009033786,0.00012765305,0.44004196,0.01986015,0.0005123766],"study_design_scores_gemma":[0.000431986,0.000018437542,0.38764572,0.000009260937,0.000025123161,5.634286e-7,0.18671928,0.000007716557,0.00007061509,0.00035152753,0.42442963,0.00029013518],"about_ca_topic_score_codex":0.7184204,"about_ca_topic_score_gemma":0.89317256,"teacher_disagreement_score":0.67315644,"about_ca_system_score_codex":0.0007465467,"about_ca_system_score_gemma":0.0030652438,"threshold_uncertainty_score":0.9995451},"labels":[],"label_agreement":null},{"id":"W2049720960","doi":"10.3115/1149293.1149385","title":"Exploring collaborative aspects of knowledge building through collaborative summary notes","year":2005,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capital Regional District; Simon Fraser University","funders":"","keywords":"Knowledge building; Unit (ring theory); Computer science; Knowledge management; Mathematics education; Psychology","score_opus":0.10550017795597491,"score_gpt":0.38699772474706895,"score_spread":0.28149754679109407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049720960","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22161674,0.0009927847,0.0003192381,0.0016502176,0.00041022693,0.0004225725,0.000009264701,0.00011141483,0.7744675],"genre_scores_gemma":[0.98544264,0.0011950015,0.010807881,0.00006328138,0.0006363867,0.000048639045,0.00000239988,0.000013629617,0.0017901385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850076,0.00019155018,0.0002791763,0.0002585832,0.00042107695,0.00034887408],"domain_scores_gemma":[0.9984767,0.00061062607,0.00014094905,0.00013439874,0.0005581018,0.000079237085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004486313,0.00015491975,0.00028164894,0.000083939056,0.00044923107,0.00007869149,0.00028240454,0.00006646566,0.00038554086],"category_scores_gemma":[0.00024193237,0.00014425005,0.00005853955,0.0016227195,0.0002910754,0.001417083,0.00009384908,0.00010143475,0.00006555983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003431185,0.00024317049,0.007671795,0.000012483044,0.000099796125,0.000002229111,0.19749582,0.000027611895,0.00286775,0.78313917,0.0031531507,0.0052527157],"study_design_scores_gemma":[0.0017821483,0.0002905561,0.011443553,0.00021045253,0.000092431386,2.4968222e-7,0.34380665,0.00006972892,0.09781615,0.005866517,0.53773326,0.0008883151],"about_ca_topic_score_codex":0.0004005295,"about_ca_topic_score_gemma":0.0049911807,"teacher_disagreement_score":0.77727264,"about_ca_system_score_codex":0.00019033877,"about_ca_system_score_gemma":0.00050720386,"threshold_uncertainty_score":0.5882346},"labels":[],"label_agreement":null},{"id":"W2050121974","doi":"10.1152/advan.00020.2004","title":"<i>The Art of Evaluation: A Handbook for Educators and Trainers.</i> T. Fenwick and J. Parson. Toronto, Canada: Thompson Educational Press, 2000. ISBN 1-55077-104-3 (US$29.95)","year":2004,"lang":"en","type":"article","venue":"AJP Advances in Physiology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wonder; Economic Justice; Autonomy; Psychology; Sociology; Law; Political science; Social psychology","score_opus":0.011543846979011734,"score_gpt":0.34221257467796906,"score_spread":0.33066872769895733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050121974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6508662,0.2821148,0.00004772957,0.027838612,0.007780127,0.0036666438,0.000039192168,0.000028433995,0.027618216],"genre_scores_gemma":[0.97228706,0.021040149,0.0012209043,0.0005768166,0.0011985976,0.0009107264,0.00009659155,0.000015464417,0.0026537129],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870473,0.0001466306,0.00028766796,0.0003036606,0.00027780797,0.0002795034],"domain_scores_gemma":[0.9988607,0.00048219296,0.0002206521,0.00014184068,0.00021722223,0.00007738849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005335844,0.00013497972,0.00019634145,0.000022153099,0.00042564294,0.000030664913,0.00015669652,0.00007022951,0.00005761981],"category_scores_gemma":[0.0002445423,0.00011823762,0.00003010132,0.00011001518,0.00043281118,0.00044908776,0.000021974476,0.00007793156,6.850441e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006884727,0.0026429282,0.07370232,0.00047412267,0.00027722603,3.4060562e-7,0.11343119,0.0007907912,0.003380195,0.2902963,0.29517406,0.21914203],"study_design_scores_gemma":[0.0013835926,0.00014567672,0.15601541,0.00013935156,0.00008418084,0.0000019977174,0.03203674,0.000055372875,0.00018596418,0.0666983,0.7428861,0.00036725958],"about_ca_topic_score_codex":0.06575624,"about_ca_topic_score_gemma":0.56411463,"teacher_disagreement_score":0.4983584,"about_ca_system_score_codex":0.0005910615,"about_ca_system_score_gemma":0.004794803,"threshold_uncertainty_score":0.940465},"labels":[],"label_agreement":null},{"id":"W2053410856","doi":"10.5054/tj.2011.269751","title":"Generalizability Theory as Evidence of Concerns About Fairness in Large‐Scale ESL Writing Assessments","year":2011,"lang":"en","type":"article","venue":"TESOL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Rating scale; Reliability (semiconductor); Psychology; Variation (astronomy); Scale (ratio); Inter-rater reliability; Mathematics education; Developmental psychology; Geography","score_opus":0.11265739958471804,"score_gpt":0.4387508983425095,"score_spread":0.3260934987577915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053410856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95152384,0.00079425727,0.0012722613,0.00011151867,0.00042527416,0.00019547172,0.0000028821732,0.00002330125,0.04565119],"genre_scores_gemma":[0.99714386,0.00039459858,0.0013591838,0.00012851044,0.00034798315,0.000007716166,5.399007e-7,0.000009792549,0.000607781],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973231,0.00078440487,0.00052540586,0.00020095467,0.000694953,0.00047116014],"domain_scores_gemma":[0.9988185,0.0003186479,0.0003294123,0.00016331741,0.00022057636,0.00014953408],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005168122,0.00012439683,0.00026469165,0.00009610049,0.00030498655,0.00009423918,0.0005775945,0.000099819976,0.0034478288],"category_scores_gemma":[0.00031608288,0.00011391602,0.0001165055,0.00030050531,0.0002606109,0.0006609263,0.000107137115,0.0003385728,0.000026910813],"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":[0.00006782139,0.00023416406,0.942015,0.000015543585,0.000025113672,0.000019605777,0.043042477,0.000001954189,0.00039574908,0.012175773,0.00013993788,0.0018668574],"study_design_scores_gemma":[0.0012496525,0.00022902586,0.8849425,0.0005219363,0.000054651024,0.000010575627,0.081247196,0.000092886454,0.0005222206,0.030109925,0.00067775935,0.00034167292],"about_ca_topic_score_codex":0.00084927573,"about_ca_topic_score_gemma":0.0007354968,"teacher_disagreement_score":0.057072505,"about_ca_system_score_codex":0.00017476977,"about_ca_system_score_gemma":0.00035511778,"threshold_uncertainty_score":0.99746317},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8048983,0.0004378584,0.0000853541,0.004960719,0.0018986425,0.0017855255,0.0000010021623,0.000055424967,0.18587713],"genre_scores_gemma":[0.9912133,0.00022335214,0.0028443325,0.00036141585,0.0004887061,0.0005173077,0.000048357066,0.000019284269,0.004283909],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964021,0.00050533336,0.0006263299,0.0005043023,0.0014640965,0.00049784366],"domain_scores_gemma":[0.99874437,0.00034475356,0.00025407106,0.00021322389,0.00031364302,0.00012996806],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0063800155,0.00020665421,0.00023295623,0.0005510771,0.00026642383,0.00023436971,0.0002334461,0.00017589876,0.0018266847],"category_scores_gemma":[0.00011915034,0.00022123841,0.000040409108,0.0009773329,0.00013235351,0.0007661438,0.00005259586,0.00027414254,0.000014492205],"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":[0.0000106116195,0.00067643286,0.9030169,0.000025293697,0.000012681162,8.2166866e-7,0.0040269494,0.000033707747,0.0002119078,0.072178595,0.00071056484,0.019095497],"study_design_scores_gemma":[0.00083870126,0.000052488576,0.96646416,0.00008957901,0.000036435198,3.7331196e-7,0.013483385,0.00018430372,0.000007552866,0.00654562,0.012054151,0.00024322125],"about_ca_topic_score_codex":0.0011585525,"about_ca_topic_score_gemma":0.0063330876,"teacher_disagreement_score":0.18631499,"about_ca_system_score_codex":0.0016661279,"about_ca_system_score_gemma":0.002593879,"threshold_uncertainty_score":0.9990858},"labels":[],"label_agreement":null},{"id":"W2055895965","doi":"10.1080/17439880802324061","title":"Electronic assessment issues and practices in Pakistan: a case study","year":2008,"lang":"en","type":"article","venue":"Learning Media and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Kent State University","keywords":"Scope (computer science); Political science; Institution; Resource (disambiguation); Quantitative assessment; Needs assessment; Higher education; Knowledge management; Public relations; Business; Computer science; Risk analysis (engineering)","score_opus":0.030134497116153357,"score_gpt":0.42456706770363806,"score_spread":0.3944325705874847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055895965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99287605,0.0012969591,0.000004438081,0.0036665956,0.000060346116,0.00024527614,9.194167e-8,0.0001272655,0.0017229709],"genre_scores_gemma":[0.99663687,0.002607805,0.00020897476,0.000013290544,0.000056275556,0.00003471048,6.1280986e-7,0.0000066269254,0.00043483308],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99890697,0.00020092916,0.00013660475,0.00024874165,0.00018618749,0.0003205519],"domain_scores_gemma":[0.99944204,0.00027320872,0.00013151874,0.000078892605,0.000032499564,0.000041862448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006508237,0.00008828982,0.00017495701,0.00022584673,0.00048280737,0.000038493676,0.0000945311,0.00012739247,0.00003330523],"category_scores_gemma":[0.0002901951,0.00008447304,0.000008499791,0.00045287109,0.00034713696,0.0001370441,0.00007977551,0.00051696406,0.0000028154857],"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":[0.0000043065365,0.000105146195,0.95795244,0.0000023759492,0.000015542468,0.0013551756,0.029188411,1.9898734e-7,0.000029834331,0.0055633397,0.00001712241,0.005766115],"study_design_scores_gemma":[0.0016883606,0.0008669005,0.25535452,0.00001592583,0.000045618755,0.0006809339,0.6992432,0.000070444345,0.00000838846,0.0023864876,0.039336108,0.00030312178],"about_ca_topic_score_codex":0.003744481,"about_ca_topic_score_gemma":0.014108941,"teacher_disagreement_score":0.7025979,"about_ca_system_score_codex":0.000050520724,"about_ca_system_score_gemma":0.00011019816,"threshold_uncertainty_score":0.78731203},"labels":[],"label_agreement":null},{"id":"W2059151369","doi":"10.5539/ies.v7n5p116","title":"Educational Assessment Profile of Teachers in the Sultanate of Oman","year":2014,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Grading (engineering); Psychology; Medical education; Mathematics education; Pedagogy; Medicine; Engineering","score_opus":0.057268269989033824,"score_gpt":0.4822276099051725,"score_spread":0.42495933991613866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059151369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.800977,0.00018527014,0.000029382658,0.017533684,0.0018243858,0.00019635196,0.00000395499,0.0000056245694,0.17924434],"genre_scores_gemma":[0.9953308,0.0001247832,0.0011419146,0.00015747073,0.0002595045,0.00007302238,0.000013672086,0.0000029722298,0.0028958526],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988227,0.00017105901,0.0002701511,0.00010662451,0.0005429072,0.00008657549],"domain_scores_gemma":[0.99834424,0.00050761417,0.00020567638,0.00008931349,0.0008385081,0.0000146596885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010518451,0.000058390047,0.00011289419,0.00012581059,0.00009149867,0.00001817522,0.00034803362,0.000022763687,0.00019262513],"category_scores_gemma":[0.00078704813,0.000045182045,0.00004146829,0.00022334665,0.00021585888,0.00012779518,0.000031666095,0.00006510716,0.0000062877803],"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":[0.000005724151,0.00076692953,0.5095964,0.000014101291,0.00010840441,3.351708e-8,0.07822725,0.000007448903,0.00013058419,0.39189857,0.014342023,0.0049024825],"study_design_scores_gemma":[0.00019785372,0.000024259629,0.78206295,0.000049245795,0.000013057027,1.7754817e-7,0.16791563,0.0000204418,0.000043264507,0.010569682,0.039034016,0.00006940543],"about_ca_topic_score_codex":0.0006979181,"about_ca_topic_score_gemma":0.00047341245,"teacher_disagreement_score":0.3813289,"about_ca_system_score_codex":0.00012588344,"about_ca_system_score_gemma":0.00038884205,"threshold_uncertainty_score":0.210911},"labels":[],"label_agreement":null},{"id":"W2060254942","doi":"10.1007/s10780-008-9041-8","title":"Equitable Classroom Assessment: Promoting Self-Development and Self-Determination","year":2008,"lang":"en","type":"article","venue":"Interchange","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; University of British Columbia; Government of Canada","keywords":"Oppression; Pedagogy; Nature versus nurture; Curriculum; Psychology; Sociology; Political science","score_opus":0.05951707463431537,"score_gpt":0.3543729971544347,"score_spread":0.29485592252011933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060254942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91368645,0.00011082818,0.0002563021,0.0007131825,0.00039176084,0.00044331682,0.0000012421895,0.0003803764,0.08401652],"genre_scores_gemma":[0.98145604,0.00020547668,0.015145746,0.00009934278,0.00027465695,0.00007099695,0.0000057586203,0.000015207759,0.0027267432],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984924,0.00012231026,0.00020988805,0.00026179972,0.0004619816,0.0004516139],"domain_scores_gemma":[0.9995114,0.00008922725,0.000097139135,0.00009824244,0.000093211806,0.00011075435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008056079,0.00013071782,0.00015073916,0.00011024266,0.00084746024,0.000107147025,0.00020953697,0.000089847046,0.00014663451],"category_scores_gemma":[0.00003068084,0.0001310358,0.000033172517,0.00018919323,0.00007494205,0.00043262859,0.0001876181,0.00013485145,0.000054121218],"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":[0.000009080352,0.00073916354,0.18837634,0.00010916496,0.00011506859,0.00007476343,0.76186657,7.398045e-8,0.00046739928,0.0046867244,0.0019787792,0.041576877],"study_design_scores_gemma":[0.002524338,0.00053508964,0.31820217,0.00035705857,0.000115793046,0.00004429516,0.045353755,0.0021561724,0.0016872108,0.0010595481,0.6264442,0.0015203633],"about_ca_topic_score_codex":0.00014550622,"about_ca_topic_score_gemma":0.0004283642,"teacher_disagreement_score":0.7165128,"about_ca_system_score_codex":0.00033279083,"about_ca_system_score_gemma":0.00017175789,"threshold_uncertainty_score":0.6518065},"labels":[],"label_agreement":null},{"id":"W2061239388","doi":"10.3138/cmlr.67.3.377","title":"Working Smarter, Not Working Harder: Revisiting Teacher Feedback in the L2 Writing Classroom","year":2011,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Feeling; Confusion; Psychology; Value (mathematics); Mathematics education; Peer feedback; Pedagogy; Social psychology; Computer science","score_opus":0.05312265572183805,"score_gpt":0.2858817771152325,"score_spread":0.23275912139339444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061239388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68924594,0.08902,0.00007583553,0.0036578753,0.00052751193,0.0015255379,0.000031529566,0.00016889167,0.2157469],"genre_scores_gemma":[0.98599356,0.0076696738,0.00094443193,0.002333809,0.0010287886,0.00008727409,0.00004502597,0.00006961344,0.0018278443],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960514,0.00088423886,0.00063794997,0.00058610016,0.00026312566,0.0015772387],"domain_scores_gemma":[0.99805766,0.00042338256,0.0002568275,0.00057620666,0.00009605333,0.0005898447],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034359007,0.0003837841,0.000610598,0.00029046982,0.00075390626,0.0002768496,0.0011718088,0.0001926438,0.0005252396],"category_scores_gemma":[0.000833842,0.0003434283,0.00023774734,0.0008379528,0.00030610818,0.00025267503,0.000068327,0.00062474073,0.000052521205],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013712108,0.000050817223,0.16956481,0.0008843634,0.00011367982,0.0024443849,0.4733525,0.0000014427063,0.00032990857,0.0053850985,0.0020304495,0.34582883],"study_design_scores_gemma":[0.0010970737,0.000078030826,0.2588188,0.032177366,0.00048306657,0.00024991576,0.27757752,0.00048026518,0.000019574789,0.0011796306,0.42530593,0.002532819],"about_ca_topic_score_codex":0.2634419,"about_ca_topic_score_gemma":0.86648977,"teacher_disagreement_score":0.6030479,"about_ca_system_score_codex":0.0008165094,"about_ca_system_score_gemma":0.00027155265,"threshold_uncertainty_score":0.9999018},"labels":[],"label_agreement":null},{"id":"W2062042622","doi":"10.7202/1024956ar","title":"Assessment for Learning","year":2009,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Psychology","score_opus":0.08600414387348224,"score_gpt":0.46872927147305815,"score_spread":0.3827251275995759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062042622","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23676239,0.0021465763,0.144533,0.35323018,0.014864427,0.003312492,0.00001593292,0.00028065834,0.24485433],"genre_scores_gemma":[0.9275457,0.0004916319,0.011969797,0.00065011065,0.0012408716,0.000074823576,0.0002321832,0.000015587122,0.057779275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9951535,0.003083307,0.00035106376,0.00033205864,0.00074972364,0.00033035284],"domain_scores_gemma":[0.99840176,0.0007304426,0.00027127724,0.00014227617,0.00038084236,0.00007337344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015937952,0.00017125977,0.00019089495,0.00009957992,0.00052891293,0.00018931822,0.00017631613,0.00019581518,0.0008831416],"category_scores_gemma":[0.00066839723,0.0001962868,0.00012905718,0.00041051485,0.00005700118,0.000626601,0.000012092606,0.00024104422,0.00012349135],"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":[0.000019340521,0.0007590725,0.02545346,0.000045529814,0.000085853906,3.2070002e-7,0.31808597,0.0012205921,0.0010230439,0.33168736,0.03863056,0.28298888],"study_design_scores_gemma":[0.0006173564,0.00027229293,0.7964701,0.00005727203,0.00015192678,4.0747466e-7,0.009778194,0.0043037506,0.00003059011,0.016061418,0.17200468,0.0002519871],"about_ca_topic_score_codex":0.00011195431,"about_ca_topic_score_gemma":0.00015146195,"teacher_disagreement_score":0.77101666,"about_ca_system_score_codex":0.0007353537,"about_ca_system_score_gemma":0.0010827987,"threshold_uncertainty_score":0.96697813},"labels":[],"label_agreement":null},{"id":"W2063505651","doi":"10.3200/joeb.81.6.322-326","title":"Using Peer Review to Improve Student Writing in Business Courses","year":2006,"lang":"en","type":"article","venue":"Journal of Education for Business","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Peer feedback; Technical peer review; Peer review; Computer science; Peer-to-peer; Medical education; Psychology; Mathematics education; World Wide Web; Medicine; Political science","score_opus":0.0662221502487459,"score_gpt":0.4615727496667562,"score_spread":0.3953505994180103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063505651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9179365,0.006277052,0.0020070118,0.058531787,0.0069773183,0.0013477023,0.000005811917,0.000015174559,0.0069016125],"genre_scores_gemma":[0.9807703,0.00096487167,0.0075095072,0.0010848951,0.0049788654,0.000041328636,0.0000121763005,0.00002823733,0.004609834],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99824613,0.00005594299,0.0006013245,0.00011814185,0.00075596804,0.00022246217],"domain_scores_gemma":[0.9941015,0.00010086413,0.00047671536,0.00008214326,0.005173782,0.00006496864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020097839,0.00009934387,0.0002664287,0.00022966972,0.00019159088,0.0001637764,0.00027338642,0.00004537252,0.00005282672],"category_scores_gemma":[0.00079878175,0.00009179631,0.00006693453,0.001142783,0.00003608268,0.00046607858,0.000024404364,0.00007613109,0.0000033298925],"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":[0.00017926499,0.0053416896,0.65487885,0.002183691,0.00011256529,0.000013270498,0.011424665,0.0013716498,0.004714921,0.02432265,0.25081,0.044646766],"study_design_scores_gemma":[0.0006803165,0.00002980366,0.806959,0.0028073445,0.00012907799,0.000007804247,0.012232379,0.0000074678987,0.000029527833,0.0006673987,0.1761816,0.00026833758],"about_ca_topic_score_codex":0.00079819665,"about_ca_topic_score_gemma":0.00031923625,"teacher_disagreement_score":0.15208007,"about_ca_system_score_codex":0.0003226585,"about_ca_system_score_gemma":0.0012632469,"threshold_uncertainty_score":0.37433448},"labels":[],"label_agreement":null},{"id":"W2063726363","doi":"10.1007/s10984-014-9170-1","title":"SWDYT: So What Do You Think? Canadian students’ attitudes about peerScholar, an online peer-assessment tool","year":2014,"lang":"en","type":"article","venue":"Learning Environments Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Sociology of Education; Peer review; Peer evaluation; Psychology; Peer assessment; Educational technology; Higher education; Medical education; Pedagogy; Political science; Medicine","score_opus":0.06964661344691153,"score_gpt":0.44059494710350894,"score_spread":0.3709483336565974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063726363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9834394,0.00047252962,0.00005043063,0.00441398,0.00046651025,0.0007782068,0.000008052525,0.00009386628,0.010277031],"genre_scores_gemma":[0.9352812,0.003440014,0.0008583498,0.0003216988,0.000685299,0.000053812328,0.00016064207,0.000063897445,0.059135042],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9887291,0.0025828332,0.00033575456,0.00085942075,0.0058808834,0.001611988],"domain_scores_gemma":[0.9979019,0.0003379964,0.0001103505,0.0006500612,0.00014086047,0.00085879466],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0110799,0.00028978844,0.00032363518,0.0004161344,0.0037381304,0.0038479231,0.0018292371,0.00028429713,0.0027419087],"category_scores_gemma":[0.000658905,0.00029465623,0.00010916569,0.00045952178,0.0007217299,0.001702824,0.0004920851,0.0019623968,0.0008359908],"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":[0.00001790069,0.0006424561,0.9173819,0.000013517683,0.000098656106,0.000023600172,0.015578582,0.00025629665,0.00028554647,0.0026300948,0.0013685426,0.061702896],"study_design_scores_gemma":[0.0004476512,0.00020162965,0.52960783,0.000048638325,0.000012285413,3.6187873e-7,0.017190881,0.00008829757,0.0000044958892,0.00010294213,0.4520535,0.00024151079],"about_ca_topic_score_codex":0.04573514,"about_ca_topic_score_gemma":0.059331704,"teacher_disagreement_score":0.45068493,"about_ca_system_score_codex":0.0014446089,"about_ca_system_score_gemma":0.00049246365,"threshold_uncertainty_score":0.9999505},"labels":[],"label_agreement":null},{"id":"W2067457676","doi":"10.1136/bmj.38993.466678.be","title":"Putting the cart before the horse: testing to improve learning","year":2007,"lang":"en","type":"article","venue":"BMJ","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Worry; Psychology; Context (archaeology); Social psychology; Test (biology); Cognitive psychology; Applied psychology; Mathematics education; History","score_opus":0.03700351524578259,"score_gpt":0.383076420799716,"score_spread":0.3460729055539334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067457676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6213578,0.0000444953,0.0002621766,0.026061578,0.00085265,0.00081860984,4.1570604e-7,0.00012522806,0.35047707],"genre_scores_gemma":[0.98812014,7.639156e-7,0.0010986069,0.00040566968,0.0021265626,0.000016789125,3.6449953e-7,0.000008194603,0.008222932],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99884677,0.00009461209,0.00015277506,0.0001306453,0.000404807,0.00037041205],"domain_scores_gemma":[0.9991968,0.00046101955,0.00008312371,0.0001254371,0.00007652829,0.000057072248],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004233623,0.0000664556,0.00006462713,0.00001998135,0.0014680733,0.00015760402,0.00034172484,0.00003811373,0.00003584192],"category_scores_gemma":[0.0014501818,0.000037739024,0.000040528586,0.00040096414,0.00009050152,0.00007105392,0.00011024563,0.00019623918,0.00008590157],"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":[0.000004493805,0.000015944504,0.61799484,0.0000036168492,0.000024411547,0.000007958409,0.08899954,0.00004554262,0.0011325176,0.008629972,0.008766907,0.27437428],"study_design_scores_gemma":[0.00014317235,0.00008865797,0.6036889,0.000028243998,0.0000238378,0.0000014293836,0.12915646,0.00010716746,0.00007201971,0.0007297288,0.2658379,0.00012248686],"about_ca_topic_score_codex":0.0011269583,"about_ca_topic_score_gemma":0.0030647493,"teacher_disagreement_score":0.36676234,"about_ca_system_score_codex":0.00005123048,"about_ca_system_score_gemma":0.000052873336,"threshold_uncertainty_score":0.99983186},"labels":[],"label_agreement":null},{"id":"W2071179638","doi":"10.1007/s11423-015-9375-8","title":"Developing an adaptive tool to select, plan, and scaffold oral assessment tasks for undergraduate courses","year":2015,"lang":"en","type":"article","venue":"Educational Technology Research and Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Scaffold; Plan (archaeology); Computer science; Educational technology; Instructional design; Computer-Assisted Instruction; Mathematics education; Multimedia; Engineering management; Psychology; Engineering","score_opus":0.22200173344247034,"score_gpt":0.4938688766434834,"score_spread":0.271867143201013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071179638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.884646,0.00026152996,0.002968539,0.10708974,0.0002951614,0.0014773641,0.000008962828,0.000107398,0.0031452838],"genre_scores_gemma":[0.819963,0.00006560192,0.17656735,0.00016552211,0.00013178564,0.00063341146,0.000039837152,0.000011407293,0.002422108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815756,0.000089750676,0.00018475586,0.000385324,0.000626306,0.0005562843],"domain_scores_gemma":[0.9984461,0.0002532538,0.000038783408,0.000100266996,0.0008884712,0.00027313715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019297128,0.000119519456,0.00015242524,0.00044278151,0.0009789914,0.00015880335,0.00026365218,0.00012100593,0.00001483298],"category_scores_gemma":[0.00034405148,0.000115917996,0.000007285999,0.00061130995,0.0003807303,0.00019391644,0.00018105362,0.00016679087,0.000017860726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009924916,0.00022884153,0.11203965,0.000010983347,0.00007669624,0.0000014913068,0.005637478,9.1969855e-7,0.000055682838,0.8385911,0.021504778,0.021753147],"study_design_scores_gemma":[0.0014706097,0.0012396582,0.1707767,0.00008437116,0.000010535921,0.000009264312,0.08452847,0.00003794433,0.0005085275,0.35752395,0.38311076,0.0006992191],"about_ca_topic_score_codex":0.00011335212,"about_ca_topic_score_gemma":0.0011215695,"teacher_disagreement_score":0.48106712,"about_ca_system_score_codex":0.0005230302,"about_ca_system_score_gemma":0.0059291576,"threshold_uncertainty_score":0.9997063},"labels":[],"label_agreement":null},{"id":"W2072017158","doi":"10.1378/chest.128.4_meetingabstracts.344s","title":"PUBLICATION OF RESEARCH UNDERTAKEN IN A CANADIAN TEACHING CENTRE: A REVIEW BY A RESEARCH ETHICS BOARD","year":2005,"lang":"en","type":"review","venue":"CHEST Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen Elizabeth II Health Sciences Centre","funders":"","keywords":"Medicine; Institutional review board; Research ethics; Engineering ethics; Medical education; Ethics committee; Clinical research; Editorial board; Family medicine; Library science; Pathology; Surgery; Public administration; Engineering; Political science","score_opus":0.5068319885516277,"score_gpt":0.6176119719025462,"score_spread":0.11077998335091854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072017158","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018807938,0.9050316,9.791794e-7,0.0340731,0.00013766752,0.00096772786,0.000010372605,0.000008164122,0.05976846],"genre_scores_gemma":[0.00004477981,0.9917067,0.0001586325,0.00013905877,0.00082560483,0.000040306524,0.00003679314,0.000032559226,0.0070155095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9842743,0.009677735,0.0010957862,0.00037588496,0.003101235,0.0014750203],"domain_scores_gemma":[0.99476373,0.0023559597,0.00045144488,0.00033964028,0.0012963779,0.0007928354],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07330133,0.00021140712,0.0009957596,0.0014044497,0.0015210124,0.0005371636,0.0016346424,0.00068655703,0.0006512218],"category_scores_gemma":[0.012509017,0.00018517903,0.0002781846,0.0024703909,0.00050766265,0.00033037204,0.0001247551,0.0100271,0.00012920826],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000015652379,0.00011048639,0.00033596597,0.010415688,0.0000558973,0.000016376358,0.008907726,1.3927035e-8,9.4418695e-8,0.005537713,0.2792625,0.69535595],"study_design_scores_gemma":[0.000092255184,0.000017204304,0.000029026107,0.042695772,0.00004980024,0.0000059852177,0.0025279487,3.7021428e-7,1.6388672e-8,0.0001562987,0.95427364,0.00015168032],"about_ca_topic_score_codex":0.18669292,"about_ca_topic_score_gemma":0.5391492,"teacher_disagreement_score":0.69520426,"about_ca_system_score_codex":0.004185048,"about_ca_system_score_gemma":0.017640341,"threshold_uncertainty_score":0.99977887},"labels":[],"label_agreement":null},{"id":"W2072764341","doi":"10.1080/09695940600563611","title":"Differential effects of global modifications to large‐scale high stakes examination programmes","year":2006,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Scholarship; Accountability; Scale (ratio); Session (web analytics); Test (biology); Empirical examination; Identification (biology); Psychology; Political science; Medical education; Medicine; Geography; Law; Actuarial science; Business; Advertising","score_opus":0.02697556704776101,"score_gpt":0.41688929703418975,"score_spread":0.38991372998642876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072764341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93778855,0.00007474767,0.001558819,0.009446842,0.0004132239,0.0009260873,0.000014085041,0.00003851156,0.049739163],"genre_scores_gemma":[0.99101067,0.00016077931,0.0068469616,0.00018745658,0.00041420077,0.00023712772,0.000045600886,0.0000071800223,0.0010900258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99810547,0.0005899787,0.00032745255,0.00025284855,0.0004319766,0.0002922973],"domain_scores_gemma":[0.9983203,0.0009493798,0.00025614194,0.00017305266,0.0002073121,0.00009383414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069051975,0.00012107696,0.00015424505,0.00014730224,0.00027527352,0.00016482784,0.00017684186,0.000082202125,0.00002681152],"category_scores_gemma":[0.0008336612,0.00012863577,0.00002934244,0.00074675056,0.0000848611,0.0006062538,0.000060173552,0.00010031758,0.0000049923005],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017679837,0.0020340139,0.09850462,0.000045637622,0.00001593483,3.0290556e-7,0.008124891,0.00001722241,0.00023895009,0.88168,0.0002097574,0.009110951],"study_design_scores_gemma":[0.0003659113,0.00006621101,0.93498874,0.000034015,0.00004658782,6.742089e-7,0.022149252,0.000025278314,0.00009678698,0.0034506163,0.038635366,0.00014054397],"about_ca_topic_score_codex":0.015155035,"about_ca_topic_score_gemma":0.0054862374,"teacher_disagreement_score":0.87822944,"about_ca_system_score_codex":0.00040176732,"about_ca_system_score_gemma":0.0010689064,"threshold_uncertainty_score":0.9914031},"labels":[],"label_agreement":null},{"id":"W2073067066","doi":"10.1080/14926150209556514","title":"New drivers for new science education highways","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Argument (complex analysis); Science education; Mathematics education; Focus (optics); Engineering ethics; Sociology; Pedagogy; Engineering; Psychology","score_opus":0.024484998501149383,"score_gpt":0.3155274204900703,"score_spread":0.29104242198892094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073067066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86210006,0.0018456774,0.0046702716,0.06778726,0.006363413,0.0008567405,0.000001847402,0.00006157059,0.056313142],"genre_scores_gemma":[0.9189497,0.000109452296,0.076184236,0.00010557786,0.00031688408,0.000003320976,1.8947352e-7,0.0000051766606,0.0043254066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99901164,0.00000389651,0.00020334036,0.00014428553,0.00031153084,0.00032530053],"domain_scores_gemma":[0.99832237,0.000033770917,0.00022959993,0.00012522744,0.00064283196,0.00064621185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008564465,0.00006749157,0.00010709103,0.0013608922,0.0012419815,0.0002797131,0.00070434465,0.00006509564,0.00008852046],"category_scores_gemma":[0.0008119499,0.00006434831,0.000022251043,0.0018858307,0.0021705145,0.0006459718,0.000015381824,0.00009338632,0.00000724074],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[3.4948798e-7,0.00005217601,0.0045573884,0.000007816292,0.000004112985,2.6210716e-7,0.022180637,3.356859e-7,0.0009549646,0.7875066,0.040952217,0.14378317],"study_design_scores_gemma":[0.0006469083,0.00034152044,0.005628715,0.000355528,0.00010947842,0.00008965555,0.23797618,0.00043419393,0.0017222692,0.4474524,0.30469692,0.000546224],"about_ca_topic_score_codex":0.0015635651,"about_ca_topic_score_gemma":0.0033122797,"teacher_disagreement_score":0.34005415,"about_ca_system_score_codex":0.00037955013,"about_ca_system_score_gemma":0.029131189,"threshold_uncertainty_score":0.9763727},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90695465,0.00006535163,0.015657438,0.0036237554,0.0039407494,0.0032015748,0.000015052856,0.00006650467,0.06647494],"genre_scores_gemma":[0.9796294,0.000072847775,0.017741136,0.00027871892,0.00021321097,0.00051930896,0.00025808156,0.000020248342,0.0012670291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9916078,0.004005195,0.001222615,0.0004851109,0.0023705326,0.00030875296],"domain_scores_gemma":[0.99407315,0.0015106013,0.0014783954,0.00043912823,0.0024059003,0.00009283395],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016967416,0.00021167126,0.00044098712,0.0002566142,0.0002129065,0.00011543775,0.00031251082,0.00017993685,0.001369642],"category_scores_gemma":[0.0014162841,0.00023173084,0.000091279704,0.00062663684,0.00009478239,0.0008686189,0.00006137231,0.00020451559,0.000009775086],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012357136,0.0036144962,0.36284626,0.00010830528,0.00013744397,1.037603e-7,0.0062421435,0.00023991746,0.004234096,0.5362723,0.0008422037,0.08533919],"study_design_scores_gemma":[0.0014260306,0.00046646994,0.95400995,0.00009197699,0.000159235,1.2004703e-7,0.007570669,0.0012131751,0.00030002726,0.032026973,0.00241343,0.00032195263],"about_ca_topic_score_codex":0.017671937,"about_ca_topic_score_gemma":0.0022299218,"teacher_disagreement_score":0.5911637,"about_ca_system_score_codex":0.0010407818,"about_ca_system_score_gemma":0.0028589894,"threshold_uncertainty_score":0.99954325},"labels":[],"label_agreement":null},{"id":"W2078247355","doi":"10.7202/1024798ar","title":"Le savoir-évaluer comme politique éducative","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Humanities; Philosophy; Political science; Economics","score_opus":0.1337467839041888,"score_gpt":0.43082348753831096,"score_spread":0.2970767036341222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078247355","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13900562,0.00073313096,0.009677479,0.3462212,0.009177033,0.0009525029,0.000016479602,0.00013351846,0.49408305],"genre_scores_gemma":[0.9538039,0.0005952865,0.0015810297,0.002215723,0.0018561515,0.00009564774,0.00020850694,0.00004053524,0.03960322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9847698,0.01270444,0.0005209609,0.0004946235,0.0009953209,0.0005148236],"domain_scores_gemma":[0.9967056,0.0017792234,0.00040324352,0.0003800001,0.0005633797,0.00016855022],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.020406194,0.00028791543,0.00032132526,0.00016212938,0.0006530975,0.0002129338,0.00037659382,0.00033020414,0.0014928965],"category_scores_gemma":[0.0018371192,0.00033568766,0.00015885517,0.0006451928,0.0003197516,0.0009445878,0.000061269864,0.00037037663,0.0009909279],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006902902,0.00039766045,0.008397976,0.000026601878,0.000055331097,1.1707053e-7,0.34095815,0.000065203705,0.00007368392,0.6057653,0.034052115,0.010200979],"study_design_scores_gemma":[0.0008057751,0.000114266404,0.49807236,0.000116809475,0.00016691156,0.0000016867348,0.03426966,0.0011480293,0.00014043754,0.06557494,0.3990722,0.000516939],"about_ca_topic_score_codex":0.005074126,"about_ca_topic_score_gemma":0.0036279385,"teacher_disagreement_score":0.8147983,"about_ca_system_score_codex":0.000880929,"about_ca_system_score_gemma":0.0030859692,"threshold_uncertainty_score":0.9999095},"labels":[],"label_agreement":null},{"id":"W2082333579","doi":"10.1017/s0958344000001014","title":"<i>Can computerised testing be authentic?</i>","year":2000,"lang":"en","type":"article","venue":"ReCALL","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Authentic assessment; Computer science; Field (mathematics); Process (computing); Portfolio; Context (archaeology); Computerized adaptive testing; Test (biology); Software testing; Multimedia; Software engineering; Software; Psychology; Pedagogy; Programming language; Psychometrics","score_opus":0.048368330273280864,"score_gpt":0.33047910175775025,"score_spread":0.2821107714844694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082333579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53943825,0.000023391165,0.000027860073,0.0035715797,0.00024072043,0.00014735323,0.000002187759,0.00017218413,0.4563765],"genre_scores_gemma":[0.971581,0.000040930114,0.002902682,0.0008403726,0.00047879555,0.000005848047,0.000003911301,0.000010128687,0.024136335],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908096,0.00008283697,0.0001207491,0.00015213054,0.00028942787,0.0002738719],"domain_scores_gemma":[0.99960774,0.00013094016,0.000030632935,0.00010073843,0.00003367671,0.000096269665],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028343152,0.00007107625,0.00009965428,0.000020832022,0.0003316463,0.00010943328,0.00022977203,0.00005113399,0.0018786368],"category_scores_gemma":[0.000036860998,0.00006991761,0.000042721287,0.0002362477,0.00009109287,0.00007424556,0.000022280232,0.000075143886,0.00018338907],"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":[0.00003916611,0.00046442225,0.1447595,0.000022406486,0.00008745387,0.00004853164,0.07085568,0.000032272812,0.0009943765,0.015760781,0.05056449,0.7163709],"study_design_scores_gemma":[0.0007224476,0.00008430008,0.056645844,0.00004989505,0.000031803178,0.0000013617291,0.0018062722,0.00069947814,0.000042267584,0.0021611576,0.93736124,0.00039391057],"about_ca_topic_score_codex":0.000541691,"about_ca_topic_score_gemma":0.00019304543,"teacher_disagreement_score":0.8867968,"about_ca_system_score_codex":0.000040952335,"about_ca_system_score_gemma":0.00005521619,"threshold_uncertainty_score":0.9990338},"labels":[],"label_agreement":null},{"id":"W2085095437","doi":"10.3109/0142159x.2014.956059","title":"Deliberate practice as a framework for evaluating feedback in residency training","year":2014,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Michael's Hospital; Hamilton General Hospital; Toronto Western Hospital; Centre for Excellence in Mining Innovation; Hamilton Health Sciences; University of Toronto","funders":"","keywords":"Residency training; Medical education; Training (meteorology); MEDLINE; Psychology; Medicine; Continuing education; Political science","score_opus":0.11777648371752797,"score_gpt":0.4901809480145839,"score_spread":0.3724044642970559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085095437","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44533747,0.00028521605,0.018392717,0.07279057,0.0011019792,0.0009542673,4.0778562e-7,0.00018181569,0.46095556],"genre_scores_gemma":[0.9444976,0.00007070598,0.038308483,0.0031752458,0.0021182073,0.00015800958,0.000003972027,0.000033098626,0.011634722],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99667996,0.0008961203,0.00032585525,0.00029492605,0.0013052276,0.00049793546],"domain_scores_gemma":[0.9973312,0.002072634,0.00012002749,0.00014217223,0.00010208413,0.00023188033],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011098157,0.00011370405,0.000215135,0.000054425695,0.00029374563,0.0001023988,0.0003608606,0.00029426703,0.0040734247],"category_scores_gemma":[0.05588114,0.00010447062,0.00006807108,0.00029371888,0.00015960929,0.00025015883,0.0000523922,0.00052094966,0.00013403816],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020270309,0.00040830637,0.036554612,0.000030279736,0.000072584335,0.000019375051,0.2252861,0.00000671903,0.000018470837,0.34355292,0.0068429653,0.38700497],"study_design_scores_gemma":[0.004675342,0.00071252574,0.01634111,0.00093675207,0.00015439093,0.000005775247,0.16556379,0.015408293,0.0000073502842,0.3542386,0.4409545,0.0010015486],"about_ca_topic_score_codex":0.00065874227,"about_ca_topic_score_gemma":0.00059822487,"teacher_disagreement_score":0.4991601,"about_ca_system_score_codex":0.00009835439,"about_ca_system_score_gemma":0.00055294833,"threshold_uncertainty_score":0.99683696},"labels":[],"label_agreement":null},{"id":"W2086620040","doi":"10.1080/01443410.2014.946890","title":"Exploring plausible causes of differential item functioning in the PISA science assessment: language, curriculum or culture","year":2014,"lang":"en","type":"article","venue":"Educational Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Differential item functioning; Curriculum; Psychology; Scientific literacy; Literacy; Mainland China; Cross-cultural studies; Cultural diversity; Scale (ratio); Measurement invariance; Cross-cultural; China; Item response theory; Item analysis; Language proficiency; Variance (accounting); Mathematics education; Psychometrics; Developmental psychology; Pedagogy; Science education; Social psychology; Geography; Sociology; Confirmatory factor analysis","score_opus":0.10948053512327983,"score_gpt":0.46128240685700556,"score_spread":0.35180187173372574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086620040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9371946,0.000022457498,0.00013916535,0.0029820795,0.0017965696,0.00014411153,0.0000012262714,0.000013391179,0.05770643],"genre_scores_gemma":[0.99716437,0.00003899654,0.0005699116,0.00029217522,0.0008782755,0.000072756746,0.0000072077864,0.000004392263,0.0009719134],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99864393,0.00019640173,0.00018570984,0.0002339101,0.00048769912,0.00025237288],"domain_scores_gemma":[0.9993122,0.0003010428,0.000105111445,0.00013953334,0.00009956089,0.000042501688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085247075,0.00007959997,0.00011083456,0.00015359865,0.00041817682,0.0000720477,0.00047555903,0.000036286983,0.00081375963],"category_scores_gemma":[0.00030160148,0.000054223692,0.000032183114,0.000806785,0.00038927293,0.00034389843,0.00003209812,0.00015847913,0.00002074919],"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":[0.000015299545,0.00058011856,0.75139946,0.000009206457,0.000013447876,4.6889906e-7,0.049599912,0.000006891292,0.0018681767,0.19049068,0.004601943,0.0014144069],"study_design_scores_gemma":[0.0002485153,0.000052462372,0.9620193,0.000017913932,0.00000817509,0.0000016130002,0.030220326,0.000016110806,0.000017649423,0.0007042759,0.0066133575,0.0000802785],"about_ca_topic_score_codex":0.00049085985,"about_ca_topic_score_gemma":0.0007887768,"teacher_disagreement_score":0.21061988,"about_ca_system_score_codex":0.00006453037,"about_ca_system_score_gemma":0.0002820369,"threshold_uncertainty_score":0.89100975},"labels":[],"label_agreement":null},{"id":"W2086922103","doi":"10.1002/tesq.105","title":"Motivation and Test Anxiety in Test Performance Across Three Testing Contexts: The <scp>CAEL</scp>,<scp> CET</scp>, and <scp>GEPT</scp>","year":2013,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Mount Saint Vincent University; Carleton University; Queen's University","funders":"U.S. Department of Energy","keywords":"Test anxiety; Test (biology); Psychology; Context (archaeology); Anxiety; Social psychology; Language assessment; Developmental psychology; Mathematics education","score_opus":0.02374035340395477,"score_gpt":0.28072218286008715,"score_spread":0.2569818294561324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086922103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98082393,0.00061981747,0.000029833076,0.00031391825,0.00024083394,0.0014201537,0.000023982218,0.00024048022,0.016287051],"genre_scores_gemma":[0.9957807,0.00016277541,0.0003048151,0.00035065052,0.0005389691,0.00020417721,0.000013611398,0.000050970368,0.002593315],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961533,0.00016826997,0.0006820718,0.00075592194,0.00080851355,0.0014319211],"domain_scores_gemma":[0.9858107,0.012681225,0.00042801615,0.00044559198,0.00035179322,0.00028265623],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017157873,0.0004921216,0.00049219193,0.00012706539,0.0018734455,0.0012052936,0.0007001758,0.00030566342,0.000014971111],"category_scores_gemma":[0.005842639,0.0004015983,0.00008309764,0.0009956824,0.00096693856,0.0016432636,0.00015807727,0.00061230035,0.00015785142],"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":[3.9885836e-7,0.00015388247,0.9138054,0.00003630797,0.000019514822,0.000002485138,0.062368914,0.000001959623,0.0015362529,0.00022037463,0.0034025796,0.018451901],"study_design_scores_gemma":[0.001020209,0.00061389455,0.9120818,0.00012150636,0.000027147904,0.00000653762,0.079905465,0.0014130236,0.00007270964,0.0008289532,0.0038363743,0.00007237762],"about_ca_topic_score_codex":0.0025953664,"about_ca_topic_score_gemma":0.0029371807,"teacher_disagreement_score":0.018379522,"about_ca_system_score_codex":0.00013002886,"about_ca_system_score_gemma":0.00013008276,"threshold_uncertainty_score":0.9998436},"labels":[],"label_agreement":null},{"id":"W2087537317","doi":"10.1111/j.1365-2923.2008.03060.x","title":"Use of retrospective pre/post assessments in faculty development","year":2008,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Intervention (counseling); Context (archaeology); Medical education; Psychology; Retrospective cohort study; Scale (ratio); Perception; Medicine; Applied psychology; Nursing; Surgery","score_opus":0.06656884565472843,"score_gpt":0.4372180617800095,"score_spread":0.37064921612528107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087537317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99129546,0.000012807187,0.00006155963,0.0012406271,0.0004452475,0.0001958252,0.0000010104927,0.000015161633,0.0067322864],"genre_scores_gemma":[0.9943969,0.000060389637,0.0020964926,0.00031440586,0.00009603001,0.000031991476,0.000034860623,0.0000037928464,0.0029650924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984787,0.0000873582,0.0002200914,0.00013960287,0.0009199597,0.0001542791],"domain_scores_gemma":[0.9995573,0.000054655844,0.00007987828,0.000068993184,0.00015502724,0.000084157036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042222644,0.000056753877,0.00011150744,0.000073800016,0.00014104124,0.000013583116,0.00015038534,0.00006930076,0.0006367381],"category_scores_gemma":[0.0009912092,0.000053106043,0.00002138141,0.00029264632,0.00015218252,0.00021992113,0.000029745894,0.00011106548,0.000017330512],"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":[0.000007899097,0.0005648599,0.95209855,0.0000041920407,0.0000082994275,0.0000010276942,0.03220318,2.1241925e-7,0.000016690476,0.0009353647,0.0054240664,0.008735631],"study_design_scores_gemma":[0.00013960418,0.000016258758,0.9700757,0.000035641253,0.0000023840582,3.175158e-7,0.002833236,0.000009964372,0.000036706046,0.000042319316,0.02674883,0.000059033493],"about_ca_topic_score_codex":0.0032784047,"about_ca_topic_score_gemma":0.0023318846,"teacher_disagreement_score":0.029369945,"about_ca_system_score_codex":0.0003189885,"about_ca_system_score_gemma":0.0032326675,"threshold_uncertainty_score":0.69718355},"labels":[],"label_agreement":null},{"id":"W2090290510","doi":"10.3138/cmlr.64.1.009","title":"AFL Research in the L2 Classroom and Evidence of Usefulness: Taking Formative Assessment to the Next Level","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Assessment for learning; Mathematics education; Psychology; Curriculum; Pedagogy; Bridge (graph theory)","score_opus":0.1996400635777524,"score_gpt":0.42204256722631234,"score_spread":0.22240250364855993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090290510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9074288,0.0704557,0.00039776057,0.0076212073,0.00014584357,0.0019524195,0.0000477945,0.000017345232,0.011933149],"genre_scores_gemma":[0.99105656,0.006778504,0.0004962279,0.0010306857,0.00019469626,0.00011710871,0.000007822695,0.000018596093,0.0002997936],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99692583,0.00091649994,0.00043579566,0.00031411403,0.00038314814,0.0010246064],"domain_scores_gemma":[0.9966396,0.002051632,0.00017138543,0.00045264934,0.00024527914,0.00043941903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010688402,0.00018413269,0.00035520896,0.00033052824,0.0006114084,0.00017029332,0.0009912907,0.000088693945,0.000069505324],"category_scores_gemma":[0.0017289725,0.0001266817,0.00008310501,0.0011859365,0.00046119004,0.00035169374,0.00008954675,0.0004309898,0.000009597355],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017166643,0.00003935793,0.022673067,0.0019538815,0.000062448344,0.00058086246,0.76542264,0.000005665282,0.000904787,0.017392999,0.001867381,0.18907973],"study_design_scores_gemma":[0.0003019885,0.00016097262,0.4102632,0.016168877,0.000096711825,0.000053244145,0.51175576,0.00021067711,0.00003400872,0.001227034,0.059148353,0.0005791428],"about_ca_topic_score_codex":0.44034252,"about_ca_topic_score_gemma":0.9675052,"teacher_disagreement_score":0.5271627,"about_ca_system_score_codex":0.0007731929,"about_ca_system_score_gemma":0.00047276783,"threshold_uncertainty_score":0.5633843},"labels":[],"label_agreement":null},{"id":"W2091897869","doi":"10.1515/1548-923x.2487","title":"High Time for a Change: Psychometric Analysis of Multiple-Choice Questions in Nursing","year":2012,"lang":"en","type":"article","venue":"International Journal of Nursing Education Scholarship","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Multiple choice; Test (biology); Psychology; Cognition; Educational measurement; MEDLINE; Nursing; Medical education; Medicine; Curriculum; Pedagogy","score_opus":0.13924153834215616,"score_gpt":0.5151177927329297,"score_spread":0.37587625439077355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091897869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858512,0.00088752917,0.0006141335,0.005356002,0.0055008796,0.00021267954,0.000014421119,0.000008987773,0.0015541184],"genre_scores_gemma":[0.9943713,0.00006326128,0.003625644,0.00010563284,0.0016287913,0.000012980785,0.000023592855,0.0000070356573,0.00016174698],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99835277,0.00020254705,0.0004889344,0.000096816824,0.00065361516,0.0002053028],"domain_scores_gemma":[0.9971325,0.00091931125,0.0005958323,0.000081670376,0.0011454342,0.00012528163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017958037,0.000081872495,0.000221794,0.0024660327,0.00010036155,0.00010649092,0.00041913794,0.00008084884,0.00011566855],"category_scores_gemma":[0.0027010362,0.000085906206,0.00018614595,0.0017476473,0.00009480628,0.0012845538,0.0000057767866,0.00018120125,0.00000559897],"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":[0.000080342725,0.002401672,0.8898499,0.0000024251274,0.00028205573,9.5283255e-8,0.017442884,0.000021409283,0.0004361851,0.0057558883,0.0008238234,0.08290329],"study_design_scores_gemma":[0.000450583,0.00003088594,0.99298257,0.0004047514,0.00031467437,0.000002272869,0.002743735,0.000030462968,0.000039148017,0.0014577345,0.0014568234,0.00008634897],"about_ca_topic_score_codex":0.0001410657,"about_ca_topic_score_gemma":0.0000336259,"teacher_disagreement_score":0.10313265,"about_ca_system_score_codex":0.0008025049,"about_ca_system_score_gemma":0.00025741986,"threshold_uncertainty_score":0.35031533},"labels":[],"label_agreement":null},{"id":"W2094237702","doi":"10.1119/1.4820241","title":"Integrated testlets and the immediate feedback assessment technique","year":2013,"lang":"en","type":"article","venue":"American Journal of Physics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Context (archaeology); Multiple choice; Set (abstract data type); Test (biology); Reliability (semiconductor); Standard deviation; Computer science; Mathematics education; Statistics; Physics; Psychology; Mathematics; Programming language; Significant difference","score_opus":0.012545079734105244,"score_gpt":0.314171238454659,"score_spread":0.30162615872055376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094237702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9450119,0.0001604601,0.009137763,0.016801752,0.0005085437,0.0009350246,0.0000028879638,0.000041658248,0.027399993],"genre_scores_gemma":[0.99365556,0.00031981483,0.0050318474,0.00036098147,0.00043252282,0.00001900647,5.264812e-7,0.000009536945,0.00017017961],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99872625,0.00030010263,0.00025602189,0.00008356306,0.0004260115,0.00020802718],"domain_scores_gemma":[0.9986572,0.00036508855,0.00047918642,0.00009646557,0.00029506252,0.00010695828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080924487,0.000102816906,0.00027996505,0.00003386408,0.00021134871,0.00015059186,0.00031584117,0.000021623586,0.00007936086],"category_scores_gemma":[0.00006388561,0.00006124085,0.00009318788,0.00039110373,0.0013367608,0.00030295274,0.000045615136,0.00029320858,0.0000138037985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001581648,0.0004539207,0.09990366,0.0000118376,0.0005164511,0.000015272097,0.031372804,0.000013567338,0.010370199,0.09438385,0.015501977,0.7472983],"study_design_scores_gemma":[0.009601241,0.0027141802,0.48825344,0.0004086049,0.00061770086,0.000059073707,0.28761277,0.00051741145,0.0018796376,0.14606947,0.0606811,0.0015853754],"about_ca_topic_score_codex":0.0012074291,"about_ca_topic_score_gemma":0.000015342444,"teacher_disagreement_score":0.74571294,"about_ca_system_score_codex":0.00006954724,"about_ca_system_score_gemma":0.00020214166,"threshold_uncertainty_score":0.49253508},"labels":[],"label_agreement":null},{"id":"W2094397051","doi":"10.7202/031735ar","title":"Liens entre anticipation, autoévaluation et le résultat à un examen de rendement scolaire","year":2007,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Anticipation (artificial intelligence); Art; Psychology; Computer science; Artificial intelligence","score_opus":0.31819851517802966,"score_gpt":0.4749758471214142,"score_spread":0.15677733194338456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094397051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8939948,0.0016907031,0.019189334,0.01610925,0.0021978815,0.00051732955,0.0000044862004,0.000077201374,0.066218995],"genre_scores_gemma":[0.9739517,0.00088887924,0.01946859,0.00049503945,0.00061676744,0.000026217058,0.0000212984,0.000013054963,0.0045184707],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9968556,0.0006479028,0.00046634453,0.0004730248,0.0007195323,0.0008376029],"domain_scores_gemma":[0.9986386,0.00033499324,0.00035711224,0.00017685938,0.00027231904,0.00022012317],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.010194475,0.00018771878,0.00017840923,0.0001914348,0.0018935968,0.0003712761,0.0004590551,0.00016573929,0.00039906168],"category_scores_gemma":[0.00047909428,0.00021363354,0.00008694992,0.0017129359,0.0014093627,0.0011063835,0.00006140433,0.00015916028,0.00011724338],"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":[0.000014967074,0.00070565456,0.116489545,0.00010182135,0.00003886056,0.0000053771737,0.5218872,0.0014415409,0.0012242867,0.28079966,0.0021188352,0.07517228],"study_design_scores_gemma":[0.00078644353,0.0004814669,0.6608965,0.00058003503,0.00021584408,0.000025941112,0.24875228,0.022213966,0.0012613905,0.04463447,0.019451253,0.00070043775],"about_ca_topic_score_codex":0.002528061,"about_ca_topic_score_gemma":0.0043369452,"teacher_disagreement_score":0.54440695,"about_ca_system_score_codex":0.0020087555,"about_ca_system_score_gemma":0.0022065328,"threshold_uncertainty_score":0.9994058},"labels":[],"label_agreement":null},{"id":"W2095178943","doi":"10.3200/jexe.76.3.243-258","title":"Subset Testing: Prevalence and Implications for Study Behaviors","year":2008,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University","funders":"","keywords":"Psychology; Set (abstract data type); Clinical psychology; Computer science","score_opus":0.1021623673174721,"score_gpt":0.45205098407033967,"score_spread":0.3498886167528676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095178943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99675626,0.00090745185,0.000012243005,0.0007078387,0.00027486018,0.00044901422,9.4325355e-7,0.0000051356838,0.0008862846],"genre_scores_gemma":[0.998654,0.00010764024,0.00050711597,0.000039629846,0.00023430397,0.000028844905,4.857869e-7,0.0000040387185,0.0004239044],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994733,0.000081316444,0.00016284321,0.000050555394,0.00014890124,0.000083100655],"domain_scores_gemma":[0.9993945,0.00015606622,0.00017499413,0.00006840492,0.00015490004,0.00005114955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048473707,0.00004522265,0.00006239995,0.00003413166,0.00061967893,0.000024062616,0.00017511168,0.0000144867845,0.00001899016],"category_scores_gemma":[0.000085384956,0.00003339635,0.000021688686,0.000110330395,0.00012226001,0.0001885226,0.000015689131,0.000046288602,9.18475e-7],"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":[0.00002918829,0.0013260099,0.8616878,0.0000021274466,0.000013133243,1.01357514e-7,0.12084179,4.2745754e-7,0.012261363,0.00052549626,0.002472043,0.0008405245],"study_design_scores_gemma":[0.00025008796,0.00036880714,0.90115476,0.0000091901275,0.000047704936,0.000017345536,0.096867055,6.430805e-7,0.0006157577,0.00013558837,0.00048166388,0.0000513832],"about_ca_topic_score_codex":0.00014014768,"about_ca_topic_score_gemma":0.0000122878555,"teacher_disagreement_score":0.039466985,"about_ca_system_score_codex":0.00006874365,"about_ca_system_score_gemma":0.00025440234,"threshold_uncertainty_score":0.4766132},"labels":[],"label_agreement":null},{"id":"W2101512152","doi":"10.26522/brocked.v16i1.77","title":"The Conundrum of Classroom Writing Assessment","year":2007,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Rubric; Writing assessment; Grading (engineering); Literacy; Mathematics education; Pedagogy; Standards-based assessment; Authentic assessment; Scale (ratio); Psychology; Professional writing; Reflective writing; Educational assessment; Curriculum; Engineering","score_opus":0.02209598557387845,"score_gpt":0.3989192757158156,"score_spread":0.37682329014193716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101512152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67992854,0.0008808094,0.003794044,0.009866309,0.0059105693,0.0002993446,6.8980825e-7,0.000029330762,0.29929033],"genre_scores_gemma":[0.9882827,0.00026691542,0.0013178998,0.00015906543,0.0014111454,0.0000025146776,5.9395506e-7,0.0000052838636,0.0085539],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871033,0.000114269875,0.0003419264,0.00006641966,0.0005111811,0.0002558797],"domain_scores_gemma":[0.99877876,0.00034520376,0.00029932952,0.00007752039,0.0003494492,0.00014975024],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0015426343,0.000053489883,0.000073507785,0.00005860354,0.0013341443,0.00020118138,0.0002675121,0.000039308765,0.00019875904],"category_scores_gemma":[0.00019724558,0.00004098068,0.000063242216,0.00019437393,0.0000974666,0.0001692629,0.000020412383,0.00019690633,0.000010307868],"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":[0.000030769825,0.00037342927,0.6149274,0.0000078232715,0.00006689084,0.0000011214555,0.010306521,0.000003050479,0.0011589705,0.10843627,0.08568893,0.17899883],"study_design_scores_gemma":[0.00023184571,0.000047517402,0.40767786,0.000039302908,0.00001918777,0.000010542542,0.22124419,0.0000028798424,0.00008794023,0.004283227,0.36625665,0.0000988538],"about_ca_topic_score_codex":0.00004746549,"about_ca_topic_score_gemma":0.00026699988,"teacher_disagreement_score":0.3083541,"about_ca_system_score_codex":0.00016593563,"about_ca_system_score_gemma":0.0014330895,"threshold_uncertainty_score":0.99996597},"labels":[],"label_agreement":null},{"id":"W2101528453","doi":"10.55016/ojs/ajer.v52i3.55156","title":"Initial Use of the Perceptions of Assessment Tasks Inventory (PATI) in English Secondary Schools","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Psychology; Mathematics education; Applied psychology; Pedagogy; Medical education","score_opus":0.10069139079290024,"score_gpt":0.4659886682713977,"score_spread":0.36529727747849744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101528453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9181191,0.00007205828,0.0000013196687,0.0040162452,0.00043733048,0.00018483128,0.00000595464,2.7749178e-7,0.07716294],"genre_scores_gemma":[0.9909627,0.00008577276,0.0002067817,0.00002809688,0.00061844994,0.000010029058,0.000004789592,0.000006372093,0.008077007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99692637,0.0007914284,0.00057441933,0.00009930363,0.0013614355,0.00024702362],"domain_scores_gemma":[0.99263823,0.0054489793,0.00030701526,0.00014736595,0.0013748361,0.00008356856],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018938263,0.00006577501,0.00016936478,0.0003459413,0.0002380195,0.000070837814,0.0005287773,0.00007105395,0.0070796064],"category_scores_gemma":[0.0036377753,0.000052480653,0.00012783021,0.00067904644,0.00045217568,0.00053203775,0.0000690623,0.0006953138,0.000008350846],"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":[0.000021416776,0.000550227,0.9370763,0.000011527081,0.000024576566,1.6416195e-7,0.004972562,0.000029444109,0.00040843055,0.03410911,0.022683457,0.00011284556],"study_design_scores_gemma":[0.00034580028,0.0000646887,0.9792823,0.00010477826,0.000011822277,8.426755e-7,0.010579887,0.000006713,0.000062056446,0.0017828463,0.007704492,0.000053765285],"about_ca_topic_score_codex":0.018553657,"about_ca_topic_score_gemma":0.024532434,"teacher_disagreement_score":0.072843656,"about_ca_system_score_codex":0.00033413238,"about_ca_system_score_gemma":0.0049586864,"threshold_uncertainty_score":0.99382806},"labels":[],"label_agreement":null},{"id":"W2104009022","doi":"10.5539/ijel.v3n1p41","title":"An Overview of Studies on Diagnostic Testing and its Implications for the Development of Diagnostic Speaking Test","year":2013,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diagnostic test; Test (biology); Empirical research; Psychology; Computer science; Medicine; Epistemology","score_opus":0.14929342317387875,"score_gpt":0.44034623423027014,"score_spread":0.29105281105639136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104009022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9646151,0.009868147,0.00055633637,0.0007206123,0.013774115,0.0012156495,0.00006191726,0.00002863718,0.009159455],"genre_scores_gemma":[0.99152356,0.0009548713,0.0046942793,0.000037910642,0.0027572948,0.000014424248,0.0000010796116,0.000006689347,0.00000986036],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99886864,0.000034456378,0.00055908406,0.00007397624,0.0003638796,0.00009998196],"domain_scores_gemma":[0.9326114,0.04162631,0.0009124465,0.00008323061,0.024698468,0.000068133064],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00077191176,0.00007320852,0.00015954072,0.00007661465,0.00016008358,0.00005583064,0.00038694238,0.000026633383,0.000009263547],"category_scores_gemma":[0.4994188,0.000054046348,0.00004123128,0.0000967868,0.00009505935,0.000073323645,0.000047668847,0.00008151405,5.7737304e-7],"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":[0.000027500426,0.0010266622,0.73861647,0.00018331161,0.000990597,0.0000029636778,0.07993235,0.0009781234,0.00027985344,0.14839047,0.0014504405,0.028121289],"study_design_scores_gemma":[0.0010923466,0.00052567455,0.9302127,0.0016676047,0.0002859772,7.904278e-7,0.026744865,0.00032447305,0.0008187317,0.011736952,0.026304943,0.0002849691],"about_ca_topic_score_codex":0.000021562988,"about_ca_topic_score_gemma":0.00007356678,"teacher_disagreement_score":0.4986469,"about_ca_system_score_codex":0.00006279119,"about_ca_system_score_gemma":0.00016558515,"threshold_uncertainty_score":0.5047978},"labels":[],"label_agreement":null},{"id":"W2105451781","doi":"10.1191/0265532204lt287oa","title":"Teacher formative assessment and talk in classroom contexts: assessment as discourse and assessment of discourse","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Formative assessment; Psychology; Pedagogy; Discourse analysis; Applied linguistics; Mathematics education; Assessment for learning; Systemic functional linguistics; Linguistics","score_opus":0.030320027060730614,"score_gpt":0.42869087904920095,"score_spread":0.39837085198847033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105451781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9221969,0.00030183233,0.00057308405,0.0011381911,0.00011379764,0.0005960678,0.000010919142,0.000066355846,0.075002834],"genre_scores_gemma":[0.98106205,0.000060021543,0.018208724,0.000108061984,0.00012889708,0.00005495936,0.000012758697,0.000022235365,0.0003422976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977274,0.00023866889,0.00047453053,0.0003772012,0.0006771764,0.0005050161],"domain_scores_gemma":[0.9987569,0.00046860028,0.00032813483,0.00019963493,0.000080045334,0.00016666968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013958275,0.0002527186,0.00041968605,0.000153969,0.00032671483,0.0001746399,0.0002231136,0.00010743899,0.00010040917],"category_scores_gemma":[0.00022201492,0.00022633294,0.000051283874,0.00037445204,0.00048026603,0.0006579131,0.00020288426,0.00043380132,0.0000016211736],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009927094,0.0005870681,0.8351541,0.00007148167,0.00007616492,0.00010911301,0.09371276,0.000041948082,0.0020737022,0.03619533,0.000028225313,0.031940132],"study_design_scores_gemma":[0.002046388,0.00023670151,0.6623685,0.00033874577,0.00006070044,0.000006857245,0.33211297,0.00051017106,0.000039597577,0.0018874267,0.0000566251,0.00033531393],"about_ca_topic_score_codex":0.0071682576,"about_ca_topic_score_gemma":0.003914115,"teacher_disagreement_score":0.2384002,"about_ca_system_score_codex":0.00041643163,"about_ca_system_score_gemma":0.0005470617,"threshold_uncertainty_score":0.9994431},"labels":[],"label_agreement":null},{"id":"W2106405220","doi":"10.1017/s0261444813000244","title":"Review of doctoral research in language assessment in Canada (2006–2011)","year":2013,"lang":"en","type":"article","venue":"Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Queen's University","funders":"","keywords":"Categorization; Psychology; Vocabulary; Test (biology); Language assessment; Linguistics; Mathematics education","score_opus":0.05336805665149192,"score_gpt":0.4393119507525629,"score_spread":0.385943894101071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106405220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90805763,0.010633614,0.0000033334459,0.0017186815,0.00013685465,0.0005613214,0.000003843032,0.000015835098,0.0788689],"genre_scores_gemma":[0.9970003,0.0007963939,0.0005981267,0.00041675702,0.00011047956,0.00004580155,0.00000970795,0.000009589974,0.0010128515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99720204,0.001012577,0.00032865818,0.00019653644,0.00075745484,0.0005027562],"domain_scores_gemma":[0.99927574,0.00030230632,0.000077450204,0.00022350492,0.00004190207,0.00007907991],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003660227,0.00009185614,0.00025399917,0.00015912537,0.00010877444,0.000040544594,0.00041060222,0.0000409674,0.0018554014],"category_scores_gemma":[0.0001857975,0.00008439891,0.000034077322,0.00031720946,0.000054868404,0.00022173228,0.00010334261,0.0006715976,0.000030080748],"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":[0.000003834693,0.00015634058,0.8451079,0.0008307503,0.000014829773,0.0001182406,0.07906668,0.0000024271799,0.0009965104,0.0038170354,0.013439727,0.0564457],"study_design_scores_gemma":[0.0009079777,0.000051604686,0.52916557,0.0054151365,0.000011270856,0.000001043097,0.45357758,0.00013060166,0.000043981392,0.00018835622,0.0100514125,0.00045546377],"about_ca_topic_score_codex":0.9958262,"about_ca_topic_score_gemma":0.9844229,"teacher_disagreement_score":0.3745109,"about_ca_system_score_codex":0.0009618598,"about_ca_system_score_gemma":0.00095706683,"threshold_uncertainty_score":0.99905705},"labels":[],"label_agreement":null},{"id":"W2107226435","doi":"10.6018/ijes.13.2.185891","title":"Washback in language assessment","year":2013,"lang":"en","type":"article","venue":"International Journal of English Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Quarter (Canadian coin); Mathematics education; Medical education; Pedagogy; Medicine; Geography","score_opus":0.02948544944097654,"score_gpt":0.42166555008289597,"score_spread":0.39218010064191944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107226435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8751909,0.001046688,0.000013288769,0.0029457938,0.005485129,0.00011541094,0.0000012313252,0.000013832497,0.11518769],"genre_scores_gemma":[0.99460846,0.0013087034,0.00072532735,0.00017670542,0.0021670447,0.0000070562883,6.079992e-7,0.0000045697216,0.0010015501],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99860734,0.00008869126,0.0003369192,0.00007228401,0.00074524,0.00014955045],"domain_scores_gemma":[0.9974218,0.00024318152,0.00020564221,0.0000425671,0.0020413012,0.00004551518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066881796,0.000070488975,0.0001719321,0.00016911389,0.00005893762,0.00011052243,0.00041800473,0.000030791572,0.00044115618],"category_scores_gemma":[0.0012048166,0.000057521687,0.000077952565,0.000114883565,0.00010418649,0.0005495373,0.0000803781,0.0001620046,0.000018815563],"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":[0.0000267976,0.000531397,0.5472085,0.00000920187,0.0010244955,0.00014050708,0.35149103,0.000050773,0.0002501019,0.015138272,0.0738667,0.010262248],"study_design_scores_gemma":[0.0017350698,0.00010098753,0.3604697,0.0001859376,0.000023383225,0.0000018584998,0.55363584,0.0000126262175,0.0000638337,0.002617204,0.08093354,0.00022001572],"about_ca_topic_score_codex":0.00021082978,"about_ca_topic_score_gemma":0.0002574878,"teacher_disagreement_score":0.2021448,"about_ca_system_score_codex":0.00027450654,"about_ca_system_score_gemma":0.00008868298,"threshold_uncertainty_score":0.4830351},"labels":[],"label_agreement":null},{"id":"W2107492014","doi":"10.3138/jvme.36.1.100","title":"Getting Started with Curriculum Mapping in a Veterinary Degree Program","year":2009,"lang":"en","type":"review","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; CLARITY; Process (computing); Curriculum mapping; Curriculum development; Medical education; Resource (disambiguation); Engineering management; Computer science; Medicine; Engineering; Pedagogy; Sociology","score_opus":0.18214046913442627,"score_gpt":0.4915750064036833,"score_spread":0.309434537269257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107492014","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01858851,0.975021,0.000020491818,0.0008226816,0.0014954562,0.00096733647,6.711154e-7,0.00003792828,0.0030459473],"genre_scores_gemma":[0.0013637352,0.99271387,0.0037626934,0.00010096864,0.0018214119,0.00006911,0.000015637923,0.000025603975,0.00012695187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99598074,0.00081789657,0.0011080408,0.00024252186,0.001427159,0.00042366417],"domain_scores_gemma":[0.99785453,0.00018880957,0.0011953814,0.00015227511,0.0002213556,0.00038766916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022847166,0.00029060224,0.0010681797,0.0005350707,0.00016998229,0.00012178191,0.0006831569,0.00035662772,0.000228729],"category_scores_gemma":[0.00064411457,0.0002152298,0.0002728642,0.00090717414,0.00016225352,0.0003868012,0.000061170256,0.001012873,0.000009093853],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014614872,0.0010098506,0.00021060219,0.0011258321,0.000053257172,0.0003059754,0.002069797,4.4599087e-8,2.3550882e-7,0.00002795942,0.0007819797,0.99439985],"study_design_scores_gemma":[0.00031474838,0.0016613198,0.0012597255,0.02937269,0.00013239605,0.00064288994,0.003818641,0.0000039313854,3.3126404e-9,0.000023766344,0.96251595,0.00025391515],"about_ca_topic_score_codex":0.00010910028,"about_ca_topic_score_gemma":0.000026763633,"teacher_disagreement_score":0.99414593,"about_ca_system_score_codex":0.0005799668,"about_ca_system_score_gemma":0.0063628787,"threshold_uncertainty_score":0.99927014},"labels":[],"label_agreement":null},{"id":"W2108440479","doi":"10.1080/00131725.2011.577669","title":"Being Fair: Teachers’ Interpretations of Principles for Standards-Based Grading","year":2011,"lang":"en","type":"article","venue":"The Educational Forum","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Grading (engineering); Mathematics education; Psychology; Academic standards; Set (abstract data type); Pedagogy; Higher education; Computer science; Engineering; Political science","score_opus":0.07001771760809876,"score_gpt":0.3902159675238942,"score_spread":0.32019824991579543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108440479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6488358,0.0002188763,0.013390211,0.0422912,0.00228536,0.0014582823,0.00009741794,0.0000817422,0.29134116],"genre_scores_gemma":[0.99344116,0.0000035506996,0.004061677,0.000113396076,0.0001380557,0.000075049575,0.000011081224,0.0000060404964,0.002149976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99929583,0.000048156915,0.00014260755,0.000082572995,0.0002733914,0.00015746747],"domain_scores_gemma":[0.99923885,0.00038233062,0.00008816575,0.000090323374,0.00016858727,0.000031763135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000741084,0.000049890088,0.000065230786,0.000043513166,0.00047254792,0.000022656954,0.0002590526,0.000023391496,0.00033440845],"category_scores_gemma":[0.00030406835,0.00003912626,0.00007374098,0.00011079376,0.00017010639,0.00010554006,0.000018210178,0.000042787688,0.000004059017],"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":[0.000013382863,0.0000697668,0.086114764,0.0000042365236,0.000025608126,9.729662e-9,0.07770976,0.0000031592056,0.000028555489,0.8329976,0.0024322208,0.0006009235],"study_design_scores_gemma":[0.00082451117,0.00017756605,0.21529526,0.00014338699,0.00015522008,2.7524808e-7,0.23669451,0.0003825849,0.0011474403,0.36776605,0.17702837,0.0003848212],"about_ca_topic_score_codex":0.00022499896,"about_ca_topic_score_gemma":0.00039960543,"teacher_disagreement_score":0.46523157,"about_ca_system_score_codex":0.00010168348,"about_ca_system_score_gemma":0.000595751,"threshold_uncertainty_score":0.36615384},"labels":[],"label_agreement":null},{"id":"W2108604890","doi":"10.1177/1478210314566733","title":"International trends in the implementation of assessment for learning: Implications for policy and practice","year":2015,"lang":"en","type":"article","venue":"Policy Futures in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; Queen's University","funders":"","keywords":"Summative assessment; Globe; Policy learning; Political science; Educational assessment; International comparisons; Public administration; Policy analysis; Economic growth; Sociology; Regional science; Formative assessment; Pedagogy; Economics; Psychology","score_opus":0.0812123857192674,"score_gpt":0.5733258516846382,"score_spread":0.49211346596537087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108604890","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19122368,0.00013637485,0.0010373663,0.66458476,0.0011550005,0.0020314022,0.00004445962,0.000026029744,0.13976091],"genre_scores_gemma":[0.9923033,0.000109033936,0.003852905,0.00071565807,0.002099111,0.0005578865,0.0001087765,0.0000053197214,0.00024802695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99925923,0.00013948786,0.0001875149,0.00011322369,0.00016175017,0.0001388027],"domain_scores_gemma":[0.9990494,0.0005036236,0.00016558137,0.0000718162,0.0001815414,0.000028013674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013159827,0.000053248103,0.0000663732,0.00040642,0.00012335641,0.00007013453,0.00018168215,0.000037799793,0.0000048695],"category_scores_gemma":[0.00098151,0.000047461956,0.000025398129,0.00047472774,0.000053716238,0.00027642294,0.000017847819,0.000055232515,1.5643805e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020515523,0.00016536227,0.0448606,0.0000041680073,0.000007795455,5.338644e-9,0.0564802,0.000010844146,0.00003870302,0.7227168,0.0044048964,0.17129008],"study_design_scores_gemma":[0.0005673313,0.00005431566,0.48645523,0.0000034230386,0.0000114641225,5.6118927e-7,0.21326065,0.000019656934,0.0000038100234,0.024832366,0.2747358,0.000055387274],"about_ca_topic_score_codex":0.0137527855,"about_ca_topic_score_gemma":0.005532595,"teacher_disagreement_score":0.80107963,"about_ca_system_score_codex":0.00036235256,"about_ca_system_score_gemma":0.0010349354,"threshold_uncertainty_score":0.9928147},"labels":[],"label_agreement":null},{"id":"W2109561464","doi":"10.1002/nur.20104","title":"Nurse editors' views on the peer review process","year":2005,"lang":"en","type":"article","venue":"Research in Nursing & Health","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Blinding; Peer review; Objectivity (philosophy); Workload; Transparency (behavior); Nursing; Medicine; Medical education; Psychology; Clinical trial; Computer science","score_opus":0.237411425472713,"score_gpt":0.6024689466926302,"score_spread":0.3650575212199172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109561464","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00353993,0.007244591,0.0000023022283,0.77249295,0.0010189425,0.0014523086,0.0000016491247,0.000037588023,0.21420977],"genre_scores_gemma":[0.8810883,0.046267636,0.0003512532,0.014506044,0.030185077,0.00050261675,0.00001892673,0.00006975476,0.027010364],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928827,0.001985113,0.00032119142,0.0002939783,0.0034930822,0.001023924],"domain_scores_gemma":[0.9982917,0.00065002224,0.000080395504,0.0002866249,0.00044609388,0.00024518016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023150673,0.00010098858,0.00022586857,0.00015090464,0.0011865697,0.00012229935,0.00063098426,0.00006616272,0.00032220795],"category_scores_gemma":[0.0010874763,0.00007059568,0.000050248458,0.0012753515,0.00046499076,0.00017321097,0.000015745005,0.00085162173,0.00036388764],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013159555,0.0003054445,0.0008035483,0.00014437857,0.0000020533382,0.0000010447657,0.022146417,0.0000011903402,6.8729685e-7,0.015637716,0.8500429,0.110901475],"study_design_scores_gemma":[0.0001633043,0.0001259002,0.0029025488,0.006358022,0.0000018901849,3.1057826e-7,0.0121389385,0.000022367105,0.0000028742872,0.002003058,0.97618514,0.000095672025],"about_ca_topic_score_codex":0.0005296031,"about_ca_topic_score_gemma":0.0006360632,"teacher_disagreement_score":0.8775484,"about_ca_system_score_codex":0.0012065897,"about_ca_system_score_gemma":0.0012005902,"threshold_uncertainty_score":0.91262543},"labels":[],"label_agreement":null},{"id":"W2112485328","doi":"10.1080/15434303.2015.1010726","title":"Teachers’ Grading Decision Making: Multiple Influencing Factors and Methods","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; English language; Multivariate analysis of variance; Statistics; Engineering; Mathematics","score_opus":0.04392888403571169,"score_gpt":0.44262896175885824,"score_spread":0.39870007772314653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112485328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9721803,0.00025679005,0.014739337,0.00013068932,0.00053192774,0.00031267287,0.000002428814,0.00017936283,0.011666475],"genre_scores_gemma":[0.9285433,0.000006457129,0.07078302,0.00011196886,0.00020828652,0.000016003172,0.000006128478,0.000021156378,0.00030365933],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9976478,0.0005109212,0.00029308398,0.00036638044,0.0006636434,0.0005181679],"domain_scores_gemma":[0.9984816,0.00079078367,0.00014999852,0.00023985007,0.00007483536,0.00026297013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002215324,0.00021650938,0.00028431753,0.0001521183,0.0004279438,0.00041469696,0.00030855194,0.00012700343,0.00009018436],"category_scores_gemma":[0.00025376683,0.00018725546,0.00007811721,0.0003026884,0.000115081486,0.0006288868,0.00006152047,0.00023380225,0.00001224679],"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":[0.000008713797,0.000048825998,0.52652055,0.000004065987,0.000034770295,0.000015180897,0.37655205,0.0000014970733,0.00092576176,0.0014289131,0.00029790003,0.094161764],"study_design_scores_gemma":[0.0009254496,0.00024675333,0.28736317,0.00006240925,0.00005070329,0.0000015854598,0.7060346,0.000321111,0.0000403012,0.0016912703,0.002886578,0.0003760849],"about_ca_topic_score_codex":0.002273368,"about_ca_topic_score_gemma":0.0018290747,"teacher_disagreement_score":0.32948256,"about_ca_system_score_codex":0.0002860255,"about_ca_system_score_gemma":0.00015201364,"threshold_uncertainty_score":0.7636056},"labels":[],"label_agreement":null},{"id":"W2116070328","doi":"10.1177/0265532210376379","title":"Think-aloud protocols in research on essay rating: An empirical study of their veridicality and reactivity","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Think aloud protocol; Psychology; Protocol analysis; Perception; Empirical research; Sample (material); Qualitative research; Rating scale; Social psychology; Nomothetic and idiographic; Cognitive psychology; Applied psychology; Developmental psychology; Epistemology; Cognitive science","score_opus":0.29237641940546794,"score_gpt":0.5510859877479262,"score_spread":0.25870956834245823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116070328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803934,0.0000029005978,7.588783e-7,0.000104596,0.000032703712,0.0041118907,0.0000011829575,0.000054597032,0.015297958],"genre_scores_gemma":[0.99917233,1.4342383e-7,0.00039210333,0.000019696705,0.00017805593,0.00017378917,6.9458065e-7,0.00000772996,0.000055460285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99759936,0.0010201227,0.00019654748,0.0002779067,0.00061586197,0.0002901692],"domain_scores_gemma":[0.9976435,0.0018473857,0.000081942424,0.0002457829,0.00009258107,0.00008882382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064406837,0.000083672,0.0001775743,0.000079156285,0.00033934735,0.00009831074,0.00026024543,0.00008569542,0.00003783099],"category_scores_gemma":[0.0033811054,0.000066861474,0.000013694083,0.0005312032,0.00021824538,0.00016640998,0.00011733514,0.000689057,0.0000017927908],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024346178,0.00091238716,0.6528844,0.0000097482725,0.0000028384216,0.000014729201,0.32728985,3.7396333e-7,0.011734171,0.00017972151,0.000008902451,0.006938535],"study_design_scores_gemma":[0.0005041019,0.0004316432,0.7267394,0.000042664353,0.0000019459414,3.4257332e-7,0.27134317,0.00013408,0.00036479346,0.00032419982,0.000025817146,0.00008783205],"about_ca_topic_score_codex":0.006873621,"about_ca_topic_score_gemma":0.013844201,"teacher_disagreement_score":0.07385501,"about_ca_system_score_codex":0.000039878472,"about_ca_system_score_gemma":0.00014670374,"threshold_uncertainty_score":0.9997397},"labels":[],"label_agreement":null},{"id":"W2118761841","doi":"10.7202/000126ar","title":"Enseignement et apprentissage des sciences: résultats de la troisième enquête internationale","year":2002,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Political science; Sociology; Art","score_opus":0.31913840906530266,"score_gpt":0.443301512179905,"score_spread":0.12416310311460232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118761841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6542894,0.0064225113,0.005842767,0.0038923884,0.0015455175,0.00034545295,0.0000108156155,0.00006548651,0.3275856],"genre_scores_gemma":[0.9357145,0.0049223923,0.027763773,0.00030320894,0.00048861024,0.00005914277,0.0000055138125,0.000013706118,0.030729193],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962925,0.0010675756,0.00038900852,0.0005897785,0.0008391003,0.00082205504],"domain_scores_gemma":[0.9985023,0.00068485446,0.00028204054,0.00016142553,0.0001546783,0.00021469471],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.004945732,0.00022903061,0.00020301221,0.00023964842,0.0030714148,0.0009916781,0.0010022782,0.00015072808,0.0020626031],"category_scores_gemma":[0.0005538758,0.0002439221,0.00013555227,0.0017705369,0.011330747,0.0013853248,0.00011434625,0.0002061287,0.00027603624],"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":[0.000005876572,0.0010916239,0.06300314,0.00018823898,0.000054379383,0.000013978324,0.51167035,0.0016151984,0.0012379407,0.36525398,0.013783847,0.042081468],"study_design_scores_gemma":[0.0016650812,0.0014779308,0.16818944,0.0023970376,0.00034415993,0.00028133462,0.24802509,0.117139205,0.00077876647,0.30733007,0.15031813,0.002053756],"about_ca_topic_score_codex":0.0017984243,"about_ca_topic_score_gemma":0.0014955784,"teacher_disagreement_score":0.2968564,"about_ca_system_score_codex":0.0022581248,"about_ca_system_score_gemma":0.00063688133,"threshold_uncertainty_score":0.99884963},"labels":[],"label_agreement":null},{"id":"W2120301971","doi":"10.3138/jvme.0512-043r","title":"Peer Generation of Multiple-Choice Questions: Student Engagement and Experiences","year":2012,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thematic analysis; Medical education; Psychology; Multiple choice; Student engagement; Resource (disambiguation); Mathematics education; Peer feedback; Process (computing); Significant difference; Qualitative research; Computer science; Medicine; Sociology","score_opus":0.18695066046439923,"score_gpt":0.4902408693508604,"score_spread":0.3032902088864612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120301971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922093,0.001363904,0.0001238502,0.0028793255,0.0026189277,0.00009912876,1.7869388e-7,0.0000040483105,0.0007013162],"genre_scores_gemma":[0.99614525,0.00044982907,0.0009753693,0.0001306547,0.0020123678,0.0000148502995,0.0000014375663,0.000003101116,0.000267142],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980241,0.00030948894,0.00033281592,0.000057528167,0.0011522311,0.00012384995],"domain_scores_gemma":[0.9989053,0.00026605054,0.00025809987,0.000050452698,0.00029824622,0.0002218619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025452015,0.000055359298,0.00011390772,0.00008022575,0.00016373183,0.000030745352,0.00014716796,0.000056381617,0.00042273148],"category_scores_gemma":[0.0031470088,0.000045716282,0.00003545201,0.0000954437,0.00013840973,0.00048511894,0.00003572533,0.00012243069,0.0000015279944],"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":[0.000038494167,0.0020839057,0.48466554,0.000027623786,0.0000596593,0.0000023591083,0.45008126,0.0000010238414,0.0020961598,0.0018407137,0.009916138,0.04918714],"study_design_scores_gemma":[0.0005495158,0.0005912025,0.5621894,0.0001380828,0.000049723676,0.000029491384,0.28973153,0.000038763545,0.000081242164,0.00002606772,0.1464495,0.00012546185],"about_ca_topic_score_codex":0.00010642336,"about_ca_topic_score_gemma":0.000020362904,"teacher_disagreement_score":0.16034974,"about_ca_system_score_codex":0.00007415372,"about_ca_system_score_gemma":0.00043502552,"threshold_uncertainty_score":0.46286133},"labels":[],"label_agreement":null},{"id":"W2122362059","doi":"10.1191/0265532206lt322oa","title":"Aiming for positive washback: a case study of international teaching assistants","year":2005,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Test (biology); Psychology; Language proficiency; Process (computing); Mathematics education; Empirical research; Computer science","score_opus":0.05418180584152639,"score_gpt":0.417552964658704,"score_spread":0.36337115881717763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122362059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9689544,0.00003273317,0.00022978257,0.00013603277,0.00014077856,0.00032807465,0.000006541906,0.000057977148,0.0301137],"genre_scores_gemma":[0.9845323,3.072115e-7,0.014273591,0.000042437918,0.00051425013,0.0000145600125,0.0000025941904,0.0000086275695,0.0006113448],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9991629,0.000079863785,0.00017863174,0.00014301934,0.00025687835,0.00017870813],"domain_scores_gemma":[0.99909174,0.0005825684,0.00012776362,0.000068469,0.000092719354,0.000036742043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071059656,0.000067600544,0.00010429358,0.00005648265,0.00040023978,0.00006266831,0.00016041397,0.000026445796,0.000039045153],"category_scores_gemma":[0.0009049757,0.00006699014,0.000031722353,0.00010132597,0.000034636047,0.00018615926,0.000052138734,0.00009001935,0.0000020921632],"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":[0.000018425306,0.00059266924,0.26160422,0.000008992158,0.00009007394,0.000386716,0.62515134,0.000033143355,0.0023640492,0.00091553485,0.00010748886,0.108727336],"study_design_scores_gemma":[0.0012065955,0.00015765922,0.018088596,0.000074744436,0.00005805515,0.000037658545,0.97810715,0.0016855712,0.00010752756,0.00002420987,0.00026923593,0.00018299378],"about_ca_topic_score_codex":0.0051838662,"about_ca_topic_score_gemma":0.005065913,"teacher_disagreement_score":0.3529558,"about_ca_system_score_codex":0.00008201926,"about_ca_system_score_gemma":0.00003300066,"threshold_uncertainty_score":0.78364897},"labels":[],"label_agreement":null},{"id":"W2122826394","doi":"10.5539/ass.v4n3p78","title":"Student Perceptions and Preferences for Feedback","year":2009,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Macquarie University","keywords":"ROWE; Quality (philosophy); Perception; Psychology; Key (lock); Undergraduate research; Element (criminal law); Medical education; Mathematics education; Computer science; Marketing; Political science; Business; Medicine","score_opus":0.0368983349792774,"score_gpt":0.392057273630894,"score_spread":0.3551589386516166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122826394","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2905108,0.000029180686,0.00014652804,0.006420318,0.0002745372,0.00047129305,0.000004197837,0.00007593474,0.7020672],"genre_scores_gemma":[0.9971195,0.000043342592,0.0007248466,0.000280766,0.00047477186,0.00001853046,0.0000010968399,0.0000028885645,0.0013342837],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984353,0.000047205456,0.0001260277,0.00030169694,0.0006407392,0.00044898296],"domain_scores_gemma":[0.99955267,0.00004552266,0.000057063102,0.00007054716,0.00012752386,0.00014669591],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00093627046,0.00008809939,0.00011820878,0.000069006324,0.0028639939,0.00041377798,0.0004847343,0.000065612076,0.00009596422],"category_scores_gemma":[0.00008331751,0.00008324609,0.000048486618,0.00056209206,0.0011737404,0.0005025998,0.000046081954,0.000077151824,0.000016882354],"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":[0.000011196068,0.00016518569,0.03640093,0.0000030970948,0.000008465351,5.481244e-7,0.17254312,4.018542e-8,0.0014046481,0.3479996,0.0028156834,0.43864748],"study_design_scores_gemma":[0.00018793045,0.00007848674,0.9034857,0.0000041598823,0.000010904624,1.3031327e-7,0.0783758,9.733268e-7,0.000008451728,0.010071369,0.007649754,0.00012632695],"about_ca_topic_score_codex":0.000057199046,"about_ca_topic_score_gemma":0.00018375555,"teacher_disagreement_score":0.8670848,"about_ca_system_score_codex":0.0001079905,"about_ca_system_score_gemma":0.0002045663,"threshold_uncertainty_score":0.9984341},"labels":[],"label_agreement":null},{"id":"W2122914175","doi":"10.5206/cjsotl-rcacea.2012.1.3","title":"Students’ Perceptions of the Effectiveness of Assessment Feedback as a Learning Tool in an Introductory Problem-solving Course","year":2012,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Sudbury; University of New Brunswick","funders":"","keywords":"Formative assessment; Summative assessment; Pedagogy; Mathematics education; Documentation; Psychology; Computer science","score_opus":0.027510770007052206,"score_gpt":0.3742973487248409,"score_spread":0.3467865787177887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122914175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.997271,0.00042233086,0.0000529499,0.0005244048,0.0003627265,0.0004645918,0.0000012948636,0.000005679156,0.00089504314],"genre_scores_gemma":[0.99893326,0.000027848504,0.00028673996,0.00002034308,0.0002471639,0.000010381064,9.750028e-7,0.000015871788,0.00045741926],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9922788,0.00633406,0.0003228862,0.00011648662,0.0005243969,0.00042334752],"domain_scores_gemma":[0.99753684,0.0016166213,0.00037471784,0.00016508416,0.00016302093,0.00014374332],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.03701611,0.00011985129,0.00022894543,0.00011444123,0.004463485,0.00024240842,0.00076259166,0.00007818647,0.000040500167],"category_scores_gemma":[0.0022298447,0.000072056086,0.00012727689,0.00019290087,0.00041017417,0.0005255191,0.000062675266,0.002530028,5.843719e-7],"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":[0.000029788562,0.000046156267,0.9371155,0.000031031886,0.00006678041,2.0245871e-7,0.05243115,0.0016578536,0.0014528183,0.0045488677,0.0000071042286,0.002612758],"study_design_scores_gemma":[0.00037774115,0.00011930446,0.92853016,0.00031229516,0.00009965332,0.00000572251,0.06918192,0.000047962127,0.0000148031695,0.0006595702,0.00056110614,0.000089769135],"about_ca_topic_score_codex":0.010926827,"about_ca_topic_score_gemma":0.018001867,"teacher_disagreement_score":0.03478626,"about_ca_system_score_codex":0.00022776717,"about_ca_system_score_gemma":0.00062099384,"threshold_uncertainty_score":0.99991703},"labels":[],"label_agreement":null},{"id":"W2124002552","doi":"10.1080/0969594x.2014.967168","title":"Instructional Rounds as a professional learning model for systemic implementation of Assessment for Learning","year":2014,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Professional learning community; Professional development; Psychology; Value (mathematics); Pedagogy; Mathematics education; Session (web analytics); Medical education; Medicine; Computer science","score_opus":0.058823989514014775,"score_gpt":0.5102705274787012,"score_spread":0.45144653796468637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124002552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8478959,0.000088223525,0.079190165,0.027419664,0.0011104749,0.0036470625,0.000013310967,0.00008674652,0.040548436],"genre_scores_gemma":[0.94067025,0.00021685647,0.05342697,0.0003297179,0.00051114656,0.00091015943,0.00010890542,0.000017600063,0.0038084134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99767625,0.00071777235,0.00052082975,0.00030212672,0.0004740259,0.0003090028],"domain_scores_gemma":[0.99580187,0.002863585,0.000699274,0.00009800112,0.00044778275,0.00008950686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041866186,0.00014401037,0.00021396183,0.0002625659,0.0007346452,0.00013733192,0.00015406361,0.0001069032,0.000028311784],"category_scores_gemma":[0.0016890072,0.00015494187,0.00006198201,0.0002695712,0.000083227766,0.0009538442,0.000051127678,0.00025935276,8.886276e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007823219,0.0002797426,0.038071327,0.00013742181,0.00004448113,4.5828713e-8,0.0138212405,0.0024591088,0.00033124513,0.9211442,0.00009349727,0.023539452],"study_design_scores_gemma":[0.0040968116,0.0007755842,0.09652027,0.0002966867,0.00023874137,0.000030985804,0.4364676,0.090975374,0.0000478515,0.037741594,0.3321038,0.0007047071],"about_ca_topic_score_codex":0.0015073032,"about_ca_topic_score_gemma":0.00028104422,"teacher_disagreement_score":0.8834026,"about_ca_system_score_codex":0.00052311056,"about_ca_system_score_gemma":0.0047072973,"threshold_uncertainty_score":0.83505434},"labels":[],"label_agreement":null},{"id":"W2124140652","doi":"10.2308/iace-50754","title":"The Power of Giving Feedback: Outcomes from Implementing an Online Peer Assessment System","year":2014,"lang":"en","type":"article","venue":"Issues in Accounting Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Peer feedback; Peer assessment; Peer review; Work (physics); Quality (philosophy); Psychology; Peer-to-peer; Peer evaluation; Computer science; Medical education; Accounting; Mathematics education; Higher education; Political science; World Wide Web; Business","score_opus":0.030205319576389736,"score_gpt":0.4144605637323217,"score_spread":0.384255244155932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124140652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9723991,0.00009819045,0.000062019826,0.0027520794,0.0018593476,0.0002496862,0.000004583717,0.00005764488,0.022517344],"genre_scores_gemma":[0.99443686,0.000017094928,0.0031579696,0.00006884262,0.00068716577,0.000021270798,0.000037154445,0.000014715099,0.0015589189],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997938,0.00028631062,0.00045480178,0.00023132004,0.0007521218,0.00033749195],"domain_scores_gemma":[0.9984586,0.00053023896,0.00036142353,0.00029604495,0.00031531203,0.000038385446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035517723,0.00011837398,0.00020115705,0.0000891114,0.00055177894,0.00034571157,0.00048801984,0.00006577215,0.00012539873],"category_scores_gemma":[0.0004998368,0.00009576573,0.000050352824,0.00024586925,0.0000776048,0.00047279717,0.00009058627,0.00013477904,0.000009148386],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020494115,0.00015504028,0.9516967,0.000012441641,0.00001548166,5.3014308e-8,0.020915389,0.000002657571,0.00012154242,0.014617614,0.00055918144,0.011901874],"study_design_scores_gemma":[0.0001363976,0.00001084933,0.76761645,0.00008394352,0.000012409859,4.2281275e-8,0.1814388,0.00019241183,0.000017027936,0.00042102384,0.049964406,0.00010626049],"about_ca_topic_score_codex":0.014235929,"about_ca_topic_score_gemma":0.008038004,"teacher_disagreement_score":0.18408026,"about_ca_system_score_codex":0.00023124425,"about_ca_system_score_gemma":0.00022063534,"threshold_uncertainty_score":0.99232835},"labels":[],"label_agreement":null},{"id":"W2126217100","doi":"10.5539/ass.v8n16p192","title":"A Case Study on Peer Review and Lecturer Evaluations in an Academic Setting","year":2012,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Kebangsaan Malaysia","keywords":"Peer assessment; Presentation (obstetrics); Strengths and weaknesses; Psychology; Medical education; Mathematics education; Peer evaluation; Peer feedback; Higher education; Social psychology; Medicine","score_opus":0.12513150999267597,"score_gpt":0.509895470399519,"score_spread":0.384763960406843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126217100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8685107,0.00035606846,0.000004381302,0.00981401,0.00025407263,0.0008372863,0.0000014082158,0.000035228022,0.1201868],"genre_scores_gemma":[0.9986586,0.00003172017,0.000047014022,0.00064668845,0.00033808142,0.00003340638,5.4884555e-7,0.0000043420514,0.00023959366],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99760985,0.0003515132,0.0001626204,0.00023845422,0.0011755726,0.00046196405],"domain_scores_gemma":[0.9994477,0.00008064714,0.00006995242,0.000086599444,0.0001517068,0.00016337172],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0077176527,0.00008314225,0.00013030462,0.000088009336,0.0014777338,0.000105632425,0.00027296063,0.000056471887,0.000069119036],"category_scores_gemma":[0.00082937453,0.00007606488,0.000019611216,0.0011405774,0.0004368892,0.0008661665,0.00006565893,0.00024539602,0.000017194752],"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":[0.0000017668855,0.00022700444,0.43979087,0.000008517657,0.000004153444,0.00002128966,0.47487965,3.782362e-8,0.00007758955,0.0061624846,0.0009469333,0.077879705],"study_design_scores_gemma":[0.0001957063,0.000054694574,0.81101775,0.000026537942,0.00004296603,0.000008021294,0.18645842,0.0000014703477,0.0000019565032,0.00022624644,0.0018098874,0.00015631103],"about_ca_topic_score_codex":0.0003195911,"about_ca_topic_score_gemma":0.00068127824,"teacher_disagreement_score":0.3712269,"about_ca_system_score_codex":0.00017234194,"about_ca_system_score_gemma":0.00019543144,"threshold_uncertainty_score":0.9998222},"labels":[],"label_agreement":null},{"id":"W2127042235","doi":"10.37119/ojs2012.v18i2.63","title":"Walking Our Talk About Assessment With Preservice Teachers","year":2013,"lang":"en","type":"article","venue":"in education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bachelor; Curriculum; Mathematics education; Psychology; Medical education; Best practice; Peer assessment; Test (biology); Pedagogy; Medicine; Political science","score_opus":0.01818101799266665,"score_gpt":0.3767391790240238,"score_spread":0.3585581610313572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127042235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8699656,0.00006861646,0.000019407484,0.005062216,0.00048813698,0.00039470135,1.3554074e-7,0.000030869884,0.12397028],"genre_scores_gemma":[0.99236315,0.000033788398,0.001908709,0.00018756864,0.00031565755,0.00019016242,0.0000058373894,0.0000070771603,0.0049880636],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99915165,0.00010213768,0.00010731558,0.00014329606,0.00029904515,0.0001965865],"domain_scores_gemma":[0.9996493,0.000032475196,0.000063377345,0.00011161708,0.00008697447,0.00005624683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032152492,0.00006396014,0.00006704082,0.000065693144,0.00014280587,0.00016798003,0.00019294828,0.000045475063,0.0002737578],"category_scores_gemma":[0.000023788733,0.00005696593,0.000014169771,0.00025812088,0.000021726275,0.0004898564,0.000019307028,0.000103844504,0.00006605538],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023575185,0.00036391613,0.86942106,0.000008950002,0.000012372198,3.6249114e-7,0.07018743,0.000010217674,0.00021266578,0.00318634,0.008849771,0.04774453],"study_design_scores_gemma":[0.0001233973,0.00001392917,0.8241872,0.000035466386,0.000005251825,1.4218999e-7,0.15718417,0.00002088752,0.00000780001,0.0006318708,0.017701624,0.000088238914],"about_ca_topic_score_codex":0.01758487,"about_ca_topic_score_gemma":0.004990266,"teacher_disagreement_score":0.1223975,"about_ca_system_score_codex":0.00024331821,"about_ca_system_score_gemma":0.00043590824,"threshold_uncertainty_score":0.9889571},"labels":[],"label_agreement":null},{"id":"W2127785047","doi":"10.5539/elt.v8n2p109","title":"An Investigation of Saudi English-Major Learners’ Perceptions of Formative Assessment Tasks and Their Learning","year":2015,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Psychology; Scope (computer science); Syllabus; Knowledge survey; Mathematics education; Curriculum; Assessment for learning; Perception; Pedagogy; Medical education; Computer science","score_opus":0.01928969685329423,"score_gpt":0.3350048161152735,"score_spread":0.31571511926197926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127785047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96584,0.00009357641,0.000499668,0.00004289251,0.00020602027,0.00018009939,0.000006483284,0.0001139459,0.03301733],"genre_scores_gemma":[0.9972229,0.000013979769,0.0021058335,0.000021360727,0.00036718053,0.000008506137,0.00004253282,0.000012869181,0.00020486015],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99816746,0.0008366846,0.00025491902,0.00016803665,0.00036841165,0.00020451688],"domain_scores_gemma":[0.99908435,0.00022473688,0.00022764431,0.0001375938,0.00017519378,0.00015049911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025965055,0.00012035932,0.00021978836,0.00011788177,0.00032229465,0.00008052635,0.00019794104,0.00008900714,0.000045265362],"category_scores_gemma":[0.0008721045,0.00010717026,0.000049751892,0.00015315796,0.000232015,0.0008706216,0.0000660844,0.0004414345,0.0000010356127],"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":[0.000004042863,0.000033036893,0.13988496,0.0000116641695,0.000020122032,3.517065e-7,0.8534443,0.00004619091,0.0025137349,0.001771334,0.00004797934,0.0022222956],"study_design_scores_gemma":[0.00041604842,0.00013888908,0.014868857,0.000042498752,0.000021206442,1.2580765e-7,0.9833899,0.00029313998,0.00024529127,0.00013165506,0.0003287773,0.00012362031],"about_ca_topic_score_codex":0.0015054017,"about_ca_topic_score_gemma":0.0003973695,"teacher_disagreement_score":0.1299456,"about_ca_system_score_codex":0.00009219645,"about_ca_system_score_gemma":0.000118477954,"threshold_uncertainty_score":0.4370276},"labels":[],"label_agreement":null},{"id":"W2128292660","doi":"10.3138/jvme.36.4.403","title":"Value and Benefits of Open-Book Examinations as Assessment for Deep Learning in a Post-graduate Animal Health Course","year":2009,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medical education; Psychology; Perception; Value (mathematics); Graduate students; Medicine; Computer science","score_opus":0.11069069268048912,"score_gpt":0.5007805023999512,"score_spread":0.39008980971946206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128292660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9534217,0.0011833292,0.00009599305,0.043103687,0.00031041962,0.0003340981,7.325736e-7,0.000004034294,0.0015459638],"genre_scores_gemma":[0.99417996,0.0015410655,0.0028775244,0.0010294946,0.00022998918,0.000009067823,0.0000049925957,0.000004019984,0.00012387852],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984206,0.00026702866,0.0004343968,0.00009972531,0.0006135036,0.00016475713],"domain_scores_gemma":[0.9988176,0.00021270155,0.0004357618,0.000044450437,0.00027303005,0.00021641838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026367889,0.00006764279,0.00021635565,0.00013008376,0.00018624436,0.00006096744,0.0002542464,0.000057703524,0.00009530746],"category_scores_gemma":[0.00069241476,0.000063239546,0.0000399825,0.0001580593,0.000074967495,0.00045824787,0.00003346343,0.00021578337,4.214377e-7],"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":[0.00045095242,0.0040334887,0.01608371,0.00007549772,0.00006256154,0.000011956082,0.055260517,0.000033509063,0.00049832824,0.041106727,0.0023770332,0.8800057],"study_design_scores_gemma":[0.0011067594,0.0064369934,0.960304,0.0003376197,0.000024944864,0.000045880093,0.02306455,0.00021480431,0.0000041391313,0.00070357305,0.007664706,0.00009201529],"about_ca_topic_score_codex":0.00027859333,"about_ca_topic_score_gemma":0.00007222874,"teacher_disagreement_score":0.9442203,"about_ca_system_score_codex":0.0001606538,"about_ca_system_score_gemma":0.0031410456,"threshold_uncertainty_score":0.557208},"labels":[],"label_agreement":null},{"id":"W2130719536","doi":"","title":"ADMISSION TO TEACHER EDUCATION PROGRAMS: THE PROBLEM AND TWO APPROACHES TO ADDRESSING IT","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Order (exchange); Face (sociological concept); Mathematics education; Computer science; Psychology; Teacher education; Pedagogy; Sociology; Artificial intelligence; Business","score_opus":0.12291906803968555,"score_gpt":0.41341670323016827,"score_spread":0.2904976351904827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130719536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56976205,0.00006727377,0.000007534742,0.37817168,0.00030631106,0.00031327555,0.000002086593,0.000002096897,0.051367663],"genre_scores_gemma":[0.9882591,0.0000056911927,0.0022312554,0.0017485899,0.0021563233,0.000021011689,0.000005736658,0.000005414419,0.005566882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992977,0.00006405196,0.000191791,0.00009897298,0.00017411655,0.00017341155],"domain_scores_gemma":[0.99866444,0.00005874572,0.0001060819,0.000060338178,0.0001450795,0.0009653023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051271473,0.00007286645,0.000071807786,0.00020189607,0.0006069821,0.00043213693,0.000147938,0.000044303095,0.00024199695],"category_scores_gemma":[0.000322828,0.000056953944,0.000021994909,0.00026140406,0.00012567946,0.00019107772,0.000007475157,0.00015848209,0.000006531338],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002326167,0.0001812135,0.14488588,0.000014357381,0.000020098063,5.855862e-7,0.06812371,0.000001662992,0.00018588828,0.6310379,0.032457598,0.123067856],"study_design_scores_gemma":[0.00019913462,0.00018721471,0.20044848,0.000096201155,0.000027891476,0.000054700507,0.025941916,0.0000048290094,0.000022536184,0.011669539,0.7611438,0.00020372531],"about_ca_topic_score_codex":0.00664968,"about_ca_topic_score_gemma":0.13399616,"teacher_disagreement_score":0.7286862,"about_ca_system_score_codex":0.00007579939,"about_ca_system_score_gemma":0.012377802,"threshold_uncertainty_score":0.99996513},"labels":[],"label_agreement":null},{"id":"W2130803473","doi":"10.47678/cjhe.v44i2.183858","title":"When intentions meet reality: Consonance and dissonance in teacher approaches to peer assessment","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Higher Education Research and Development Society of Australasia; Universitetet i Tromsø","keywords":"Consonance and dissonance; Cognitive dissonance; Peer assessment; Psychology; Peer evaluation; Mathematics education; Peer feedback; Teaching method; Pedagogy; Higher education; Social psychology","score_opus":0.10557192750967995,"score_gpt":0.36962017448641865,"score_spread":0.2640482469767387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130803473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6670805,0.001132433,0.0003322525,0.19198559,0.0033847285,0.00039660186,0.0000059979466,0.000009041189,0.13567284],"genre_scores_gemma":[0.96563774,0.000012752114,0.0012939258,0.00047562327,0.0004833091,0.000012252124,0.0000021303254,0.0000061251276,0.032076143],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99899924,0.0001689665,0.00021552407,0.000113511924,0.000289277,0.0002134858],"domain_scores_gemma":[0.99914426,0.000045450997,0.000120205776,0.00008302016,0.00022900445,0.0003780544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011088655,0.00006828314,0.00012821394,0.0001823557,0.000165889,0.00013501347,0.00017317195,0.000050034476,0.00020766728],"category_scores_gemma":[0.00016456711,0.000067116925,0.000028579605,0.00018035145,0.00010468862,0.00023523728,0.000007690484,0.00012346751,0.000003150415],"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":[0.0000029824764,0.00007783839,0.7224402,0.0000066098582,0.000014753151,0.0000011163221,0.018921593,0.0000042974802,0.000011481554,0.10090659,0.1457164,0.011896187],"study_design_scores_gemma":[0.00008297978,0.000016493836,0.5510443,0.000038009595,0.000008235802,6.6129235e-7,0.0028625135,0.0000028625018,5.213082e-7,0.0039137816,0.44197395,0.00005569749],"about_ca_topic_score_codex":0.016352255,"about_ca_topic_score_gemma":0.147287,"teacher_disagreement_score":0.29855722,"about_ca_system_score_codex":0.00037754702,"about_ca_system_score_gemma":0.0016690874,"threshold_uncertainty_score":0.99019796},"labels":[],"label_agreement":null},{"id":"W2131806896","doi":"","title":"The Evolving Culture of Large-Scale Assessments in Canadian Education.","year":2008,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Gatekeeping; Scale (ratio); Accountability; Christian ministry; Educational assessment; Political science; Medical education; Public relations; Geography; Psychology; Pedagogy; Medicine","score_opus":0.019308866200619203,"score_gpt":0.36926440630244384,"score_spread":0.3499555401018246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131806896","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21616392,0.00026447835,0.000008180164,0.0011026968,0.00035420238,0.00016979617,0.0000015544829,0.000010219026,0.78192496],"genre_scores_gemma":[0.96112984,0.00026219038,0.00046150212,0.00016549786,0.00008036283,0.000010202491,0.0000024058234,0.0000026900802,0.037885316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99922115,0.000059292433,0.00011314229,0.0000814739,0.0002438681,0.00028110147],"domain_scores_gemma":[0.9996442,0.000040821073,0.000034364202,0.00008931982,0.00008901755,0.0001022419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000396356,0.00004276058,0.000061140636,0.00004580116,0.0006341307,0.000031852393,0.00023211674,0.00004440181,0.00038110642],"category_scores_gemma":[0.00004944875,0.000030327155,0.00002616812,0.0002915664,0.00008416042,0.00014276497,0.00001648497,0.00006659553,0.00001782744],"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":[0.0000010762952,0.00005755863,0.92003816,0.0000010104184,0.000004970818,5.4074815e-7,0.027757922,4.0187572e-7,0.000010522476,0.011848511,0.03983032,0.00044902525],"study_design_scores_gemma":[0.00011201672,0.00000828206,0.6659837,0.000007947744,0.000002545689,1.94933e-7,0.084784634,0.000030774652,0.000008566895,0.0003078694,0.24868973,0.00006375119],"about_ca_topic_score_codex":0.5154262,"about_ca_topic_score_gemma":0.94323784,"teacher_disagreement_score":0.7449659,"about_ca_system_score_codex":0.00018536189,"about_ca_system_score_gemma":0.0015198488,"threshold_uncertainty_score":0.48780063},"labels":[],"label_agreement":null},{"id":"W2133368865","doi":"10.5539/elt.v6n8p1","title":"Malaysian Primary School ESL Teachers’ Questions during Assessment for Learning","year":2013,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Class (philosophy); Mathematics education; Pedagogy; Teaching method; Kuala lumpur; Qualitative research; Cognition","score_opus":0.008446958120055175,"score_gpt":0.3179391097802562,"score_spread":0.309492151660201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133368865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.861209,0.00018164248,0.001319145,0.00038896073,0.00045125905,0.0007458992,0.0000022801844,0.0005622918,0.13513957],"genre_scores_gemma":[0.9647292,0.000020659949,0.014388806,0.000113171314,0.0019065721,0.0002470208,0.00003769288,0.00003912093,0.018517766],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99795955,0.00044576408,0.00025182913,0.00033248693,0.0004365944,0.0005737748],"domain_scores_gemma":[0.99911046,0.00027194174,0.00012364853,0.00020205788,0.00007184574,0.00022003209],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014268683,0.00018205684,0.00021520798,0.00012523083,0.0015448091,0.00053162774,0.00036322896,0.00012217146,0.00096055097],"category_scores_gemma":[0.0012655505,0.00018749357,0.000134119,0.00013127945,0.000069154026,0.00089034194,0.00010300074,0.00083641073,0.00006636786],"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":[0.0000064973588,0.0001849073,0.23907584,0.000046760313,0.00010211669,0.000009238429,0.72432995,0.00009686216,0.0076556113,0.0055519743,0.00186209,0.021078156],"study_design_scores_gemma":[0.0015799982,0.000088634384,0.16676262,0.00022056243,0.0000827829,0.0000011050694,0.7979211,0.00023206879,0.00007040626,0.00027300738,0.0319907,0.00077697955],"about_ca_topic_score_codex":0.0021275214,"about_ca_topic_score_gemma":0.0001694477,"teacher_disagreement_score":0.1166218,"about_ca_system_score_codex":0.00046803223,"about_ca_system_score_gemma":0.00013124486,"threshold_uncertainty_score":0.99995273},"labels":[],"label_agreement":null},{"id":"W2134230384","doi":"10.26522/brocked.v16i1.29","title":"Assessment - A Powerful Lever for Learning","year":2007,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lever; Assessment for learning; Psychology; Alternative assessment; Pedagogy; Mathematics education; Formative assessment; Engineering","score_opus":0.02843135377807545,"score_gpt":0.41798267199760963,"score_spread":0.3895513182195342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134230384","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54268366,0.0003869951,0.08282899,0.005791646,0.009018123,0.00070912216,9.3186947e-7,0.00009427035,0.35848626],"genre_scores_gemma":[0.9283219,0.00006419828,0.008938755,0.0003931196,0.002789876,0.000007086471,0.0000041207927,0.000011093342,0.059469882],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989265,0.000070567134,0.00021688845,0.000103008184,0.00038080526,0.0003022109],"domain_scores_gemma":[0.9990792,0.00015754497,0.00017125536,0.000048801034,0.00031428997,0.00022886244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010436553,0.00006786375,0.000080818456,0.00011302301,0.00097592187,0.00023373269,0.000170667,0.000054180113,0.0008694122],"category_scores_gemma":[0.00027346704,0.000066637665,0.00008181987,0.00016552163,0.000031914955,0.0002716595,0.00001293875,0.0002182924,0.000036020774],"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":[0.00005786066,0.00077848346,0.5473995,0.0000152257435,0.00009414796,0.0000019463414,0.026504906,0.000026704327,0.0017935148,0.036984958,0.2740748,0.112267904],"study_design_scores_gemma":[0.00026707482,0.00005229373,0.2327181,0.000016163245,0.000015850039,0.0000067584137,0.051754557,0.0000036294023,0.000019314624,0.0016330775,0.71341145,0.00010175928],"about_ca_topic_score_codex":0.00003529794,"about_ca_topic_score_gemma":0.00007705646,"teacher_disagreement_score":0.43933663,"about_ca_system_score_codex":0.00027080745,"about_ca_system_score_gemma":0.0013959956,"threshold_uncertainty_score":0.95194536},"labels":[],"label_agreement":null},{"id":"W2135920839","doi":"10.18733/c3qc71","title":"Teaching For Understanding: Spotlighting the Blythe and Associates Pedagogical Model","year":2015,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Field (mathematics); Order (exchange); Computer science; Mathematics education; Deep learning; Engineering ethics; Management science; Pedagogy; Psychology; Artificial intelligence; Engineering","score_opus":0.8727235814564107,"score_gpt":0.5610861116109416,"score_spread":0.31163746984546914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135920839","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95443654,0.00074831233,0.0019092768,0.015265118,0.00031501183,0.0004156367,0.0000055839255,0.0001125637,0.026791934],"genre_scores_gemma":[0.9876508,0.00012593916,0.0005171016,0.00045657848,0.001058229,0.000020727346,0.0000066710995,0.000007731384,0.01015623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99867576,0.00016537114,0.00017637076,0.00026190683,0.00035320016,0.00036738324],"domain_scores_gemma":[0.99913305,0.0004318346,0.000077719786,0.00006324636,0.000074179385,0.0002199647],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0013475762,0.00015116845,0.0001944363,0.000016710263,0.0015168511,0.00038961953,0.00018256629,0.00014202131,0.000014313457],"category_scores_gemma":[0.00038599942,0.00007826167,0.00007291831,0.000065647255,0.00059144787,0.0002946909,0.00012350413,0.00023788166,0.0000037493971],"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":[0.00006391915,0.000060651106,0.011829558,0.000011996395,0.000043202275,0.0000021369335,0.40119928,0.000015392572,0.00012497767,0.5763801,0.008608234,0.0016605573],"study_design_scores_gemma":[0.0009845106,0.00015078144,0.001859875,0.000025464893,0.000085281914,0.0000044322933,0.8183771,0.0032494494,0.000004102555,0.13019243,0.044695657,0.00037092846],"about_ca_topic_score_codex":0.00011694527,"about_ca_topic_score_gemma":0.00008204876,"teacher_disagreement_score":0.44618765,"about_ca_system_score_codex":0.000091614835,"about_ca_system_score_gemma":0.000045984078,"threshold_uncertainty_score":0.99978304},"labels":[],"label_agreement":null},{"id":"W2136543334","doi":"10.3138/cmlr.64.1.135","title":"A New Washback Model of Students’ Learning","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":119,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Mathematics education; Context (archaeology); Psychology; English as a foreign language; Pedagogy; Geography","score_opus":0.024228455206167343,"score_gpt":0.31234216665668124,"score_spread":0.2881137114505139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136543334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89776695,0.048770856,0.0025090617,0.00059919304,0.0002169311,0.0008377918,0.00006395344,0.00011637135,0.0491189],"genre_scores_gemma":[0.96708274,0.0118640205,0.0034010762,0.000554314,0.00038687355,0.000012723322,0.0000613335,0.00006346067,0.01657345],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975261,0.00017677377,0.0004871894,0.0003823344,0.00029876613,0.0011288394],"domain_scores_gemma":[0.9976276,0.00022839119,0.0002111188,0.0003556921,0.00018441956,0.0013927746],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019240731,0.0002676478,0.0005554741,0.00028581015,0.00033495596,0.00007678496,0.0008395838,0.00015512388,0.00039969687],"category_scores_gemma":[0.00076923065,0.00027796518,0.00020635307,0.00054092106,0.00023072431,0.00020649093,0.000062272025,0.00029923735,0.000033649918],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004648559,0.00012915634,0.13299423,0.003524052,0.00049185444,0.0015382859,0.5646811,0.00026293224,0.0133543,0.019704953,0.009782875,0.25348976],"study_design_scores_gemma":[0.00441402,0.00056869525,0.17535155,0.028715748,0.0019022743,0.0002137536,0.25284863,0.005519224,0.00068290415,0.0066463933,0.5167316,0.006405171],"about_ca_topic_score_codex":0.38929924,"about_ca_topic_score_gemma":0.8877521,"teacher_disagreement_score":0.50694877,"about_ca_system_score_codex":0.0006909453,"about_ca_system_score_gemma":0.0006335968,"threshold_uncertainty_score":0.9999673},"labels":[],"label_agreement":null},{"id":"W2138588257","doi":"10.18806/tesl.v27i2.1052","title":"A Peer Review Training Workshop: Coaching Students to Give and Evaluate Peer Feedback","year":2010,"lang":"en","type":"review","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Coaching; Psychology; Peer review; Training (meteorology); Consciousness; Pedagogy; Medical education; Mathematics education; Political science","score_opus":0.14475727150004924,"score_gpt":0.46145459967225444,"score_spread":0.3166973281722052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138588257","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021767024,0.9795824,0.000007306663,0.010637229,0.002218802,0.0011692708,0.00003091556,0.000024090888,0.0063081863],"genre_scores_gemma":[0.00000892187,0.96206915,0.0003294332,0.010956689,0.0017727809,0.00004489524,0.00002106119,0.00006215407,0.024734903],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98975164,0.00083849306,0.0009844606,0.0004957632,0.0069808206,0.00094881584],"domain_scores_gemma":[0.99599355,0.0006317591,0.00076564547,0.00028534443,0.0012815327,0.0010421803],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011592456,0.0005523813,0.0018755799,0.00019057169,0.0014121861,0.0010317335,0.0014978349,0.00029652438,0.0066941166],"category_scores_gemma":[0.003929837,0.0004508086,0.00034220313,0.0006152594,0.00011816214,0.00024073487,0.00027880273,0.0024346749,0.000033044023],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002219545,0.000016320595,0.000031950145,0.0009947136,0.00018853908,0.00008158017,0.0037151051,1.3805044e-7,3.627215e-8,0.00005637639,0.3256215,0.66929156],"study_design_scores_gemma":[0.00020756798,0.000021487192,0.000084132356,0.021275064,0.0010118785,0.000092805414,0.0029875466,3.3124783e-7,3.7346726e-9,0.000029415105,0.973776,0.0005137943],"about_ca_topic_score_codex":0.031919975,"about_ca_topic_score_gemma":0.27924743,"teacher_disagreement_score":0.66877776,"about_ca_system_score_codex":0.0010470733,"about_ca_system_score_gemma":0.0073561845,"threshold_uncertainty_score":0.9998878},"labels":[],"label_agreement":null},{"id":"W2138788260","doi":"","title":"A ROLE FOR RESEARCH IN INITIAL TEACHER EDUCATION ADMISSIONS: A CASE STUDY FROM ONE CANADIAN UNIVERSITY","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Confidentiality; Identity (music); Teacher education; Pedagogy; Service (business); Psychology; Medical education; Sociology; Political science; Medicine; Business","score_opus":0.19502835079680142,"score_gpt":0.4716467493462753,"score_spread":0.2766183985494739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138788260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9471845,0.00009253969,9.383887e-7,0.015922852,0.00018943971,0.00035526403,0.000035250996,0.0000010296994,0.036218207],"genre_scores_gemma":[0.9966222,0.000011235831,0.00031483432,0.00015904492,0.000963235,0.0000070055485,0.000012701138,0.000004553953,0.0019051579],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9990654,0.0002455161,0.00018817319,0.0001065808,0.00015466951,0.00023965763],"domain_scores_gemma":[0.99800754,0.00017663902,0.00008177633,0.000060256356,0.0003723982,0.0013014022],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00072727684,0.000056980887,0.00008697502,0.00088074617,0.0006433392,0.00008583436,0.00014819072,0.000067746834,0.0011042615],"category_scores_gemma":[0.0005495012,0.000066414184,0.000026181717,0.00039652418,0.0001064074,0.0002479763,0.0000041262965,0.00016301704,0.000004181245],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001164313,0.0012455044,0.56790334,0.0000069981766,0.000059621838,0.00016660253,0.25354776,2.3333465e-7,0.00000962001,0.15869987,0.0069558993,0.011288136],"study_design_scores_gemma":[0.00059992436,0.00034632813,0.4657392,0.000044582845,0.00002768525,0.00006609246,0.4672199,0.0000025358215,0.0000031867028,0.015101903,0.050709236,0.00013943182],"about_ca_topic_score_codex":0.94946384,"about_ca_topic_score_gemma":0.993773,"teacher_disagreement_score":0.21367215,"about_ca_system_score_codex":0.00069685327,"about_ca_system_score_gemma":0.085645534,"threshold_uncertainty_score":0.99980885},"labels":[],"label_agreement":null},{"id":"W2139024900","doi":"10.5430/ijhe.v2n4p143","title":"“What do I do here?”: Higher Order Learning Effects of Enhancing Task Instructions","year":2013,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Griffith University","keywords":"Psychological intervention; Task (project management); Comprehension; Explication; Psychology; Order (exchange); Reading comprehension; Computer science; Mathematics education; Reading (process); Engineering","score_opus":0.00911962686682635,"score_gpt":0.35042354684175814,"score_spread":0.3413039199749318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139024900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9554916,0.0016243617,0.000083756015,0.004944046,0.027195578,0.0001615302,2.7940493e-7,0.000014825421,0.010484],"genre_scores_gemma":[0.98250777,0.0006284254,0.0008488585,0.00014432173,0.0023269004,0.000012228282,0.0000028672441,0.000010840528,0.013517767],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984225,0.00014148814,0.00040401868,0.00010861519,0.0007824032,0.00014099786],"domain_scores_gemma":[0.99762195,0.00020307876,0.000565386,0.000068086745,0.0014567988,0.00008470994],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026864273,0.00009354275,0.00014757545,0.0002366709,0.00013282802,0.0003672816,0.00037647248,0.00007405866,0.0025640656],"category_scores_gemma":[0.00010739312,0.00008543805,0.00009563641,0.00023880096,0.0000920778,0.0015461255,0.00003530879,0.00021731954,0.00006506868],"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":[0.000118234806,0.0023459054,0.43406746,0.00011160129,0.0015735197,0.000013561748,0.072472766,0.00027143426,0.050495457,0.14686099,0.038737644,0.25293142],"study_design_scores_gemma":[0.0011562556,0.00017821681,0.68255484,0.000914113,0.00011245468,0.000013541604,0.02792354,0.0000035761,0.0013982248,0.012368355,0.273052,0.00032484738],"about_ca_topic_score_codex":0.0003500709,"about_ca_topic_score_gemma":0.000014692802,"teacher_disagreement_score":0.25260657,"about_ca_system_score_codex":0.00023078929,"about_ca_system_score_gemma":0.00035467252,"threshold_uncertainty_score":0.9983477},"labels":[],"label_agreement":null},{"id":"W2140654065","doi":"","title":"Formative Assessment and the Contemporary Classroom: Synergies and Tensions between Research and Practice.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Formative assessment; Variety (cybernetics); Professional development; Pedagogy; Mathematics education; Psychology; Faculty development; Teacher education; Medical education; Sociology; Medicine; Computer science","score_opus":0.25949078778983575,"score_gpt":0.4333496664294458,"score_spread":0.17385887863961003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140654065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93153274,0.0013086357,0.00002866259,0.033295915,0.00081191136,0.00031549294,0.0000053145195,0.0000029549526,0.0326984],"genre_scores_gemma":[0.9973254,0.00040773355,0.0008745736,0.00028271548,0.00036281598,0.000018539477,0.000004804387,0.0000076450815,0.0007157449],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.998451,0.0006847926,0.00028506859,0.00012180761,0.00012048794,0.00033682014],"domain_scores_gemma":[0.9966347,0.0011287301,0.0002877412,0.00011396337,0.001024376,0.0008104439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052309297,0.00008039937,0.00016172537,0.0003663796,0.0009871922,0.00020118713,0.00016854996,0.00007290884,0.000032098982],"category_scores_gemma":[0.0019935851,0.000067661116,0.000021273532,0.0002939814,0.0008056787,0.0007339992,0.000015652256,0.00030834824,9.212743e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025150539,0.00003296807,0.12842892,0.000021773458,0.000071388924,0.000005324046,0.6919468,1.1404107e-7,0.0000079647,0.16210905,0.012125033,0.0052255373],"study_design_scores_gemma":[0.00028754663,0.000090535366,0.35822266,0.000085875465,0.000049894956,0.000057334168,0.58918124,0.000003916492,0.0000017535903,0.015670871,0.0362656,0.00008274681],"about_ca_topic_score_codex":0.12883464,"about_ca_topic_score_gemma":0.35925284,"teacher_disagreement_score":0.2304182,"about_ca_system_score_codex":0.00095760095,"about_ca_system_score_gemma":0.008864352,"threshold_uncertainty_score":0.99675447},"labels":[],"label_agreement":null},{"id":"W2142362115","doi":"10.5539/elt.v4n1p214","title":"The Relationship between Peer Assessment and the Cognition Hypothesis","year":2011,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Task (project management); Peer assessment; Cognition; Consistency (knowledge bases); Peer feedback; Set (abstract data type); Cognitive psychology; Scale (ratio); Cognitive complexity; Rating scale; Mathematics education; Developmental psychology; Computer science; Artificial intelligence","score_opus":0.07356505215943827,"score_gpt":0.35661802034715906,"score_spread":0.2830529681877208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142362115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6669884,0.00014278294,0.00013422575,0.0009098249,0.00020345605,0.00022974865,0.000002188104,0.000087197484,0.33130223],"genre_scores_gemma":[0.9951986,0.000014435709,0.00077156356,0.00007282528,0.00073091016,0.000026634905,0.0000044319645,0.0000095060805,0.0031710686],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99822295,0.0008759882,0.00014171291,0.00012602995,0.00042763518,0.00020569057],"domain_scores_gemma":[0.9953163,0.0043688565,0.00008097003,0.0001453994,0.000042155792,0.00004628831],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005018913,0.00007879085,0.00009301476,0.000026546873,0.0020925323,0.00024976712,0.00024512262,0.00005364074,0.00006767117],"category_scores_gemma":[0.0035672118,0.00004589512,0.000049222977,0.00007956172,0.00029464756,0.00022003928,0.000059009493,0.0003864185,0.000009857589],"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":[0.000007385757,0.000010516456,0.33016708,0.000001357565,0.000024761297,9.790441e-7,0.54243773,2.5390197e-8,0.0000015087663,0.11878434,0.0002918324,0.008272481],"study_design_scores_gemma":[0.0005347495,0.000009682047,0.55709344,0.000012552457,0.00007568821,1.4224439e-7,0.43167037,0.000003483851,0.000003959105,0.0068431427,0.0036527517,0.00010002724],"about_ca_topic_score_codex":0.00079314876,"about_ca_topic_score_gemma":0.00040350767,"teacher_disagreement_score":0.32821026,"about_ca_system_score_codex":0.000041813902,"about_ca_system_score_gemma":0.00003144747,"threshold_uncertainty_score":0.9992066},"labels":[],"label_agreement":null},{"id":"W2142506285","doi":"10.1017/s0267190509090060","title":"FORMATIVE ASSESSMENT IN LANGUAGE EDUCATION POLICIES: EMERGING LESSONS FROM WALES AND SCOTLAND","year":2009,"lang":"en","type":"article","venue":"Annual Review of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Devolution (biology); Welsh; Political science; Autonomy; Ideology; Politics; Public administration; Policy learning; State (computer science); Pedagogy; Sociology; Geography; Law","score_opus":0.015926529424384373,"score_gpt":0.41923635554121186,"score_spread":0.4033098261168275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142506285","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11173256,0.03129442,0.00008866279,0.0042110113,0.0005989101,0.0011633976,0.000101339734,0.0000545124,0.8507552],"genre_scores_gemma":[0.9597191,0.036363833,0.002300492,0.0011067864,0.00038103168,0.000011176065,0.000045980414,0.000004931869,0.000066642184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990672,0.000041624364,0.00031009127,0.00013405985,0.00027517628,0.00017183233],"domain_scores_gemma":[0.9993932,0.00013580358,0.00017752328,0.00010647881,0.00013027873,0.00005668869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047031423,0.000098772274,0.00027267612,0.000060757542,0.00010457766,0.000026113483,0.0001450566,0.00004367357,0.00002819863],"category_scores_gemma":[0.00040670246,0.00009176284,0.000030578365,0.00021415451,0.00007670909,0.000033441418,0.000031364554,0.00011482449,0.0000035094258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011652945,0.0003083971,0.0036058642,0.0005934933,0.000028786353,0.0000016616192,0.16699909,0.0000013186609,0.000068151916,0.67766523,0.0052099237,0.14550644],"study_design_scores_gemma":[0.00079458836,0.00013021244,0.071488015,0.008037387,0.00021022906,2.1254942e-7,0.41661897,0.000032735526,0.00010160142,0.023221964,0.47869617,0.00066791725],"about_ca_topic_score_codex":0.001072212,"about_ca_topic_score_gemma":0.00032745325,"teacher_disagreement_score":0.8506885,"about_ca_system_score_codex":0.000055406006,"about_ca_system_score_gemma":0.00022424824,"threshold_uncertainty_score":0.37419802},"labels":[],"label_agreement":null},{"id":"W2143532033","doi":"10.5539/elt.v4n1p156","title":"On the Interaction of Test Washback and Teacher Assessment Literacy: The Case of Iranian EFL Secondary School Teachers","year":2011,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Psychology; Literacy; Context (archaeology); Mathematics education; Pedagogy; Test (biology); Formative assessment","score_opus":0.01969515509746019,"score_gpt":0.33426519506656943,"score_spread":0.31457003996910926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143532033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80834496,0.000106429754,0.000017717537,0.00017189159,0.00022079788,0.00026511797,0.0000062094605,0.000039448176,0.19082743],"genre_scores_gemma":[0.99795616,0.0000112935795,0.0004489401,0.00012228683,0.00028896256,0.000014385212,0.0000030678311,0.000016133947,0.0011387812],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9983416,0.0007132276,0.0002777196,0.00019609639,0.0002574359,0.00021391065],"domain_scores_gemma":[0.9983004,0.0010516758,0.00022767753,0.00030123844,0.000049549333,0.00006951286],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025439747,0.00014150408,0.00017639961,0.00006950631,0.00046218044,0.00010374242,0.0003198319,0.00007418492,0.001236781],"category_scores_gemma":[0.0013931503,0.00008678815,0.000082540246,0.00012031453,0.00021630005,0.00039149335,0.00009161515,0.00085899414,0.0000045705565],"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":[0.000015579608,0.00021000499,0.036864016,0.0000141062155,0.000061875355,0.00004063405,0.92529756,6.2374534e-7,0.0004477192,0.007120398,0.000659492,0.02926798],"study_design_scores_gemma":[0.0004438567,0.00014022959,0.023248665,0.00010929706,0.00006782335,0.000009167275,0.9737285,0.00007142615,0.00023009918,0.00025509388,0.0015250244,0.00017085149],"about_ca_topic_score_codex":0.0047934316,"about_ca_topic_score_gemma":0.00074700563,"teacher_disagreement_score":0.18968865,"about_ca_system_score_codex":0.00008009342,"about_ca_system_score_gemma":0.00006515282,"threshold_uncertainty_score":0.9996762},"labels":[],"label_agreement":null},{"id":"W2144199041","doi":"10.1080/17425960902830385","title":"Responding to the Challenges Posed by Summative Teacher Candidate Evaluation: A collaborative self-study of practicum supervision by faculty","year":2009,"lang":"en","type":"article","venue":"Studying Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Practicum; Formative assessment; Summative assessment; Medical education; Psychology; Pedagogy; Faculty development; Professional development; Medicine","score_opus":0.06576449714630696,"score_gpt":0.4328585198866927,"score_spread":0.3670940227403858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144199041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95483047,0.0009970278,0.000009011493,0.01873858,0.00034825763,0.0030598838,0.000008142193,0.00007048595,0.021938162],"genre_scores_gemma":[0.9963069,0.00009197195,0.00017933176,0.00011137776,0.00025325004,0.00026559774,0.000040322517,0.000013259022,0.0027380222],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9956563,0.002035915,0.0003458787,0.00041842085,0.0012501015,0.0002933778],"domain_scores_gemma":[0.99846023,0.00016252622,0.0003005109,0.00030171513,0.0006757572,0.000099237826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004263103,0.00019553328,0.00023481963,0.00018732088,0.00090057426,0.00015883501,0.0004129694,0.00008241709,0.00013597954],"category_scores_gemma":[0.0006749272,0.00015323576,0.000037670216,0.0013077873,0.00004159504,0.0004551777,0.000053189044,0.0002188772,0.000021888289],"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":[0.00007234115,0.0040565385,0.027045233,0.0000031752083,0.00009660912,1.1405518e-7,0.8918498,0.000002677178,0.000561475,0.0003555355,0.06119725,0.014759261],"study_design_scores_gemma":[0.0007736693,0.0005977736,0.076892495,0.000033347456,0.00016424683,1.06688454e-7,0.8922012,0.00003970076,0.00006899075,0.000112947724,0.028895209,0.00022035379],"about_ca_topic_score_codex":0.0012578084,"about_ca_topic_score_gemma":0.0010092417,"teacher_disagreement_score":0.04984726,"about_ca_system_score_codex":0.0005165139,"about_ca_system_score_gemma":0.00060930895,"threshold_uncertainty_score":0.692658},"labels":[],"label_agreement":null},{"id":"W2147077701","doi":"10.5539/ells.v1n2p89","title":"Ethics and Validity Stance in Educational Assessment","year":2011,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Engineering ethics; Test (biology); Curriculum; Psychology; Professional ethics; Pedagogy; Engineering","score_opus":0.06718898482724732,"score_gpt":0.404638927251174,"score_spread":0.3374499424239267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147077701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91671956,0.019385112,0.0000027499284,0.00085865596,0.0005605093,0.00013643345,0.000009035013,0.00002713918,0.0623008],"genre_scores_gemma":[0.99229616,0.004200285,0.0010881908,0.00014583915,0.00052916555,0.000019353181,0.000006054235,0.000004348567,0.001710608],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9991051,0.00023502873,0.00010756632,0.0001837367,0.00020412065,0.00016443507],"domain_scores_gemma":[0.9993243,0.00038155896,0.000036833906,0.00006704864,0.00014510132,0.000045138822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095873757,0.00009192813,0.00013723008,0.000052535666,0.0003347064,0.000093939954,0.00007044946,0.00008547582,0.00006199839],"category_scores_gemma":[0.0006406167,0.000077037614,0.00001702954,0.00018217541,0.00019608309,0.00024841062,0.000059595855,0.0003808249,5.139642e-7],"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":[0.0000043333916,0.000040343723,0.08983792,0.00002415526,0.000019091329,0.0000102237045,0.871568,9.176411e-9,0.000004320213,0.037674133,0.0005684409,0.00024897855],"study_design_scores_gemma":[0.0002809861,0.00003305323,0.21019042,0.00013558938,0.000012773215,4.1889282e-7,0.77693063,4.6185372e-7,0.0000066512434,0.0029632824,0.009292279,0.00015345226],"about_ca_topic_score_codex":0.00010786013,"about_ca_topic_score_gemma":0.001090659,"teacher_disagreement_score":0.1203525,"about_ca_system_score_codex":0.000032748187,"about_ca_system_score_gemma":0.00005880855,"threshold_uncertainty_score":0.31415027},"labels":[],"label_agreement":null},{"id":"W2147146043","doi":"10.5430/ijhe.v3n3p70","title":"Teachers’ Accounts of Their Perceptions and Practices of Providing Written Feedback to Nursing Students on Their Assignments","year":2014,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Competence (human resources); Psychology; Affect (linguistics); Exploratory research; Medical education; Sample (material); Mathematics education; Pedagogy; Medicine; Social psychology; Sociology; Communication","score_opus":0.04166792534371942,"score_gpt":0.4427322760168186,"score_spread":0.40106435067309915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147146043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9843607,0.000064418346,0.00005994335,0.005542351,0.0017354183,0.0001398651,0.0000033726262,0.0000040561035,0.008089875],"genre_scores_gemma":[0.99738383,0.00005665437,0.000507236,0.00018210584,0.0008219533,0.0000041425,0.0000026038058,0.0000075561657,0.0010339294],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984317,0.00016639238,0.0003499231,0.000107420106,0.0008436972,0.00010087917],"domain_scores_gemma":[0.9981166,0.00020695677,0.000976959,0.00007234071,0.0005528259,0.000074304895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008019326,0.00008494909,0.00014903609,0.00022325962,0.000089067515,0.00011390916,0.00048185143,0.000047692392,0.00013495522],"category_scores_gemma":[0.0001480885,0.000069032605,0.00005766908,0.000110275185,0.00008074073,0.0004919081,0.000033683107,0.00011390744,0.000004668923],"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":[0.00015038614,0.0020882692,0.81054014,0.000009329096,0.00027816868,2.688828e-7,0.11358555,0.00001548124,0.012475953,0.004378503,0.0043398845,0.052138083],"study_design_scores_gemma":[0.00036409305,0.00016452892,0.9598822,0.00037855032,0.00003366924,0.0000016507728,0.028911712,0.0000025523036,0.00040761917,0.0010691949,0.008709166,0.00007505408],"about_ca_topic_score_codex":0.000104525476,"about_ca_topic_score_gemma":0.000013945402,"teacher_disagreement_score":0.14934209,"about_ca_system_score_codex":0.00024908572,"about_ca_system_score_gemma":0.0001782983,"threshold_uncertainty_score":0.2815068},"labels":[],"label_agreement":null},{"id":"W2147604064","doi":"10.1097/acm.0b013e3181ed42f2","title":"Which Factors, Personal or External, Most Influence Studentsʼ Generation of Learning Goals?","year":2010,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; University of British Columbia","funders":"","keywords":"Perception; Observer (physics); Psychology; Quality (philosophy); Applied psychology; Medical education; Medicine","score_opus":0.06773309048148761,"score_gpt":0.4094149782330245,"score_spread":0.34168188775153685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147604064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99384916,0.00014675177,0.00012475616,0.001432495,0.0007347744,0.0001903822,9.876395e-7,0.000039915954,0.0034807995],"genre_scores_gemma":[0.990709,0.0007665182,0.00006613987,0.00017016176,0.0016642582,0.0000073821693,0.000010301974,0.00000952218,0.0065967063],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99800617,0.000121375735,0.00034315218,0.00021996153,0.0010424947,0.00026683323],"domain_scores_gemma":[0.9990391,0.00027632073,0.00023156794,0.00009300409,0.00021824092,0.00014173173],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001246133,0.00012353231,0.00022802652,0.00008683707,0.00030546778,0.000016297505,0.0004247236,0.00022421598,0.0016487697],"category_scores_gemma":[0.0019401748,0.00008785063,0.000020994283,0.00043394248,0.00031346935,0.0002796836,0.0000615622,0.00088850426,0.000017124696],"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":[0.000012026787,0.000008377214,0.7877835,0.000006866109,0.000015738626,8.958655e-7,0.058848985,0.0000038940616,0.15000208,0.0013306501,0.0015795938,0.0004073639],"study_design_scores_gemma":[0.0023502551,0.0005042401,0.8091798,0.00034529497,0.00016864091,0.0000050653307,0.13326134,0.0007366743,0.0023051929,0.00025901443,0.050356857,0.0005276424],"about_ca_topic_score_codex":0.001162926,"about_ca_topic_score_gemma":0.0010036458,"teacher_disagreement_score":0.14769688,"about_ca_system_score_codex":0.000035720317,"about_ca_system_score_gemma":0.00015968119,"threshold_uncertainty_score":0.9992639},"labels":[],"label_agreement":null},{"id":"W2147628522","doi":"","title":"Some drivers of test item difficulty in mathematics : an analysis of the competency rubric","year":2012,"lang":"en","type":"article","venue":"ACEReSearch (Australian Council for Educational Research)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rubric; Test (biology); Inclusion (mineral); Mathematics education; Test preparation; Psychology; Pedagogy; Computer science; Medical education; Engineering; Social psychology; Medicine","score_opus":0.35000712176952,"score_gpt":0.4785186624063204,"score_spread":0.12851154063680043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147628522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863477,0.0000884189,0.0000010723875,0.005986522,0.00015498925,0.0009161863,0.00017433731,0.0000060140374,0.0063248044],"genre_scores_gemma":[0.9759531,0.00011425218,0.00036712846,0.0000090349195,0.00026058935,0.00008703986,0.000042324788,0.00001280376,0.02315375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934162,0.0004569809,0.00041343103,0.00023141962,0.004604148,0.00087782135],"domain_scores_gemma":[0.9912003,0.005345425,0.00014870454,0.00042138112,0.0025956125,0.00028857772],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009152442,0.00011359846,0.0002860887,0.00047150734,0.0004816415,0.000070937844,0.0011868692,0.00010573774,0.0015258576],"category_scores_gemma":[0.00895057,0.0000894094,0.00020060294,0.0029964237,0.0011546691,0.0005722618,0.00015270943,0.00033626254,0.000027081212],"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":[0.00001770966,0.0019519138,0.813169,0.000083271756,0.00017333515,9.879776e-8,0.02695471,0.000016763493,0.001594415,0.14096984,0.014999441,0.000069468195],"study_design_scores_gemma":[0.00028281528,0.00008407081,0.94497794,0.000041573287,0.00007093918,1.0386438e-7,0.042319562,0.0001357899,0.00017345019,0.0052282903,0.00657298,0.00011250247],"about_ca_topic_score_codex":0.005162846,"about_ca_topic_score_gemma":0.007404346,"teacher_disagreement_score":0.13574156,"about_ca_system_score_codex":0.0015362096,"about_ca_system_score_gemma":0.0041472474,"threshold_uncertainty_score":0.99939746},"labels":[],"label_agreement":null},{"id":"W2148189517","doi":"10.1111/j.1365-2729.2008.00290.x","title":"Peering into large lectures: examining peer and expert mark agreement using peerScholar, an online peer assessment tool","year":2008,"lang":"en","type":"article","venue":"Journal of Computer Assisted Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":114,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Peer assessment; Peering; Class (philosophy); Computer science; Accountability; Class size; Peer evaluation; Rank (graph theory); Peer feedback; Mathematics education; Online assessment; World Wide Web; Multimedia; Higher education; The Internet; Psychology; Artificial intelligence; Formative assessment; Mathematics","score_opus":0.08174915342893448,"score_gpt":0.3820792831741884,"score_spread":0.3003301297452539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148189517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94158745,0.00029429467,0.054820854,0.00090544054,0.0009196801,0.000139583,8.3396503e-7,0.000047086636,0.0012847496],"genre_scores_gemma":[0.8733247,0.00011529865,0.12318709,0.00026446476,0.0018392236,0.0000013952458,0.000009288213,0.00002859543,0.0012299842],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954913,0.0007052255,0.00069218414,0.0003058628,0.0022893508,0.00051607465],"domain_scores_gemma":[0.9976903,0.0002415302,0.000611992,0.00015191101,0.0010316226,0.00027260196],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0034875607,0.00026305774,0.0004797551,0.00031343158,0.0015474166,0.0004896019,0.00040421655,0.00015084578,0.00019599854],"category_scores_gemma":[0.00025720318,0.0002443668,0.00014620936,0.00031587525,0.00011608098,0.001090377,0.00019888121,0.0010398686,0.000002033338],"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":[0.00014468521,0.0010230639,0.7131329,0.00004812596,0.0006550683,0.00065198605,0.18857074,0.006100516,0.004975659,0.000266344,0.0029096014,0.081521295],"study_design_scores_gemma":[0.002504215,0.00077889586,0.85320514,0.000280025,0.00010547377,0.00024243022,0.032137506,0.021551717,0.000020108522,0.000030109843,0.088537015,0.0006073761],"about_ca_topic_score_codex":0.00012540026,"about_ca_topic_score_gemma":0.00005878198,"teacher_disagreement_score":0.15643322,"about_ca_system_score_codex":0.0003926846,"about_ca_system_score_gemma":0.00032183435,"threshold_uncertainty_score":0.99975246},"labels":[],"label_agreement":null},{"id":"W2149953989","doi":"","title":"Formative assessment: A systematic and artistic process of instruction for supporting school and lifelong learning","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Lifelong learning; Process (computing); Adaptation (eye); Mathematics education; Pedagogy; Engineering ethics; Knowledge management; Psychology; Computer science; Engineering","score_opus":0.03395313789157107,"score_gpt":0.35764916895792603,"score_spread":0.323696031066355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149953989","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958929,0.00038955867,0.00050197245,0.00075645844,0.0012409929,0.00040573985,0.0000030651606,0.0000029195721,0.0008064222],"genre_scores_gemma":[0.9982329,0.000026812522,0.00093532214,0.00004694048,0.00046828762,0.000039314484,0.00000797771,0.000008749439,0.00023369947],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9989053,0.0001445152,0.0004410973,0.00007603267,0.00007565082,0.000357394],"domain_scores_gemma":[0.9975223,0.00017004814,0.0008037528,0.000052740754,0.000608933,0.0008422217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020453664,0.000077085606,0.00020033559,0.0003439389,0.00040447369,0.00008941924,0.000087783155,0.000059058017,0.000027436634],"category_scores_gemma":[0.0026653935,0.000084229,0.000030628507,0.00022419386,0.00008120475,0.00074786495,0.0000028816098,0.00013028286,3.627614e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006538979,0.000039120125,0.44370225,0.003804859,0.00006261435,4.0376827e-7,0.527109,0.000016168215,0.0000723668,0.021371793,0.00032944433,0.0034854452],"study_design_scores_gemma":[0.00033589447,0.00011794543,0.24468632,0.0018497594,0.0002185681,0.00009961846,0.7488135,0.00022576649,0.000023982424,0.0023758642,0.001069756,0.00018302017],"about_ca_topic_score_codex":0.006821086,"about_ca_topic_score_gemma":0.08174456,"teacher_disagreement_score":0.2217045,"about_ca_system_score_codex":0.0011697778,"about_ca_system_score_gemma":0.0048974035,"threshold_uncertainty_score":0.9997926},"labels":[],"label_agreement":null},{"id":"W2155777959","doi":"10.5539/ijel.v2n1p35","title":"The Effect of Student Receptivity to Instructional Feedback on Writing Proficiency among Chinese Speaking English Language Learners","year":2012,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Paragraph; Receptivity; Psychology; Mathematics education; Corrective feedback; Principal (computer security); Computer science; Medicine","score_opus":0.013271327943449672,"score_gpt":0.3607904881070761,"score_spread":0.34751916016362644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155777959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89777017,0.00006887124,0.000020756754,0.000033777535,0.024464672,0.00016157045,0.0000057625793,0.000018081906,0.07745633],"genre_scores_gemma":[0.9701331,0.00003366921,0.00031450053,0.000024773288,0.029350344,0.0000032359046,0.0000021705798,0.000013190295,0.00012501863],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971382,0.00027120224,0.0005366312,0.00011341434,0.0016395994,0.00030096297],"domain_scores_gemma":[0.9924988,0.0012987466,0.000568761,0.00010113382,0.0053772144,0.00015531923],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003184028,0.00014265973,0.00021918827,0.00016644431,0.00026231224,0.00018102328,0.0007390657,0.000066808476,0.000048921524],"category_scores_gemma":[0.072349705,0.00010039013,0.00015947517,0.00024522367,0.0001904179,0.00017167765,0.00012025831,0.0003862506,0.0000044947583],"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":[0.00015309858,0.000121575635,0.9350611,0.000005733711,0.00013403878,0.0000051630973,0.0545943,0.00022425977,0.00002302693,0.005903776,0.00046692818,0.0033069805],"study_design_scores_gemma":[0.0018168021,0.0007389297,0.83204144,0.00031639345,0.00009492644,0.0000011089179,0.09057086,0.0000216846,0.0005516265,0.00008395652,0.07339267,0.00036959475],"about_ca_topic_score_codex":0.000057887817,"about_ca_topic_score_gemma":0.000068040696,"teacher_disagreement_score":0.10301966,"about_ca_system_score_codex":0.00025892287,"about_ca_system_score_gemma":0.00007820578,"threshold_uncertainty_score":0.93546426},"labels":[],"label_agreement":null},{"id":"W2156268470","doi":"10.5206/cjsotl-rcacea.2011.2.5","title":"Writing Helpful Feedback: The Influence of Feedback Type on Students’ Perceptions and Writing Performance","year":2011,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Humber Polytechnic; Carleton University; Mount Royal University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Helpfulness; Humanities; Psychology; Perception; Social psychology; Art","score_opus":0.06405168957209802,"score_gpt":0.3494725568997996,"score_spread":0.2854208673277016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156268470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99547476,0.00040079255,0.000007817829,0.0012180092,0.00014634401,0.0002003493,0.0000014919509,0.000008242653,0.002542193],"genre_scores_gemma":[0.9986297,0.00018587016,0.00017950978,0.00015133922,0.00020387144,0.0000035380865,4.0780748e-7,0.000013013566,0.0006327495],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99803674,0.0008409632,0.00027636398,0.000117744385,0.00037102093,0.00035718214],"domain_scores_gemma":[0.99828655,0.00096910656,0.00026086718,0.00013208282,0.00018647853,0.00016489456],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.011381965,0.00011288165,0.00014535539,0.00008870184,0.010082222,0.0004103927,0.0006774585,0.00006416824,0.000042115054],"category_scores_gemma":[0.0013627526,0.000065888664,0.00006487104,0.00014285483,0.0005392146,0.00032685068,0.000049710845,0.0018880218,0.0000027263743],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044397464,0.000010529171,0.87923163,0.000017930946,0.0000678932,7.6118795e-7,0.10137963,0.0003460461,0.000114067094,0.0034769299,0.000028167751,0.015281994],"study_design_scores_gemma":[0.00022097438,0.00018748509,0.9091091,0.00027173673,0.00006597681,0.000013765551,0.088624515,0.000055224977,0.000005399256,0.00033967238,0.0010125091,0.00009363809],"about_ca_topic_score_codex":0.00755499,"about_ca_topic_score_gemma":0.0066213296,"teacher_disagreement_score":0.029877456,"about_ca_system_score_codex":0.000062162355,"about_ca_system_score_gemma":0.00019609643,"threshold_uncertainty_score":0.9990538},"labels":[],"label_agreement":null},{"id":"W2159609851","doi":"10.1191/0265532204lt288oa","title":"ESL/EFL instructors’ classroom assessment practices: purposes, methods, and procedures","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Psychology; English as a foreign language; Mathematics education; Tertiary level; Pedagogy; Second language; Language assessment; Linguistics","score_opus":0.06401151606627827,"score_gpt":0.4566933338742858,"score_spread":0.39268181780800754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159609851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88996714,0.0010865754,0.00091468275,0.0011419782,0.0003414859,0.0005238556,0.000003373891,0.00038530212,0.105635606],"genre_scores_gemma":[0.66833675,0.000045215726,0.3304719,0.00020610109,0.00041520045,0.000023970428,0.000004750965,0.000017263876,0.00047885528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983709,0.00023232849,0.00023016303,0.00033622226,0.00042266166,0.0004077303],"domain_scores_gemma":[0.9984898,0.00073267025,0.00038974822,0.0001591591,0.00008756423,0.00014104483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012594918,0.00016029156,0.00019261414,0.00007346245,0.0006034473,0.00033342637,0.00025224616,0.00009594835,0.00007815419],"category_scores_gemma":[0.0042768843,0.00014758801,0.00003457235,0.00035829487,0.00015921147,0.00049749925,0.000119671015,0.00025058602,0.000009544773],"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":[0.000017907454,0.00031890383,0.571827,0.00022070242,0.00014528548,0.00016533208,0.16596346,0.00002255949,0.03583076,0.04561178,0.00037620644,0.17950013],"study_design_scores_gemma":[0.004627989,0.00053177046,0.5233849,0.00087021524,0.00042780183,0.00009897222,0.417603,0.00026029817,0.0024667666,0.022054665,0.025515001,0.0021586095],"about_ca_topic_score_codex":0.005643806,"about_ca_topic_score_gemma":0.0027572415,"teacher_disagreement_score":0.32955724,"about_ca_system_score_codex":0.00015519245,"about_ca_system_score_gemma":0.00047157542,"threshold_uncertainty_score":0.8531784},"labels":[],"label_agreement":null},{"id":"W2160202591","doi":"10.1002/j.2168-9830.2010.tb01072.x","title":"Students' Conceptions of Tutor and Automated Feedback in Professional Writing","year":2010,"lang":"en","type":"article","venue":"Journal of Engineering Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Australian Research Council; University of Sydney; Carnegie Mellon University","keywords":"TUTOR; Perception; Mathematics education; Peer feedback; Engineering education; Psychology; Relation (database); Pedagogy; Computer science; Engineering; Mechanical engineering","score_opus":0.010193223868575763,"score_gpt":0.36939951109769625,"score_spread":0.3592062872291205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160202591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99698997,0.00006103907,0.000019054558,0.00034440254,0.0021764645,0.00007309327,3.883237e-7,0.000013619366,0.0003219819],"genre_scores_gemma":[0.997446,0.000026969847,0.0019112565,0.000008460548,0.0003404515,0.000002630762,6.275053e-7,0.0000039653187,0.00025965172],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993588,0.000022080803,0.00024472442,0.000041209987,0.0002495263,0.0000836998],"domain_scores_gemma":[0.9995175,0.00008952027,0.00015059825,0.000032563792,0.00016008652,0.000049738628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005907193,0.00004094188,0.00009376634,0.00013808667,0.000044965556,0.000031292886,0.0001114114,0.00004657568,0.000040493203],"category_scores_gemma":[0.00022157993,0.000039126935,0.000021789021,0.00016137841,0.0000332868,0.00020475393,0.000013781501,0.00017936763,6.632385e-7],"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":[0.000011882673,0.0005735053,0.9038472,0.000061321334,0.000031138836,0.0000011146473,0.025020529,0.00012921148,0.05837591,0.00804583,0.0014719343,0.0024304313],"study_design_scores_gemma":[0.0002513498,0.000019084904,0.98997736,0.00014982832,0.000009057393,0.000002709539,0.0074710553,0.00026193116,0.000082103244,0.00004200128,0.0016814455,0.000052049236],"about_ca_topic_score_codex":0.000040367264,"about_ca_topic_score_gemma":0.000030062407,"teacher_disagreement_score":0.086130194,"about_ca_system_score_codex":0.00003833113,"about_ca_system_score_gemma":0.0002545347,"threshold_uncertainty_score":0.159555},"labels":[],"label_agreement":null},{"id":"W2160982769","doi":"10.1145/1734263.1734380","title":"Turning exams into a learning experience","year":2010,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics education; Psychology; Computer science","score_opus":0.021424129341993347,"score_gpt":0.3681600372934324,"score_spread":0.34673590795143905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160982769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6900108,0.0000061688484,0.00017843134,0.00027283753,0.0004077819,0.000048062284,7.0380066e-9,0.00010758296,0.30896837],"genre_scores_gemma":[0.9792857,0.000010119902,0.0015774254,0.0000865054,0.0003147588,0.000010585037,4.340145e-7,0.000004679133,0.018709749],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992342,0.000043683853,0.000080808735,0.00013849336,0.00028882571,0.00021398364],"domain_scores_gemma":[0.99969006,0.00009184653,0.000031451647,0.000073359195,0.000030893,0.00008240259],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036036718,0.000054570133,0.00006195059,0.000029418083,0.0006369923,0.00013990517,0.00022507193,0.000056244808,0.0033402331],"category_scores_gemma":[0.00022724501,0.00004836038,0.000029368748,0.00016858274,0.00016044421,0.00023823403,0.00005353564,0.00023464978,0.00018916576],"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":[0.0000034710508,0.000030028345,0.60304284,0.0000015869989,0.0000061812916,0.000003303959,0.27881238,0.0000033231725,0.035167176,0.061757077,0.0005270565,0.020645553],"study_design_scores_gemma":[0.0003356243,0.00004709836,0.11000311,0.000008234651,0.0000060953894,7.437591e-7,0.23732941,0.00025839638,0.0015563288,0.0013361142,0.6487198,0.0003990322],"about_ca_topic_score_codex":0.0014176258,"about_ca_topic_score_gemma":0.002252959,"teacher_disagreement_score":0.64819276,"about_ca_system_score_codex":0.00001536459,"about_ca_system_score_gemma":0.000040898674,"threshold_uncertainty_score":0.9975709},"labels":[],"label_agreement":null},{"id":"W2162144918","doi":"10.7202/1006438ar","title":"Formative Assessment: Revisiting the territory from the point of view of teachers","year":2011,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Formative assessment; Negotiation; Point (geometry); Pedagogy; Sociology; Mathematics education; Psychology; Social science","score_opus":0.3482909014551487,"score_gpt":0.45681419665933376,"score_spread":0.10852329520418508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162144918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8519402,0.0009937043,0.00055717793,0.0069602914,0.0022463708,0.00041914446,0.000029587078,0.000013318016,0.13684018],"genre_scores_gemma":[0.98748696,0.00056689366,0.0108801,0.00046869798,0.00038792467,0.000011123845,0.0000015569435,0.0000068782774,0.00018989561],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99748534,0.0008988698,0.0007173652,0.00013459063,0.0005182688,0.00024555926],"domain_scores_gemma":[0.9968344,0.000714125,0.0015310666,0.00019617954,0.0006273203,0.00009691724],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006238612,0.00011036052,0.0002221192,0.00012986556,0.0014621713,0.00004971057,0.0010323966,0.00005651809,0.0002722424],"category_scores_gemma":[0.0007590712,0.00007213537,0.00015979234,0.00060100295,0.0010742742,0.00080410443,0.00005007853,0.00022246334,0.0000029141213],"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":[0.000036647827,0.00069777673,0.09626131,0.000110943074,0.00018963436,0.000001004577,0.66724926,0.00007570251,0.0014612917,0.13216183,0.004222037,0.09753253],"study_design_scores_gemma":[0.00027505046,0.00023917039,0.32238176,0.0009050885,0.00020811606,0.000032993205,0.58401155,0.000111631925,0.0013680627,0.028817492,0.06141344,0.00023561428],"about_ca_topic_score_codex":0.0020702214,"about_ca_topic_score_gemma":0.0003102593,"teacher_disagreement_score":0.22612046,"about_ca_system_score_codex":0.0006598569,"about_ca_system_score_gemma":0.0009114205,"threshold_uncertainty_score":0.9998378},"labels":[],"label_agreement":null},{"id":"W2162556894","doi":"10.21432/t21c7r","title":"Utilizing peer interactions to promote learning through a web-based peer assessment system","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer evaluation; Psychology; Ligne; Valuation (finance); Pedagogy; Higher education; Humanities; Political science; Philosophy","score_opus":0.022870909531472555,"score_gpt":0.34798379124800916,"score_spread":0.32511288171653663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162556894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8497632,0.00026447474,0.0013320632,0.07896016,0.0006657546,0.00021653339,0.0000012052634,0.00016092308,0.06863565],"genre_scores_gemma":[0.99241567,0.000009922145,0.0032907669,0.000072186784,0.0001537724,0.000002970528,0.0000012017535,0.000010103026,0.0040434],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986326,0.00014513898,0.00027390916,0.00015937722,0.00036879905,0.0004201849],"domain_scores_gemma":[0.9987274,0.00006184403,0.00021833101,0.000069582915,0.00061489746,0.0003079411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011034514,0.00011512883,0.00023909846,0.00063659035,0.0010405885,0.00018974506,0.0002301088,0.00014376116,0.00009438757],"category_scores_gemma":[0.0006977948,0.000113773654,0.000058733167,0.0006403715,0.00012626585,0.00017140957,0.000013146477,0.00097178307,0.000012009674],"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":[0.000039948365,0.00008876059,0.750133,0.00003956141,0.00020767661,0.0007366139,0.03365502,0.0008002516,0.0026959826,0.09557799,0.008133853,0.107891336],"study_design_scores_gemma":[0.0004996896,0.00052579504,0.0035886983,0.00024631506,0.000044584343,0.00006286157,0.10943963,0.00036827291,0.0000405013,0.00023534529,0.88476473,0.00018357777],"about_ca_topic_score_codex":0.0012369596,"about_ca_topic_score_gemma":0.0072689936,"teacher_disagreement_score":0.8766309,"about_ca_system_score_codex":0.00040072648,"about_ca_system_score_gemma":0.0011577765,"threshold_uncertainty_score":0.8003471},"labels":[],"label_agreement":null},{"id":"W2167507251","doi":"10.1111/medu.12517","title":"Automated essay scoring and the future of educational assessment in medical education","year":2014,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada; University of Alberta","funders":"","keywords":"Summative assessment; Formative assessment; Computer science; Process (computing); Context (archaeology); Scoring system; Writing assessment; Educational measurement; Artificial intelligence; Natural language processing; Machine learning; Mathematics education; Curriculum; Psychology; Medicine; Pedagogy","score_opus":0.007292918176272418,"score_gpt":0.38894998801684083,"score_spread":0.3816570698405684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167507251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5630151,0.0009811503,0.000088985784,0.35997987,0.005178316,0.0005364445,4.1207042e-7,0.00005643197,0.07016329],"genre_scores_gemma":[0.9942191,0.00038355592,0.00040666573,0.0022772348,0.0017931893,0.00011319984,0.000022666356,0.000006207894,0.0007781372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99754024,0.00052629266,0.00032423192,0.00018072865,0.0012553097,0.00017319877],"domain_scores_gemma":[0.99888426,0.0005535576,0.00013243302,0.00013216253,0.00012771199,0.00016989285],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032478578,0.000083008235,0.00016428689,0.00010182347,0.00019281854,0.000044469652,0.0003106954,0.00015603055,0.001711079],"category_scores_gemma":[0.0026037835,0.000060685867,0.000032014854,0.00036062792,0.0004784511,0.00013843375,0.00004613607,0.0002516379,0.000008097481],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000149142115,0.0008687578,0.20903978,0.00003781899,0.000011948252,6.532783e-8,0.011043757,5.021541e-7,0.0000026356238,0.61447304,0.017246516,0.14726025],"study_design_scores_gemma":[0.0016593792,0.000030380179,0.8698143,0.00041317026,0.000032469838,0.000003347403,0.022556087,0.0050272844,0.0000028540367,0.016796801,0.0834605,0.00020345654],"about_ca_topic_score_codex":0.0016132622,"about_ca_topic_score_gemma":0.0018067089,"teacher_disagreement_score":0.66077447,"about_ca_system_score_codex":0.00015786277,"about_ca_system_score_gemma":0.012410129,"threshold_uncertainty_score":0.9992015},"labels":[],"label_agreement":null},{"id":"W2167980328","doi":"10.1007/s10459-010-9263-2","title":"Exploring the divergence between self-assessment and self-monitoring","year":2010,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":190,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Self-assessment; Self-monitoring; Self evaluation; Psychology; Medicine; Applied psychology; Social psychology","score_opus":0.06736112885207077,"score_gpt":0.45624517824613237,"score_spread":0.3888840493940616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167980328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98269147,0.0010732632,0.00002754536,0.004484038,0.0055811107,0.0004176181,4.2387347e-7,0.00007510979,0.0056494363],"genre_scores_gemma":[0.97065324,0.016460193,0.011688946,0.000081050544,0.00094588473,0.00013426018,5.4966324e-7,0.0000039981164,0.000031856445],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982615,0.00016977191,0.0002766715,0.00031421898,0.0005558048,0.00042202367],"domain_scores_gemma":[0.9990632,0.00043757533,0.00017012727,0.00013610844,0.000057942878,0.00013507545],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0030473385,0.000094679664,0.00011714307,0.00011304581,0.0018978369,0.0001612887,0.00046949767,0.00002656247,0.00001329096],"category_scores_gemma":[0.000056820685,0.00007433657,0.000016821086,0.0008383776,0.00030780476,0.0018219448,0.0000708329,0.00025215227,0.0000047913963],"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":[3.268843e-7,0.00005079174,0.91644293,0.000016045664,0.0000014047661,3.8972065e-8,0.016714927,0.0000040600735,0.0000050991744,0.013670777,0.000009729284,0.053083844],"study_design_scores_gemma":[0.000054684624,0.000042359497,0.93893987,0.000040674215,0.0000037009888,2.3077824e-7,0.024401024,0.000022493083,0.000009757865,0.0019863565,0.034400374,0.000098457516],"about_ca_topic_score_codex":0.0018476694,"about_ca_topic_score_gemma":0.0014899548,"teacher_disagreement_score":0.052985385,"about_ca_system_score_codex":0.00022190959,"about_ca_system_score_gemma":0.0013476564,"threshold_uncertainty_score":0.99940157},"labels":[],"label_agreement":null},{"id":"W2170205952","doi":"10.5539/elt.v8n1p1","title":"Influence of Instructor Personality on Student Evaluation of Teaching: A Comparison between English Majors and Non-English Majors","year":2014,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Neuroticism; Personality; Extraversion and introversion; Class (philosophy); Mathematics education; Scale (ratio); Big Five personality traits; Social psychology; Pedagogy","score_opus":0.023434109967104204,"score_gpt":0.3660662689247755,"score_spread":0.3426321589576713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170205952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9460498,0.00007936463,0.00002183099,0.000023248444,0.00044650453,0.0005722478,0.000019465413,0.000120829325,0.052666727],"genre_scores_gemma":[0.997918,0.0000044519406,0.0005168066,0.000031278836,0.0013849416,0.000018259405,0.000026120622,0.000025260422,0.00007484107],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99454856,0.0019315692,0.0006417993,0.00046641767,0.0020011135,0.00041054393],"domain_scores_gemma":[0.99760187,0.0008777896,0.0005264415,0.00037234765,0.00045141802,0.00017014157],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0104665905,0.00026868453,0.00059652247,0.00020627593,0.00049495784,0.00013352484,0.0005862423,0.00018420762,0.000056347286],"category_scores_gemma":[0.0076370495,0.00026606035,0.00012330941,0.00019549069,0.00028217162,0.00053386664,0.00017689733,0.0008402151,0.0000016424299],"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":[0.000010388345,0.00011963189,0.42312115,0.000026870772,0.00005292534,3.9244327e-7,0.568887,0.00008530946,0.00011989994,0.0026836833,0.00004482845,0.0048479093],"study_design_scores_gemma":[0.0014354684,0.00017774603,0.5671936,0.00017964773,0.00020028999,7.03808e-8,0.42932853,0.00012797714,0.0001958131,0.00011638821,0.0007374343,0.00030701756],"about_ca_topic_score_codex":0.0029536248,"about_ca_topic_score_gemma":0.000515106,"teacher_disagreement_score":0.14407246,"about_ca_system_score_codex":0.00021227535,"about_ca_system_score_gemma":0.0001030334,"threshold_uncertainty_score":0.99997914},"labels":[],"label_agreement":null},{"id":"W2170425544","doi":"10.5539/ies.v8n6p46","title":"What Are the Learning Approaches Applied by Undergraduate Students in English Process Writing Based on Gender?","year":2015,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Context (archaeology); Psychology; Process (computing); Writing process; Computer science","score_opus":0.18188207616860608,"score_gpt":0.4501978746869645,"score_spread":0.2683157985183584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170425544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89241934,0.0012995555,0.000055334745,0.018486299,0.007807076,0.00057059276,0.0000016404135,0.00011203332,0.07924812],"genre_scores_gemma":[0.9954923,0.00024115245,0.000028004695,0.0006538106,0.00051275146,0.0002643772,0.00001894068,0.000009625385,0.0027790712],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99816227,0.00014160814,0.00021292378,0.00023856327,0.0010673915,0.00017727242],"domain_scores_gemma":[0.99866116,0.00028742506,0.00018053428,0.00006769853,0.00075461203,0.00004857439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009850694,0.000114918425,0.00012411876,0.00010754311,0.00032963362,0.00044399785,0.0004102161,0.000037375885,0.000009774176],"category_scores_gemma":[0.0008618158,0.00009333167,0.000030119396,0.000258066,0.00013041604,0.00035823663,0.00006385525,0.0001849033,0.000018130979],"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":[0.000040620296,0.0009941164,0.8227771,0.00001620465,0.00014248943,5.027003e-7,0.15288296,0.0020876315,0.0000016116645,0.004974316,0.012289323,0.003793159],"study_design_scores_gemma":[0.00039368818,0.000014217535,0.025340246,0.00008465706,0.00001051535,4.6535785e-8,0.95542353,0.0002905064,0.0000109145185,0.0022796688,0.016013809,0.00013821875],"about_ca_topic_score_codex":0.000047856527,"about_ca_topic_score_gemma":0.00012024465,"teacher_disagreement_score":0.80254054,"about_ca_system_score_codex":0.00036300256,"about_ca_system_score_gemma":0.00022392195,"threshold_uncertainty_score":0.42814815},"labels":[],"label_agreement":null},{"id":"W2171832653","doi":"","title":"Alternative sources of feedback and second language writing development in university content courses","year":2011,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Content (measure theory); Mathematics education; Higher education; Computer science; Pedagogy; Psychology; Political science; Mathematics","score_opus":0.30687951107584355,"score_gpt":0.5127492825080466,"score_spread":0.20586977143220309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171832653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9639086,0.0024975,0.000020785663,0.000032141535,0.00015117366,0.00028676895,0.0000117280215,0.000011098662,0.03308019],"genre_scores_gemma":[0.9965162,0.0020722921,0.0003488864,0.00003828172,0.000049262602,0.0000024765145,0.0000014080869,0.00001050516,0.00096063945],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99829197,0.00026030367,0.0004353921,0.00023761616,0.0004985663,0.00027615638],"domain_scores_gemma":[0.99872077,0.00023739095,0.00058680127,0.00010972361,0.00020470598,0.00014060317],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012509599,0.00015128027,0.0004326559,0.0004170068,0.0002633132,0.00023347214,0.0012661427,0.00006432411,0.0054752263],"category_scores_gemma":[0.00009472902,0.00014982616,0.000061029426,0.0004426577,0.00032012587,0.0013270404,0.000549598,0.00017548328,0.000003233116],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000905446,0.00015751843,0.9524619,0.000027599039,0.00010890164,0.00003747485,0.038541973,0.0000014978864,0.002925478,0.0005523763,0.0003606246,0.0047340863],"study_design_scores_gemma":[0.0005996942,0.0000068650875,0.93626976,0.00024397916,0.000023509674,8.7790715e-7,0.05090307,0.0000037041045,0.009694116,0.00032702077,0.0017322621,0.0001951423],"about_ca_topic_score_codex":0.009540302,"about_ca_topic_score_gemma":0.004579142,"teacher_disagreement_score":0.032607637,"about_ca_system_score_codex":0.00011182454,"about_ca_system_score_gemma":0.00017105081,"threshold_uncertainty_score":0.99705523},"labels":[],"label_agreement":null},{"id":"W2179337464","doi":"10.5296/jei.v1i2.8381","title":"A Smart Way of Coping with Common Core Challenges - Introduction to CAFA SmartWorkbook","year":2015,"lang":"en","type":"article","venue":"Journal of Educational Issues","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Coping (psychology); Information and Communications Technology; Mathematics education; Pedagogy; Computer science; Psychology","score_opus":0.08941035088302628,"score_gpt":0.4076068602910477,"score_spread":0.3181965094080214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179337464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75880873,0.0042115874,0.00001936132,0.21630085,0.0018908719,0.00018658281,0.0000011606163,0.0000068576533,0.018573983],"genre_scores_gemma":[0.9851935,0.00050054776,0.0029999558,0.00015420928,0.0065217977,0.000005133887,0.0000030076149,0.000008623183,0.004613236],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988295,0.0000770259,0.00026859672,0.00008661294,0.0006112355,0.00012705328],"domain_scores_gemma":[0.99860466,0.00014351774,0.00029444293,0.000082160426,0.00072090945,0.0001542921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000805243,0.000070423805,0.00019845698,0.00012342968,0.00009864493,0.000034371507,0.0001945363,0.000035216523,0.00022856066],"category_scores_gemma":[0.00019999567,0.00005662598,0.000039069793,0.00017686033,0.00010021259,0.00025525028,0.000018714929,0.000093487026,0.000016610189],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038012938,0.000750855,0.27351034,0.000036721627,0.00022460661,0.0000029215598,0.16461772,0.00018553218,0.00019811778,0.09490864,0.46204948,0.0031349603],"study_design_scores_gemma":[0.0005638426,0.0007874502,0.11667357,0.00018414987,0.00006923823,0.0000151684035,0.056800414,0.0000020728426,0.00016298101,0.007010302,0.8175359,0.00019492925],"about_ca_topic_score_codex":0.00031232927,"about_ca_topic_score_gemma":0.0008523518,"teacher_disagreement_score":0.3554864,"about_ca_system_score_codex":0.00013444063,"about_ca_system_score_gemma":0.0004258989,"threshold_uncertainty_score":0.2502579},"labels":[],"label_agreement":null},{"id":"W2183435816","doi":"10.1007/s11092-015-9233-6","title":"Teacher assessment literacy: a review of international standards and measures","year":2015,"lang":"en","type":"review","venue":"Educational Assessment Evaluation and Accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":253,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Literacy; Educational assessment; Mainland; Psychology; Pedagogy; Geography","score_opus":0.13742489297286617,"score_gpt":0.5795117938372106,"score_spread":0.44208690086434443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183435816","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000070910195,0.9466183,0.000028332346,0.0029385,0.0010372748,0.0023122719,0.00021035915,0.000021447728,0.04676258],"genre_scores_gemma":[0.00059036084,0.9954776,0.0012236641,0.00016560507,0.0007095266,0.00062387163,0.0007282111,0.000021239792,0.00045990988],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920936,0.0017142249,0.0010788116,0.00064115244,0.00422735,0.0002448302],"domain_scores_gemma":[0.99441123,0.0006462519,0.00087784807,0.00033797073,0.0035319782,0.00019469377],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019898808,0.0003648247,0.001121853,0.00020339819,0.00028392562,0.00029252144,0.00040092075,0.0002018631,0.0043696505],"category_scores_gemma":[0.0010661912,0.0003140791,0.00021191448,0.00038542596,0.00035246304,0.00066303986,0.00017300271,0.00037824683,0.000004934088],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036664612,0.00041655597,0.008758956,0.009534821,0.00020637889,8.3757435e-8,0.0010178514,8.103374e-8,9.133324e-8,0.003787145,0.010471021,0.9658033],"study_design_scores_gemma":[0.00029457634,0.000026800499,0.0099680135,0.010690639,0.0008722066,0.0000017452187,0.00086513365,0.00002604948,9.680338e-9,0.0015047371,0.9754583,0.00029174858],"about_ca_topic_score_codex":0.0002951071,"about_ca_topic_score_gemma":0.00010423875,"teacher_disagreement_score":0.9655116,"about_ca_system_score_codex":0.0022665164,"about_ca_system_score_gemma":0.01331173,"threshold_uncertainty_score":0.99993116},"labels":[],"label_agreement":null},{"id":"W2183500712","doi":"10.3968/7840","title":"On the Analysis of the Effective Implementation of Peer Feedback in Non-English Majors’ Writing","year":2015,"lang":"en","type":"article","venue":"Studies in literature and language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Computer science; Process (computing); Checklist; Second language writing; Key (lock); Mathematics education; Psychology; Second language; Cognitive psychology; Linguistics","score_opus":0.019006474254120956,"score_gpt":0.39053473684621026,"score_spread":0.3715282625920893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183500712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9882938,0.0014932372,2.7374935e-7,0.00041754264,0.00014536754,0.0002798034,0.000013566592,0.0000027734302,0.009353583],"genre_scores_gemma":[0.99955,0.000057356112,0.000012640195,0.00008970305,0.00007370357,0.000018321902,0.0000034866687,0.000002179766,0.0001926507],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99912655,0.00021472857,0.00015467047,0.000100363504,0.00029329187,0.00011039529],"domain_scores_gemma":[0.99923384,0.00040412505,0.00008625949,0.000091253125,0.0001724376,0.000012095585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012295322,0.00006320906,0.00018413164,0.000106108615,0.000076655175,0.000026316106,0.00011551118,0.000033747172,0.000012388471],"category_scores_gemma":[0.00037808344,0.00003463834,0.0000521892,0.0011542718,0.00015900591,0.00007357535,0.00006972766,0.00011557514,1.3882578e-7],"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":[0.000011864102,0.000018005387,0.21801265,0.000012138805,0.00015991811,0.0000017634744,0.7763338,0.000003724948,0.000021478794,0.0039848187,0.0006742701,0.00076558365],"study_design_scores_gemma":[0.00030810016,0.000023707898,0.39335975,0.00007968879,0.00006822255,2.282559e-8,0.60568005,0.000003766444,0.000050473704,0.00028563128,0.00010266346,0.000037949096],"about_ca_topic_score_codex":0.00061855867,"about_ca_topic_score_gemma":0.006797063,"teacher_disagreement_score":0.17534709,"about_ca_system_score_codex":0.000041398056,"about_ca_system_score_gemma":0.000012994107,"threshold_uncertainty_score":0.37929207},"labels":[],"label_agreement":null},{"id":"W2186483225","doi":"10.37514/wac-j.2005.16.1.06","title":"Dangerous Partnerships: How Competence Testing Can Sabotage WAC","year":2005,"lang":"en","type":"article","venue":"The WAC Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Competence (human resources); Business; Engineering; Psychology; Social psychology","score_opus":0.14391756235668948,"score_gpt":0.3537266698029337,"score_spread":0.20980910744624423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186483225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.788687,0.00081626413,0.00025077956,0.10748368,0.0010147732,0.00026953715,0.000003309018,0.00013107725,0.10134359],"genre_scores_gemma":[0.9887719,0.0001019442,0.001830739,0.00062562624,0.00320125,0.0000030345523,4.645933e-7,0.000010634309,0.0054543912],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982641,0.00030395557,0.00016506646,0.00011970963,0.00064687064,0.0005003278],"domain_scores_gemma":[0.999048,0.00034724112,0.00017806128,0.00014025766,0.000116646544,0.00016982833],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0017462398,0.0001121033,0.00013489243,0.000038171915,0.0016788845,0.00051416626,0.0006684187,0.0000474626,0.00020944192],"category_scores_gemma":[0.00030131443,0.00007527758,0.00007275711,0.00028492504,0.0002655345,0.0002657561,0.0000628429,0.000416727,0.000062801075],"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":[0.00006231252,0.0003229918,0.44118464,0.000014053378,0.00024039486,0.00015089894,0.19928412,0.00018029498,0.004006242,0.032569356,0.059079196,0.2629055],"study_design_scores_gemma":[0.0015268157,0.00022404297,0.10245236,0.00019432204,0.00016575362,0.00019766539,0.12123373,0.0004407562,0.00022738171,0.0041490966,0.7683296,0.0008584592],"about_ca_topic_score_codex":0.00013688659,"about_ca_topic_score_gemma":0.0014811722,"teacher_disagreement_score":0.7092504,"about_ca_system_score_codex":0.00015231782,"about_ca_system_score_gemma":0.00017524466,"threshold_uncertainty_score":0.9996208},"labels":[],"label_agreement":null},{"id":"W2187181284","doi":"","title":"Re/Viewing Student Success in an Era of Accountability","year":2011,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Student achievement; Perspective (graphical); Success factors; Point (geometry); Academic achievement; Mathematics education; Student engagement; Psychology; Public relations; Political science; Pedagogy; Computer science; Business","score_opus":0.43951187835644734,"score_gpt":0.6218540625177319,"score_spread":0.18234218416128456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187181284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9589403,0.0028916572,0.00002003381,0.00009030776,0.0006935084,0.0006932929,0.000010337998,0.000027188938,0.036633346],"genre_scores_gemma":[0.9948953,0.004455287,0.00020957756,0.00011123104,0.0001712641,0.000036634763,0.0000033631616,0.000026413978,0.000090935384],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99549913,0.0008512745,0.0011781617,0.00048807074,0.0014547876,0.0005285483],"domain_scores_gemma":[0.99745935,0.000328671,0.00094472436,0.0005318214,0.00047061668,0.00026481674],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00557994,0.0002682207,0.0008576708,0.00046328898,0.00035666497,0.000877962,0.004921142,0.00014734465,0.018477198],"category_scores_gemma":[0.0002494475,0.00025250373,0.00018649615,0.0014419015,0.00038272224,0.0053443667,0.00096289045,0.00049924897,0.000009678111],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011368603,0.0009029322,0.9656951,0.00003540676,0.00006657579,0.000010410494,0.025317764,0.000005940748,0.0017964131,0.00024589803,0.0006811553,0.0051287212],"study_design_scores_gemma":[0.00045767723,0.000015784917,0.9840028,0.00024382112,0.000046124424,2.1750326e-7,0.010353466,0.0000045459315,0.0013462135,0.002377427,0.00085846346,0.0002934197],"about_ca_topic_score_codex":0.024574785,"about_ca_topic_score_gemma":0.011887947,"teacher_disagreement_score":0.036542412,"about_ca_system_score_codex":0.00022794971,"about_ca_system_score_gemma":0.000293689,"threshold_uncertainty_score":0.9999927},"labels":[],"label_agreement":null},{"id":"W2194885127","doi":"10.5206/cjsotl-rcacea.2015.3.2","title":"A Systematic Assessment of ‘None of the Above’ on Multiple Choice Tests in a First Year Psychology Classroom","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University; McMaster University","funders":"","keywords":"Psychology; Experimental psychology; Cognitive psychology; Quality (philosophy); Social psychology; Epistemology; Cognition","score_opus":0.0797850047565336,"score_gpt":0.40178674937091463,"score_spread":0.322001744614381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2194885127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992152,0.0005000302,0.00003923503,0.004094859,0.00038627678,0.0004285839,0.0000027948113,0.0000034855689,0.0023927328],"genre_scores_gemma":[0.99914163,0.000018070908,0.00019542208,0.00007597789,0.0000979102,0.000007681207,2.622847e-7,0.000009221425,0.00045381175],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971079,0.001837383,0.00034184914,0.00008993961,0.0003755336,0.00024738262],"domain_scores_gemma":[0.9958331,0.0032936048,0.00045075107,0.00017487546,0.00011071268,0.00013694324],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.013453142,0.000084488725,0.00023682116,0.00011468443,0.0015617585,0.00009651799,0.0006129905,0.00007135869,0.0000075199896],"category_scores_gemma":[0.010700512,0.000045622466,0.00009641222,0.00017020549,0.0002319394,0.00010459702,0.000024427569,0.0014591969,5.318438e-7],"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":[0.000022669408,0.000027839846,0.9662115,0.00015901634,0.00007487319,7.537476e-7,0.027812745,0.0010420149,0.000051943935,0.0040723854,0.000120277546,0.00040395974],"study_design_scores_gemma":[0.0014552058,0.00028351636,0.95094186,0.0035202524,0.00011600744,0.0000095567475,0.038130384,0.0005885288,0.000004708821,0.00165499,0.0031701943,0.00012480868],"about_ca_topic_score_codex":0.018445617,"about_ca_topic_score_gemma":0.15197964,"teacher_disagreement_score":0.13353401,"about_ca_system_score_codex":0.00014737672,"about_ca_system_score_gemma":0.00045344807,"threshold_uncertainty_score":0.9997381},"labels":[],"label_agreement":null},{"id":"W2197088744","doi":"","title":"Electronic Peer Assessment Tool","year":2008,"lang":"en","type":"article","venue":"Society for Information Technology & Teacher Education International Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science","score_opus":0.026709120625550482,"score_gpt":0.37287959423006173,"score_spread":0.34617047360451125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2197088744","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35696822,0.00010871957,0.07940181,0.12284874,0.0044399095,0.0023766046,0.000052084917,0.0012164692,0.43258744],"genre_scores_gemma":[0.9684737,0.00028659706,0.009638304,0.00081228145,0.0002860096,0.000569897,0.0003029541,0.000007847002,0.01962241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847364,0.000021787013,0.00035866408,0.00016447135,0.00064981135,0.00033164243],"domain_scores_gemma":[0.9978928,0.00004163631,0.0002552364,0.00016988449,0.0015957638,0.000044680153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064565305,0.0001310669,0.000122021585,0.00018743254,0.0007288182,0.00013472927,0.00062187895,0.0002529222,0.0009086663],"category_scores_gemma":[0.00021536673,0.00014385101,0.00018959474,0.00034335055,0.0003316309,0.0013840235,0.000060447546,0.00031738053,0.00010446271],"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":[0.0000063906286,0.00014907788,0.030960869,0.000005470956,0.00008550261,2.4661261e-8,0.013246169,0.0000015230404,0.000043896936,0.87235147,0.06812981,0.015019798],"study_design_scores_gemma":[0.0004889079,0.000044740977,0.012017011,0.00001133196,0.000020953392,0.0000032426658,0.05166042,0.0004611958,0.000054591186,0.017239679,0.91776687,0.00023107108],"about_ca_topic_score_codex":0.00009346019,"about_ca_topic_score_gemma":0.00002299734,"teacher_disagreement_score":0.8551118,"about_ca_system_score_codex":0.00071653316,"about_ca_system_score_gemma":0.0024963536,"threshold_uncertainty_score":0.99492586},"labels":[],"label_agreement":null},{"id":"W2206067169","doi":"10.47678/cjhe.v45i4.184831","title":"Framing Student Perspectives into the Higher Education Institutional Review Policy Process","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Framing (construction); CLARITY; Process (computing); Higher education; Public relations; Political science; Pedagogy; Sociology; Psychology; Computer science","score_opus":0.04157630342662869,"score_gpt":0.43192402969644056,"score_spread":0.39034772626981185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206067169","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2443243,0.3067066,0.000010274078,0.25760886,0.014600428,0.00084670034,0.0000021400356,0.000020355938,0.17588033],"genre_scores_gemma":[0.9670123,0.00097595935,0.00010962287,0.0031458598,0.004630449,0.000023994176,0.0000041134012,0.00000813848,0.024089573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987336,0.00016329535,0.00026542947,0.00011220403,0.0005117259,0.00021378695],"domain_scores_gemma":[0.9979581,0.00003061197,0.0002629002,0.000114843075,0.0011173348,0.0005161914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007135147,0.00009528212,0.00013184067,0.00022570754,0.000550906,0.00017870756,0.00045699542,0.000053635,0.0005469298],"category_scores_gemma":[0.0001609476,0.000073295756,0.00006221964,0.00059523166,0.00025055057,0.0005111294,0.000008376179,0.00019152746,0.000031001113],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070786823,0.00032621325,0.13204166,0.00009120918,0.000089198504,0.0000027351691,0.25481614,0.00001362796,0.0000032443943,0.36923325,0.23090726,0.01246838],"study_design_scores_gemma":[0.00009771344,0.000026400221,0.20342585,0.00034660654,0.000049369,0.000004138509,0.048550576,6.387912e-8,6.842925e-7,0.009197899,0.73820066,0.00010003548],"about_ca_topic_score_codex":0.017541321,"about_ca_topic_score_gemma":0.009823606,"teacher_disagreement_score":0.722688,"about_ca_system_score_codex":0.0015708706,"about_ca_system_score_gemma":0.038499884,"threshold_uncertainty_score":0.989001},"labels":[],"label_agreement":null},{"id":"W2206430552","doi":"10.82308/51495","title":"The effects of audio-taped feedback on ESL graduate student writing","year":2003,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Graduate students; Computer science; Higher education; Psychology; Medical education; Pedagogy; Mathematics education; Multimedia; Medicine; Political science","score_opus":0.029484367536438984,"score_gpt":0.3092915513043904,"score_spread":0.27980718376795144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206430552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7744705,0.0001781177,1.811412e-7,0.00011757479,0.0013079689,0.0007799504,0.000016590848,0.00012930494,0.22299978],"genre_scores_gemma":[0.9947682,0.0006998563,0.00017919339,0.00029828635,0.00008563307,0.000089578716,0.0000035024577,0.000060299684,0.003815429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942065,0.0015073742,0.00070726307,0.0006365018,0.0019077668,0.0010345808],"domain_scores_gemma":[0.9958586,0.002471604,0.00044287843,0.0005963803,0.0003221057,0.0003084126],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0036697916,0.0004128572,0.00048025863,0.00013755982,0.0039679604,0.00021622593,0.0010179862,0.00021943859,0.00009605494],"category_scores_gemma":[0.0025928672,0.00034047724,0.0003269859,0.00082692795,0.00038271653,0.00046932464,0.00018286516,0.0007451736,0.0002804149],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076362994,0.00057705335,0.004085719,0.00008326098,0.00029047162,0.00004005386,0.00042799476,0.000008890488,0.009593074,0.93889976,0.000055986642,0.04586138],"study_design_scores_gemma":[0.011975832,0.002545241,0.17414889,0.0015850862,0.0008384102,0.0000148606805,0.049120072,0.00001299707,0.14945441,0.099224195,0.50693953,0.004140499],"about_ca_topic_score_codex":0.00025227002,"about_ca_topic_score_gemma":0.00053561013,"teacher_disagreement_score":0.83967555,"about_ca_system_score_codex":0.00049778994,"about_ca_system_score_gemma":0.00006511647,"threshold_uncertainty_score":0.99990475},"labels":[],"label_agreement":null},{"id":"W2206649886","doi":"10.47678/cjhe.v45i4.184403","title":"The Challenge of Differing Perspectives Surrounding Grades in the Assessment Education of Pre Service Teachers","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bachelor; Mathematics education; Teacher education; Ranking (information retrieval); Higher education; Psychology; Pedagogy; Rank (graph theory); Rubric; Service (business); Philosophy of education; sort; Sociology; Computer science; Political science; Mathematics","score_opus":0.053751278267874125,"score_gpt":0.3906394212021311,"score_spread":0.33688814293425695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206649886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.958312,0.004521579,0.000003250926,0.019334823,0.0014530101,0.00017149109,5.963893e-7,0.0000013784293,0.016201908],"genre_scores_gemma":[0.9983557,0.00011353832,0.000097981516,0.000056407,0.0004197094,0.0000079770425,9.3273184e-7,0.000004854594,0.0009429198],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99891675,0.00029048193,0.00025189223,0.00006350312,0.0003252158,0.00015217793],"domain_scores_gemma":[0.9988953,0.00013444516,0.00032167786,0.00010667599,0.00040635353,0.00013553193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013550367,0.000059493952,0.00010618335,0.00014541249,0.00018647195,0.00007783524,0.00039113514,0.000038219798,0.000029135717],"category_scores_gemma":[0.00008236458,0.00004059091,0.000040309467,0.00032515632,0.00010907435,0.000248952,0.0000054191482,0.0001552822,4.1571425e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062675717,0.00018488805,0.3861763,0.000014400412,0.000031438114,3.369944e-7,0.5540179,0.000010302774,0.00003127211,0.05286308,0.003636611,0.003027231],"study_design_scores_gemma":[0.00008386457,0.000033424934,0.56713325,0.000060947743,0.000016269641,6.526278e-7,0.40910447,8.3981257e-7,0.000002698163,0.0022695998,0.021257084,0.000036903562],"about_ca_topic_score_codex":0.029408492,"about_ca_topic_score_gemma":0.07348268,"teacher_disagreement_score":0.18095694,"about_ca_system_score_codex":0.00061395444,"about_ca_system_score_gemma":0.0058164145,"threshold_uncertainty_score":0.9998197},"labels":[],"label_agreement":null},{"id":"W2228140964","doi":"10.1080/02671522.2015.1086015","title":"Predictability in high-stakes examinations: students’ perspectives on a perennial assessment dilemma<sup>*</sup>","year":2015,"lang":"en","type":"article","venue":"Research Papers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast; University of Oxford","keywords":"Dilemma; Certificate; Context (archaeology); Active listening; Irish; Pedagogy; Predictability; Relevance (law); Psychology; Quality (philosophy); Medical education; Engineering ethics; Public relations; Political science; Computer science; Medicine; Epistemology; Engineering","score_opus":0.0924787417886633,"score_gpt":0.4819874739115618,"score_spread":0.3895087321228985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228140964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9088344,0.000109135515,0.0000017992587,0.002341367,0.00029772863,0.0010925252,0.0000041987264,0.00003490034,0.08728397],"genre_scores_gemma":[0.9963167,0.0003204727,0.000355755,0.000028688468,0.0005063934,0.00057974836,0.00002455022,0.000013394207,0.0018543001],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940862,0.0019448176,0.0003054509,0.0005226819,0.0025562253,0.0005846326],"domain_scores_gemma":[0.99815345,0.0007582898,0.00005636649,0.00031039538,0.0004938803,0.00022761206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072142635,0.00013903377,0.00018844775,0.00062371534,0.00035081568,0.00028996164,0.0006154515,0.00013173943,0.00033552785],"category_scores_gemma":[0.0025205307,0.0001384133,0.00004078931,0.0012449413,0.00045239273,0.00039505312,0.000110039204,0.00058868254,0.000038314054],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043992422,0.002641999,0.7887654,0.000009997064,0.000010709277,0.0000016693516,0.17902437,0.000069696325,0.00001905955,0.02202815,0.0007749708,0.0066100387],"study_design_scores_gemma":[0.00048744638,0.00012121818,0.5611221,0.00004626414,0.0000023160067,6.69636e-8,0.43427315,0.00005856068,0.0000011604889,0.0008363239,0.0029647497,0.00008662038],"about_ca_topic_score_codex":0.008516969,"about_ca_topic_score_gemma":0.0039345818,"teacher_disagreement_score":0.2552488,"about_ca_system_score_codex":0.0037975365,"about_ca_system_score_gemma":0.002657207,"threshold_uncertainty_score":0.9980854},"labels":[],"label_agreement":null},{"id":"W2237938873","doi":"10.37119/ojs2015.v21i2.214","title":"Inquiring into the Assessment Education of Preservice Teachers: A Collaborative Self-Study of Teacher Educators","year":2015,"lang":"en","type":"article","venue":"in education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bachelor; Teacher education; Teacher preparation; Mathematics education; Pedagogy; Psychology","score_opus":0.03333096806200037,"score_gpt":0.42589355295932946,"score_spread":0.3925625848973291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237938873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9407106,0.0002821516,0.000002787647,0.0012618138,0.0012002954,0.0009919652,2.3389588e-7,0.000016602648,0.055533573],"genre_scores_gemma":[0.99760103,0.000030906423,0.0010301055,0.000036838082,0.00031962662,0.0002755872,0.0000045791044,0.000008587775,0.0006927376],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9981974,0.0006259964,0.00033197054,0.00018051421,0.000523419,0.00014073755],"domain_scores_gemma":[0.9987374,0.000116728064,0.00029299653,0.00024834502,0.0005356954,0.00006882681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001545891,0.00009463704,0.00015381236,0.00016154208,0.00011839309,0.000048344813,0.00038531105,0.00006171207,0.000027576743],"category_scores_gemma":[0.00021239655,0.00007974556,0.000022583376,0.0010576408,0.00010311874,0.00036144754,0.00005806633,0.00013538009,0.000004002997],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041291178,0.0031855556,0.4280107,0.0000073987435,0.000017767905,1.3752379e-8,0.5601816,0.0000067973415,0.000023699387,0.00235502,0.0016261041,0.0045812055],"study_design_scores_gemma":[0.00019911645,0.00006929768,0.27862662,0.00002845283,0.000024765277,3.5264737e-8,0.71194476,0.0000072547423,0.000018668832,0.00069999584,0.008318794,0.00006226202],"about_ca_topic_score_codex":0.021077191,"about_ca_topic_score_gemma":0.007989923,"teacher_disagreement_score":0.15176313,"about_ca_system_score_codex":0.0005707632,"about_ca_system_score_gemma":0.005707553,"threshold_uncertainty_score":0.9999292},"labels":[],"label_agreement":null},{"id":"W2241999475","doi":"","title":"Blending community and authentic assessment in a hybrid course","year":2007,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Course (navigation); Computer science; Engineering","score_opus":0.09098612383706327,"score_gpt":0.38366467255759934,"score_spread":0.29267854872053606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2241999475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.880871,0.0002940388,0.000027512444,0.010887356,0.0009997581,0.00063808495,0.0000042404245,0.000075370415,0.10620267],"genre_scores_gemma":[0.9731561,0.0007945821,0.00027897183,0.00057962665,0.0001896407,0.000053696964,0.000024332874,0.000025819538,0.024897259],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99641645,0.0010439006,0.0005424688,0.00047060955,0.0008639751,0.0006625672],"domain_scores_gemma":[0.9982945,0.0004497337,0.00060131366,0.00024178896,0.000110369954,0.000302318],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0035888378,0.0002760214,0.00036234007,0.00026038184,0.00091170735,0.00031551698,0.0002676275,0.00011948253,0.00034783396],"category_scores_gemma":[0.00007112964,0.0003077165,0.000034085024,0.00067780056,0.00026478348,0.00035282288,0.000106194515,0.0015190605,0.000016473776],"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":[0.00008811452,0.0005354153,0.79289335,0.00007305526,0.0000127139665,0.000007490604,0.0070264176,0.0000031259299,0.000037047117,0.17889406,0.00027292586,0.020156316],"study_design_scores_gemma":[0.0006514006,0.00024316207,0.94585395,0.00040213068,0.000015576432,0.000001218943,0.034352083,0.00007718274,0.0000068270037,0.0055554886,0.012521804,0.00031917862],"about_ca_topic_score_codex":0.0080770375,"about_ca_topic_score_gemma":0.025844706,"teacher_disagreement_score":0.17333856,"about_ca_system_score_codex":0.001032994,"about_ca_system_score_gemma":0.0009336637,"threshold_uncertainty_score":0.9999375},"labels":[],"label_agreement":null},{"id":"W2249312354","doi":"10.11575/prism/5279","title":"Developing Preservice Teachers' Assessment Literacy: A Problem-Based Learning Approach","year":2014,"lang":"en","type":"article","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Authentic assessment; Curriculum; Mathematics education; Pedagogy; Assessment for learning; Government (linguistics); Literacy; Educational assessment; Standardized test; Formative assessment; Psychology; Medical education; Medicine","score_opus":0.06303854882660766,"score_gpt":0.40843042952233605,"score_spread":0.3453918806957284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2249312354","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14892237,0.000018589079,0.017086567,0.0020550508,0.00011221491,0.0009760721,8.8210123e-7,0.000015038275,0.8308132],"genre_scores_gemma":[0.64148474,0.000003816908,0.3459503,0.00013207829,0.00017121814,0.00008453112,0.000029393941,0.000014924044,0.012129023],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979442,0.00052749546,0.00022836353,0.00039112277,0.0005079263,0.00040094534],"domain_scores_gemma":[0.9992805,0.00016336811,0.00014667862,0.00018502919,0.00011420951,0.000110199595],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025534302,0.00014153942,0.00020302583,0.00006134167,0.00074553123,0.0011930809,0.0009841335,0.00009346395,0.0011154918],"category_scores_gemma":[0.00008236952,0.00013462576,0.00004781307,0.00034755113,0.00006899819,0.0006139262,0.0002871049,0.00025734786,0.00016886652],"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":[0.000046188474,0.00056724506,0.3335878,0.0000579591,0.00013142417,0.0000044597546,0.15570089,0.0009960526,0.00030788986,0.013266412,0.0011855077,0.49414816],"study_design_scores_gemma":[0.0008933369,0.0000636892,0.016756559,0.00008253585,0.00003111048,2.2138431e-7,0.007473108,0.0045201103,0.000053974192,0.0002819026,0.9694874,0.00035599392],"about_ca_topic_score_codex":0.0007536225,"about_ca_topic_score_gemma":0.00028954606,"teacher_disagreement_score":0.96830195,"about_ca_system_score_codex":0.00017198731,"about_ca_system_score_gemma":0.0005078308,"threshold_uncertainty_score":0.9998438},"labels":[],"label_agreement":null},{"id":"W2255198894","doi":"10.20381/ruor-20086","title":"Implications of the multiple-use of large-scale assessments for the process of validation: A case study of the multiple-use of a Grade 9 mathematics assessment","year":2011,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Scale (ratio); Process (computing); Argument (complex analysis); Quality (philosophy); Perspective (graphical); Test (biology); Data collection; Computer science; Management science; Data science; Psychology; Mathematics education; Engineering; Mathematics; Artificial intelligence; Medicine; Statistics; Political science; Geography","score_opus":0.1975998779485343,"score_gpt":0.4601881434004951,"score_spread":0.2625882654519608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2255198894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99279636,0.000010829047,0.00039032326,0.00017365992,0.000117920026,0.0046712873,0.0005128722,0.000007695098,0.0013190426],"genre_scores_gemma":[0.9950502,0.000065385335,0.0019819678,0.0000016396739,0.000015992355,0.00003268978,0.00004637973,0.000019989075,0.002785791],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99601215,0.0007163087,0.0006377156,0.00031414072,0.0019842945,0.00033538768],"domain_scores_gemma":[0.991384,0.002881114,0.0018287543,0.0009550102,0.0028829784,0.00006808908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002229478,0.00019068691,0.0005857495,0.00030218196,0.000883676,0.000026561744,0.0018620881,0.0002049234,0.000071243776],"category_scores_gemma":[0.0007088065,0.00013827636,0.0003757765,0.0013289785,0.00078847964,0.00036115694,0.00033630405,0.0003751783,2.667022e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080961814,0.0070991474,0.81715417,0.0015301454,0.00088561623,0.000002374316,0.16118689,0.0000825182,0.002131137,0.008817037,0.0005400478,0.0004899783],"study_design_scores_gemma":[0.0015874351,0.00033188125,0.45130026,0.00026231603,0.00046636464,7.639726e-7,0.54293483,0.00084750605,0.0014323498,0.00034377223,0.0003590481,0.00013347116],"about_ca_topic_score_codex":0.007124819,"about_ca_topic_score_gemma":0.05770664,"teacher_disagreement_score":0.38174796,"about_ca_system_score_codex":0.00010677038,"about_ca_system_score_gemma":0.00089694094,"threshold_uncertainty_score":0.9994868},"labels":[],"label_agreement":null},{"id":"W2267422080","doi":"10.55016/ojs/ajer.v61i1.56028","title":"Assessment and Grading Practices in Outreach Schools","year":2015,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Grading (engineering); Outreach; Mathematics education; Psychology; Pedagogy; Medical education; Political science; Medicine; Engineering","score_opus":0.3218829329466501,"score_gpt":0.5831476598950716,"score_spread":0.26126472694842146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2267422080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7571533,0.00044626827,6.093708e-7,0.04088388,0.00024201378,0.00010325901,1.6081297e-7,2.3499422e-7,0.2011703],"genre_scores_gemma":[0.9849575,0.00036617726,0.00066571013,0.000039683266,0.0006067947,0.000007988902,0.0000010946881,0.000004984119,0.013350066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99756247,0.0006082803,0.00026201585,0.00011475597,0.0011793034,0.00027318718],"domain_scores_gemma":[0.9891502,0.009558967,0.00026407954,0.000071724615,0.0006627038,0.00029232816],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005856617,0.000053388725,0.00012015133,0.00035700438,0.00021683985,0.00024706507,0.00030711063,0.00004565509,0.0008512401],"category_scores_gemma":[0.016270274,0.000046718953,0.000026530775,0.00047549594,0.00013306882,0.00078747043,0.000056034598,0.0005004804,0.000044832723],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019417725,0.00019286158,0.9295257,0.0000033126423,0.000018500457,8.605701e-7,0.007038151,0.0000013746758,0.00003554781,0.05148883,0.011375084,0.00030038776],"study_design_scores_gemma":[0.00063039485,0.00014342078,0.8757168,0.00007485583,0.000011459486,0.000011043957,0.06878265,0.000013968016,0.0000038724093,0.008536125,0.04598739,0.00008803464],"about_ca_topic_score_codex":0.0070434674,"about_ca_topic_score_gemma":0.00914918,"teacher_disagreement_score":0.22780423,"about_ca_system_score_codex":0.00046483096,"about_ca_system_score_gemma":0.0034750355,"threshold_uncertainty_score":0.9995687},"labels":[],"label_agreement":null},{"id":"W2269884609","doi":"10.5539/hes.v6n1p136","title":"An Examination of Using Self-, Peer-, and Teacher-Assessment in Higher Education: A Case Study in Teacher Education","year":2016,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Peer assessment; Psychology; Teacher education; Self-assessment; Medical education; Peer evaluation; Presentation (obstetrics); Mathematics education; Pedagogy; Higher education; Medicine","score_opus":0.11012340218764399,"score_gpt":0.4709792748283706,"score_spread":0.3608558726407266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2269884609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98223233,0.0011974709,0.0000014960792,0.0028852643,0.0019761412,0.00082865165,8.6100505e-7,0.00003990259,0.010837878],"genre_scores_gemma":[0.9729362,0.00013555636,0.0008114978,0.000069586866,0.00061788363,0.00036007332,0.000003449684,0.000017907596,0.025047855],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975953,0.0007299855,0.00048162046,0.00042948083,0.0005164836,0.00024711937],"domain_scores_gemma":[0.9986337,0.00014430632,0.00026012998,0.00025545337,0.00061806804,0.00008835687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014439241,0.0001970271,0.00029900752,0.00043723054,0.00025072688,0.000072355106,0.00015638843,0.000094982104,0.0003700326],"category_scores_gemma":[0.000031909014,0.00016591088,0.000028452296,0.0006649021,0.00015414388,0.0007429669,0.00005691106,0.00012494288,0.0000038147177],"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":[0.0000064762303,0.008693654,0.9069144,0.000029473282,0.000040650208,0.000002381146,0.058150083,4.5970495e-7,0.00010221277,0.0054792664,0.0006142368,0.019966695],"study_design_scores_gemma":[0.00039943928,0.000064317006,0.7176674,0.0000775542,0.000043381107,0.0000025250238,0.2772391,0.0000012838965,0.0000025433833,0.0002524506,0.0040921583,0.00015783178],"about_ca_topic_score_codex":0.0037350287,"about_ca_topic_score_gemma":0.0019293427,"teacher_disagreement_score":0.21908903,"about_ca_system_score_codex":0.0010025828,"about_ca_system_score_gemma":0.0015356628,"threshold_uncertainty_score":0.676565},"labels":[],"label_agreement":null},{"id":"W2272782403","doi":"","title":"Process-Oriented Assessment in Mathematics Education","year":2009,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Process (computing); Mathematics education; Computer science; Mathematics; Programming language","score_opus":0.06589933623880866,"score_gpt":0.378212484093377,"score_spread":0.3123131478545683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2272782403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53157693,0.0003341986,0.00002448566,0.051348265,0.001751126,0.0014766837,0.0000041474714,0.00015494878,0.41332924],"genre_scores_gemma":[0.937877,0.0006769073,0.00075464067,0.0012530896,0.00031496576,0.0001610676,0.000042939995,0.00002344715,0.05889593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966034,0.00043522337,0.0006360495,0.0006288743,0.0011197735,0.00057667284],"domain_scores_gemma":[0.99832124,0.00012708339,0.0007969905,0.0002510558,0.00024233114,0.0002613162],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010654293,0.0003104478,0.00037743768,0.0003142597,0.00045768786,0.00026520193,0.00028459646,0.00017225905,0.00053039193],"category_scores_gemma":[0.0000900047,0.00033607922,0.000042760435,0.0011914718,0.000120148325,0.0004643257,0.00003197937,0.00089546817,0.000039720395],"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":[0.000046097448,0.0014618353,0.42652845,0.00009139436,0.000007432092,0.0000018219692,0.008115193,0.000011976573,0.000043923177,0.5351731,0.00078446843,0.027734263],"study_design_scores_gemma":[0.0005756377,0.0002872887,0.91254663,0.0006689176,0.000013874984,6.945779e-7,0.0320134,0.0001292414,0.000009346401,0.029121537,0.024201397,0.00043205323],"about_ca_topic_score_codex":0.0013427762,"about_ca_topic_score_gemma":0.0032412582,"teacher_disagreement_score":0.5060516,"about_ca_system_score_codex":0.0012469111,"about_ca_system_score_gemma":0.0028631901,"threshold_uncertainty_score":0.9999091},"labels":[],"label_agreement":null},{"id":"W2274734137","doi":"10.2304/pfie.2012.10.4.447","title":"Building Teacher Capacity within the Evolving Assessment Culture in Canadian Education","year":2012,"lang":"en","type":"article","venue":"Policy Futures in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; Queen's University","funders":"","keywords":"Formative assessment; Accountability; Professional development; Faculty development; Educational assessment; Assessment for learning; Pedagogy; Scale (ratio); Focus group; Summative assessment; Best practice; Professional learning community; Psychology; Teacher education; Sociology; Mathematics education; Political science","score_opus":0.024756394277784217,"score_gpt":0.41317470547846463,"score_spread":0.38841831120068043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274734137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8525527,0.00077863905,0.0000042825973,0.010422222,0.0029142932,0.00045301882,0.0000012055898,0.000017821483,0.13285579],"genre_scores_gemma":[0.99061894,0.00005776648,0.0016895944,0.0010634721,0.004999181,0.00011027072,0.000008588065,0.000009950403,0.0014422324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99852467,0.00032490902,0.00020158503,0.00015128028,0.00028290148,0.0005146424],"domain_scores_gemma":[0.99940443,0.000047889986,0.00010300308,0.00017126239,0.00006713621,0.00020625786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015048026,0.00011247943,0.00009470909,0.0003351692,0.00044327788,0.00014486756,0.00030893067,0.00012784799,0.00011205171],"category_scores_gemma":[0.00042682016,0.00009229417,0.000031607924,0.0007661827,0.000082828265,0.000521519,0.000021913524,0.0003357564,0.000010863566],"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":[0.0000010162966,0.00019466593,0.60421216,0.0000050131803,0.000003795398,2.4031731e-8,0.14606255,0.0000061721,0.00005081499,0.23551309,0.008116763,0.0058339033],"study_design_scores_gemma":[0.000056270565,0.0000034955424,0.84661764,0.000033236993,0.000005955213,4.787395e-7,0.09678299,0.000017269442,0.000008421809,0.00429515,0.05206035,0.000118752374],"about_ca_topic_score_codex":0.86907184,"about_ca_topic_score_gemma":0.85216296,"teacher_disagreement_score":0.24240544,"about_ca_system_score_codex":0.0028746456,"about_ca_system_score_gemma":0.005300363,"threshold_uncertainty_score":0.94026166},"labels":[],"label_agreement":null},{"id":"W2283163237","doi":"10.14288/1.0102214","title":"Teacher evaluation in British Columbia as perceived by teachers, a survey study","year":2011,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical education; Psychology; Pedagogy; Mathematics education; Medicine","score_opus":0.03735594129290467,"score_gpt":0.26701512243704506,"score_spread":0.22965918114414038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2283163237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97824425,0.00010191557,0.000003905641,0.00001971706,0.00015939916,0.0011692368,0.00006496722,0.00006798807,0.020168623],"genre_scores_gemma":[0.98804003,0.00011067606,0.00005355509,0.000021871252,0.000030580657,0.0000044608523,0.00004541048,0.000016465732,0.011676923],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966566,0.0012397253,0.000205073,0.0005424729,0.00094596273,0.00041015807],"domain_scores_gemma":[0.9990244,0.00007880823,0.000162235,0.00022598823,0.00034654918,0.00016203737],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029586738,0.000051785486,0.00032922433,0.00003994921,0.00062032935,0.0004767787,0.0006212256,0.00018341416,0.004911275],"category_scores_gemma":[0.00026361505,0.000253465,0.000097030264,0.0005792045,0.00040644308,0.00062271254,0.00013258052,0.00023141672,0.000049003003],"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":[0.0000064193455,0.0010423654,0.8410982,0.0000034148266,0.000045637003,0.000052223022,0.025081703,1.0021458e-7,0.0000108503245,7.412661e-8,0.017846161,0.11481288],"study_design_scores_gemma":[0.0019197456,0.00014715048,0.8581463,0.00005341213,0.00006093017,0.000002315211,0.1391219,0.000014012919,9.988549e-9,0.00008621204,0.00021267368,0.00023531777],"about_ca_topic_score_codex":0.9943962,"about_ca_topic_score_gemma":0.99950844,"teacher_disagreement_score":0.11457757,"about_ca_system_score_codex":0.00034364907,"about_ca_system_score_gemma":0.0003112153,"threshold_uncertainty_score":0.9999918},"labels":[],"label_agreement":null},{"id":"W2288795982","doi":"10.18806/tesl.v32i0.1215","title":"Building Teachers’ Assessment Capacity for Supporting English Language Learners Through the Implementation of the STEP Language Assessment in Ontario K-12 Schools","year":2016,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ell; Christian ministry; Psychology; Mathematics education; Language proficiency; Pedagogy; English language; Sociology; Teaching method; Political science","score_opus":0.029337185190978634,"score_gpt":0.3732268630508298,"score_spread":0.3438896778598512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288795982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99096864,0.00010249264,0.0010394531,0.00404298,0.0007461091,0.0006055205,0.00001901446,0.000011471593,0.0024643294],"genre_scores_gemma":[0.99371135,0.0000068452146,0.004364333,0.0010538531,0.00030854953,0.000028304028,0.0000018936624,0.000012771605,0.0005121082],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99748963,0.00035475666,0.00048439947,0.00016726129,0.0009901541,0.00051379367],"domain_scores_gemma":[0.998742,0.00033367096,0.0005439514,0.00017550543,0.00012049492,0.000084422],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025380962,0.00013557245,0.0001964812,0.000039164042,0.00064144924,0.00014176134,0.0005462321,0.000050633204,0.0025405695],"category_scores_gemma":[0.0002159222,0.0000755796,0.00011255035,0.0001530012,0.00008935234,0.00037018396,0.00007149936,0.00053784257,1.6821666e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013879721,0.00006664889,0.72655934,0.000011431411,0.00016637212,0.000012698755,0.22631237,0.000021342506,0.0045311316,0.009266588,0.01431238,0.018725803],"study_design_scores_gemma":[0.0015738321,0.000055370663,0.38315907,0.00008653069,0.00006001389,0.0000025126758,0.5854694,0.0000058174196,0.00039461197,0.00034515583,0.028651794,0.00019585942],"about_ca_topic_score_codex":0.92032933,"about_ca_topic_score_gemma":0.9936873,"teacher_disagreement_score":0.35915706,"about_ca_system_score_codex":0.0033221522,"about_ca_system_score_gemma":0.0052038576,"threshold_uncertainty_score":0.99837124},"labels":[],"label_agreement":null},{"id":"W2289974468","doi":"10.18806/tesl.v32i0.1220","title":"PBLA: Moving Toward Sustainability","year":2016,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Portfolio; Sustainability; Political science; Humanities; Sociology; Business; Art; Accounting","score_opus":0.019074220604149927,"score_gpt":0.31347581332822944,"score_spread":0.2944015927240795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289974468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74823415,0.00497487,0.0015525222,0.17802258,0.004249681,0.0004758615,0.000012193384,0.00012331177,0.06235484],"genre_scores_gemma":[0.99199456,0.00005560285,0.00007857994,0.003509298,0.0007279308,0.000001895936,1.1487626e-7,0.000006057308,0.0036259315],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984356,0.00012250806,0.00017436522,0.00010928651,0.0007253579,0.00043287757],"domain_scores_gemma":[0.99909866,0.00017940473,0.00009105068,0.000087355074,0.00028884437,0.00025467447],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008751637,0.00007436514,0.000106917665,0.000034083827,0.00062881544,0.000103775536,0.0003101431,0.000036652033,0.01582202],"category_scores_gemma":[0.0006668881,0.000050191626,0.00004785367,0.00013201336,0.00010963421,0.00023399088,0.000039591116,0.00012780949,0.0000052945616],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057057783,0.00009150369,0.24027541,0.000020599222,0.0001254204,0.0003894426,0.012666415,0.000004215071,0.00035065354,0.035051435,0.6109121,0.10005576],"study_design_scores_gemma":[0.0006057091,0.0000387559,0.13532217,0.000028661394,0.00001958355,0.000011974796,0.02058259,0.000002325548,0.00003759357,0.01054838,0.8325412,0.00026104663],"about_ca_topic_score_codex":0.32335782,"about_ca_topic_score_gemma":0.480207,"teacher_disagreement_score":0.24376045,"about_ca_system_score_codex":0.0020313028,"about_ca_system_score_gemma":0.005002205,"threshold_uncertainty_score":0.9850777},"labels":[],"label_agreement":null},{"id":"W2291984861","doi":"10.19173/irrodl.v17i2.2221","title":"Learners’ Interpersonal Beliefs and Generated Feedback in an Online Role-Playing Peer- Feedback Activity: An Exploratory Study","year":2016,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Interpersonal communication; Psychology; Computer-mediated communication; Perception; Constructive; Quality (philosophy); Exploratory research; Interpersonal relationship; Social psychology; Mathematics education; Computer science; The Internet; World Wide Web","score_opus":0.1796078959938181,"score_gpt":0.4821766519664574,"score_spread":0.3025687559726393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291984861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874967,0.001836353,0.000014274812,0.008392207,0.000061986764,0.00080967386,0.000034644567,0.000012883782,0.0013413075],"genre_scores_gemma":[0.9881794,0.010935534,0.00004417995,0.0000792252,0.00012222886,0.0000596211,0.000067662586,0.00001186248,0.0005002876],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99539834,0.0023476025,0.00035297294,0.00040437726,0.0011325554,0.0003641785],"domain_scores_gemma":[0.99839985,0.0006683334,0.0001447958,0.00017763332,0.0004582621,0.00015111869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010195979,0.00013850872,0.00031348126,0.00019242842,0.00036978867,0.00036339214,0.001075914,0.000058749454,0.0002307208],"category_scores_gemma":[0.0015083976,0.00009234093,0.000029097024,0.00057192065,0.00039505362,0.0011100481,0.0007402292,0.00058056746,0.000007485775],"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":[0.0003469582,0.0010110022,0.8765448,0.000102603604,0.00005838776,0.000020220234,0.016344652,0.000008680004,0.0015488392,0.001610221,0.0002271135,0.102176525],"study_design_scores_gemma":[0.0039392593,0.00089312973,0.5976384,0.0060729347,0.000020770427,0.0000040707364,0.37283126,0.001134727,0.000039421007,0.00047545772,0.016551392,0.0003991508],"about_ca_topic_score_codex":0.0022995498,"about_ca_topic_score_gemma":0.007011141,"teacher_disagreement_score":0.35648662,"about_ca_system_score_codex":0.00022136372,"about_ca_system_score_gemma":0.00025609363,"threshold_uncertainty_score":0.39123812},"labels":[],"label_agreement":null},{"id":"W2295570895","doi":"10.18192/olbiwp.v4i0.1105","title":"Digital Documentation: Using digital technologies to promote language assessment for the 21st century","year":2012,"lang":"en","type":"article","venue":"OLBI Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Documentation; Curriculum; Computer science; Process (computing); Language acquisition; Digital learning; Multimedia; Mathematics education; Pedagogy; Psychology","score_opus":0.02947728125630048,"score_gpt":0.38375803982468853,"score_spread":0.35428075856838803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295570895","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76862204,0.004030952,0.04383372,0.024826001,0.0071893944,0.0032091187,0.00010434857,0.0005084499,0.14767598],"genre_scores_gemma":[0.99404293,0.00013095688,0.0034620645,0.000059132883,0.00095029676,0.000016661506,0.0000034664372,0.000011615418,0.0013228643],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9987818,0.00001962887,0.00018047854,0.00009710424,0.00047928392,0.000441705],"domain_scores_gemma":[0.99948907,0.00010825346,0.00011975345,0.00010094047,0.00007523075,0.00010675119],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00051729404,0.00010185003,0.00010197274,0.00006335221,0.0009474924,0.0016529461,0.00035492316,0.0000518798,0.00014011867],"category_scores_gemma":[0.00010317318,0.00006885165,0.00009614225,0.00020641144,0.00009400919,0.0016631838,0.000076046934,0.00016216766,0.00002413078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003477909,0.00027545355,0.08755724,0.000009868553,0.00020349272,0.0000072225134,0.036782924,0.000018740573,0.0006786566,0.010558465,0.0025584637,0.8613147],"study_design_scores_gemma":[0.0008434365,0.00014761822,0.008657016,0.00006337373,0.00008894134,0.00004333517,0.5252608,0.00006514309,0.00019147842,0.0010253114,0.46319994,0.00041361467],"about_ca_topic_score_codex":0.000009089911,"about_ca_topic_score_gemma":0.0000073039514,"teacher_disagreement_score":0.86090106,"about_ca_system_score_codex":0.00021991215,"about_ca_system_score_gemma":0.000092565446,"threshold_uncertainty_score":0.99938345},"labels":[],"label_agreement":null},{"id":"W2298211336","doi":"10.1057/9781137440068_10","title":"Using Screen Capture Software to Improve the Value of Feedback on Academic Assignments in Teacher Education","year":2015,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Cursor (databases); Computer science; Software; Context (archaeology); Multimedia; Value (mathematics); Focus (optics); Component (thermodynamics); Audio feedback; Human–computer interaction; Engineering; Artificial intelligence; Operating system","score_opus":0.06286936481616026,"score_gpt":0.35525782345666784,"score_spread":0.29238845864050755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298211336","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005134438,0.00056879857,0.000058931004,0.0002357624,0.0008978897,0.0019145549,0.00007117765,0.0000432959,0.99107516],"genre_scores_gemma":[0.9523236,0.00003541003,0.00046946353,0.0003727088,0.0008574572,0.000038677746,0.000028140077,0.0000734775,0.04580102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99702007,0.0001713469,0.0005373826,0.00053569855,0.0012559188,0.00047956454],"domain_scores_gemma":[0.9984827,0.00014554294,0.00045918027,0.0004847446,0.00020098354,0.00022682517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010708626,0.0004351835,0.00050489587,0.00028062268,0.0002107332,0.00005891823,0.0008619436,0.0006948442,0.00022316663],"category_scores_gemma":[0.00014376894,0.00034987612,0.00017242826,0.00006707073,0.0002683337,0.0000025572738,0.00022196908,0.00082273036,0.00008290887],"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":[0.00014241617,0.0000069250614,0.011916693,0.000045293513,0.00015794006,0.000005479538,0.022355743,0.000028086537,0.0004003355,0.922796,0.00081248494,0.041332565],"study_design_scores_gemma":[0.0011132901,0.0002509898,0.010955798,0.0013335019,0.0003106847,0.0000018590302,0.009626568,0.000024066965,0.000099423356,0.95926625,0.015604835,0.0014127521],"about_ca_topic_score_codex":0.0028820455,"about_ca_topic_score_gemma":0.00088166713,"teacher_disagreement_score":0.9471892,"about_ca_system_score_codex":0.0006944367,"about_ca_system_score_gemma":0.0008998086,"threshold_uncertainty_score":0.99989533},"labels":[],"label_agreement":null},{"id":"W2308497147","doi":"10.11575/prism/5282","title":"Exploring New Frontiers in Self and Peer Assessment","year":2014,"lang":"en","type":"article","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Literacy; Pedagogy; Peer assessment; Mathematics education; Psychology; Sociology; Public relations; Political science","score_opus":0.1448085639772032,"score_gpt":0.3969174249054853,"score_spread":0.2521088609282821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2308497147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6975553,0.000017818287,0.00023920066,0.0021261242,0.0004292144,0.0002414513,3.304013e-7,0.0000024952528,0.29938808],"genre_scores_gemma":[0.92098594,0.000099375415,0.06312556,0.000046898884,0.00024292721,0.000016928734,0.000002032179,0.0000068589566,0.015473508],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991516,0.00008396423,0.000102963524,0.0001828245,0.0002871079,0.00019152962],"domain_scores_gemma":[0.9997238,0.00004206148,0.0000330669,0.000082023485,0.000020493457,0.00009856492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010374901,0.00006108383,0.00012022325,0.000046571466,0.00014646821,0.00034682243,0.00028098613,0.000029977706,0.0005033113],"category_scores_gemma":[0.00003739692,0.000060106813,0.000014008541,0.00013742533,0.00003264099,0.0005990776,0.0001278792,0.00007296576,0.00004247443],"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":[0.000008110723,0.00005876597,0.60819286,0.0000016397378,0.000019361732,0.0000026059645,0.054674547,0.0000021680357,0.000025522586,0.0012898537,0.0062258206,0.32949877],"study_design_scores_gemma":[0.0006598189,0.000028871907,0.20041496,0.000016109125,0.000011542652,9.377938e-8,0.02188142,0.00010239941,0.000021961645,0.0003591333,0.7763641,0.00013962043],"about_ca_topic_score_codex":0.0011246585,"about_ca_topic_score_gemma":0.0012465406,"teacher_disagreement_score":0.77013826,"about_ca_system_score_codex":0.000067244495,"about_ca_system_score_gemma":0.00011315716,"threshold_uncertainty_score":0.55109054},"labels":[],"label_agreement":null},{"id":"W2312774039","doi":"10.18192/olbiwp.v4i0.1106","title":"Multidimensionality of assessment in the Common European Framework of Reference for languages (CEFR)","year":2012,"lang":"en","type":"article","venue":"OLBI Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Perspective (graphical); Context (archaeology); Process (computing); Raising (metalworking); Domain (mathematical analysis); Computer science; Psychology; Linguistics; Artificial intelligence; Geography; Engineering","score_opus":0.07346238474137637,"score_gpt":0.4446475901687345,"score_spread":0.3711852054273581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312774039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94566244,0.0003219505,0.0006517015,0.0012719159,0.00025482217,0.00017984214,0.000009715556,0.0000046578566,0.05164295],"genre_scores_gemma":[0.9930778,0.00010062018,0.0063469056,0.00007403086,0.00030262175,0.0000021000292,0.0000020515677,0.000004153727,0.00008969728],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998485,0.0005977387,0.00025851032,0.000050173432,0.0004151331,0.00019339242],"domain_scores_gemma":[0.9989441,0.0005893611,0.00023572319,0.00009696752,0.00008734377,0.000046516125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042317715,0.000053691594,0.00013185198,0.000035737186,0.00016921875,0.000023428955,0.00030105168,0.000036724767,0.000111168556],"category_scores_gemma":[0.00016877755,0.00003542975,0.000059945054,0.00011403099,0.00009910847,0.00012703928,0.000033213655,0.00024445163,0.0000018436201],"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":[0.000032184198,0.00046942048,0.8704771,0.000018143399,0.000033779776,0.0000026650632,0.032102123,0.000009093084,0.0007604516,0.08798231,0.0022885827,0.0058241906],"study_design_scores_gemma":[0.00030135454,0.000056228673,0.9613544,0.00007739876,0.000019482291,0.0000019185234,0.027114077,0.000007633872,0.00005623266,0.0012220058,0.009725062,0.000064224245],"about_ca_topic_score_codex":0.0001532701,"about_ca_topic_score_gemma":0.00011521721,"teacher_disagreement_score":0.09087733,"about_ca_system_score_codex":0.00003568338,"about_ca_system_score_gemma":0.000056366327,"threshold_uncertainty_score":0.14666559},"labels":[],"label_agreement":null},{"id":"W2316879809","doi":"10.15405/futureacademy/ejsbs(2301-2218).2012.1.8","title":"The Enabling Constraints of Building an Assessment Pedagogy: Engaging Pre-service Teachers in a Professional Exploration of Current Conceptions of Classroom Assessment","year":2012,"lang":"en","type":"article","venue":"The European Journal of Social & Behavioural Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Summative assessment; Formative assessment; Context (archaeology); Psychology; Pedagogy; Class (philosophy); Professional development; Assessment for learning; Thematic analysis; Mathematics education; Sociology; Qualitative research; Computer science","score_opus":0.1823104768364378,"score_gpt":0.4975260007389156,"score_spread":0.3152155239024778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316879809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945696,0.0002587112,0.00060593267,0.0013341001,0.0012524788,0.00026727008,0.0000047589774,0.0000062177364,0.0017009521],"genre_scores_gemma":[0.9985647,0.00011575892,0.00084417267,0.000012192963,0.0004282013,0.000003574543,0.0000011575596,0.0000075185585,0.00002268505],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940105,0.0032668808,0.0008863881,0.00011993457,0.0013397812,0.00037653567],"domain_scores_gemma":[0.9975069,0.00040644364,0.001528114,0.000089792855,0.00037268392,0.000096027055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01660232,0.00012372792,0.00026611757,0.0001229148,0.001298227,0.0000775565,0.00093574263,0.000030327246,0.00004236346],"category_scores_gemma":[0.000114655355,0.000076234915,0.00012872185,0.00062097196,0.0016731748,0.0013166679,0.00012936883,0.00048461233,3.4958842e-7],"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":[0.000026470454,0.0006043939,0.6438816,0.000013198669,0.000033148426,9.1247244e-7,0.26038384,0.00011342983,0.010778846,0.021513704,0.0000505517,0.06259985],"study_design_scores_gemma":[0.0003849149,0.00013152769,0.7065679,0.00014536842,0.00006127242,9.528827e-7,0.2919873,0.000037348123,0.0001024292,0.00028469454,0.00020592494,0.00009037944],"about_ca_topic_score_codex":0.00020981191,"about_ca_topic_score_gemma":0.00027452564,"teacher_disagreement_score":0.06268626,"about_ca_system_score_codex":0.00014710816,"about_ca_system_score_gemma":0.00072783005,"threshold_uncertainty_score":0.9985044},"labels":[],"label_agreement":null},{"id":"W2318621088","doi":"10.1515/cercles-2014-0009","title":"Investigating language assessment literacy: Collaboration between assessment specialists and Canadian university admissions officers","year":2014,"lang":"en","type":"article","venue":"Language Learning in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Test (biology); Psychology; Language assessment; Literacy; Medical education; Diversity (politics); Language proficiency; Pedagogy; Applied psychology; Sociology; Medicine","score_opus":0.017945070602510656,"score_gpt":0.3650585029343927,"score_spread":0.347113432331882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318621088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89916795,0.00004941629,0.000015825628,0.0077871443,0.0004651335,0.000241478,0.00000421076,0.0000682373,0.092200585],"genre_scores_gemma":[0.97928756,0.000013579777,0.0029285273,0.00033461346,0.0008916664,0.0000059782687,0.0001422322,0.000012443042,0.016383365],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983748,0.0006389482,0.00016120171,0.00025664203,0.00029195796,0.0002764379],"domain_scores_gemma":[0.9991,0.00022102066,0.00013282934,0.00011867148,0.00008488597,0.00034255668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075791794,0.000112063506,0.00014305733,0.00024838082,0.0005663913,0.00024750104,0.00015221248,0.00011036944,0.00060477504],"category_scores_gemma":[0.00019494894,0.00013049973,0.000021184847,0.00058161333,0.00006449571,0.00037329897,0.000032710937,0.00030510046,0.000008909798],"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":[0.0000014033611,0.000030827647,0.8917998,0.000014256147,0.000010006032,0.0000023267417,0.07616906,0.000028858154,0.00028070985,0.015453118,0.0004749319,0.015734714],"study_design_scores_gemma":[0.0001979963,0.000020471702,0.8444734,0.000056198845,0.00001819299,9.3676256e-8,0.05362011,0.00006836411,0.000004943682,0.000037398568,0.10135838,0.00014441693],"about_ca_topic_score_codex":0.1105537,"about_ca_topic_score_gemma":0.08602412,"teacher_disagreement_score":0.10088345,"about_ca_system_score_codex":0.00086145836,"about_ca_system_score_gemma":0.0022345807,"threshold_uncertainty_score":0.9306536},"labels":[],"label_agreement":null},{"id":"W2326599554","doi":"10.3138/cmlr.2802","title":"Putting Students at the Centre of Classroom L2 Writing Assessment","year":2016,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Assessment for learning; Writing assessment; Mathematics education; Pedagogy; Psychology","score_opus":0.017451156989710875,"score_gpt":0.3097419731982567,"score_spread":0.2922908162085458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326599554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9411009,0.029509945,0.00007309612,0.0074344203,0.00027213886,0.00093068136,0.0002671401,0.00006695809,0.02034471],"genre_scores_gemma":[0.9778125,0.010500121,0.0005347765,0.00064571085,0.00035045468,0.000037826896,0.00004059315,0.000048720503,0.01002929],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.997143,0.0005142175,0.0005081159,0.00042013245,0.00034806493,0.0010664698],"domain_scores_gemma":[0.9976587,0.0006558143,0.00029060876,0.00051132846,0.0002099434,0.00067359855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018564129,0.00026665468,0.0004890958,0.00013377579,0.0006543593,0.00009390651,0.0009660757,0.000111617905,0.000869309],"category_scores_gemma":[0.0007307691,0.00018126678,0.00021221647,0.00036595057,0.0004564279,0.00019635836,0.000142565,0.00016360045,0.000040070452],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009781248,0.000088341425,0.52560395,0.0018426209,0.00040060986,0.0008303711,0.10007378,0.000002089217,0.013391835,0.008326164,0.010169298,0.33926114],"study_design_scores_gemma":[0.0019963395,0.00012935912,0.43472904,0.027462924,0.00080856076,0.000116963034,0.082249716,0.00011980598,0.00027701983,0.0018535913,0.4482879,0.0019687817],"about_ca_topic_score_codex":0.14388548,"about_ca_topic_score_gemma":0.8485536,"teacher_disagreement_score":0.7046681,"about_ca_system_score_codex":0.0015261696,"about_ca_system_score_gemma":0.00037141275,"threshold_uncertainty_score":0.95183235},"labels":[],"label_agreement":null},{"id":"W2333528754","doi":"10.2304/elea.2011.8.4.296","title":"‘We've Spent too Much Money to Go Back Now’: Credit-Crunched Literacy and a Future for Learning","year":2011,"lang":"en","type":"article","venue":"E-Learning and Digital Media","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Literacy; Scholarship; Discipline; Diversity (politics); Intervention (counseling); Information literacy; Sociology; Pedagogy; Public relations; Mathematics education; Engineering ethics; Psychology; Political science; Social science; Engineering","score_opus":0.02779370566600818,"score_gpt":0.3081507892681815,"score_spread":0.2803570836021733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333528754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7897162,0.0014784515,0.0001610548,0.0031541854,0.0012623299,0.0006666178,0.000016536196,0.0001898019,0.20335484],"genre_scores_gemma":[0.95480675,0.00093834905,0.0029135668,0.00017288046,0.0023495478,0.000037173813,0.000047941725,0.000036750305,0.038697038],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985524,0.00006192498,0.00021002704,0.00038150087,0.000341878,0.00045227143],"domain_scores_gemma":[0.999016,0.0003391271,0.00009646034,0.00008047111,0.00008756476,0.000380381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032800404,0.00019341911,0.00024801283,0.00007439906,0.00044351025,0.0006265035,0.00015450013,0.00012174796,0.00031328542],"category_scores_gemma":[0.0005120641,0.00017615069,0.0000684378,0.0001738879,0.00012385452,0.0006260789,0.0001299476,0.00026034238,0.00024757776],"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":[0.00033072324,0.0001755814,0.17722829,0.00006588254,0.0000963338,0.000019352294,0.6040273,0.0000013667646,0.000093754876,0.0035644674,0.028451925,0.18594503],"study_design_scores_gemma":[0.00072161324,0.00034291294,0.016920475,0.000053344098,0.000025626898,0.0000020500183,0.03939361,0.000038488357,0.000019945921,0.0007312723,0.94141734,0.00033333545],"about_ca_topic_score_codex":0.000047652604,"about_ca_topic_score_gemma":0.00004425947,"teacher_disagreement_score":0.9129654,"about_ca_system_score_codex":0.000031402633,"about_ca_system_score_gemma":0.000049495295,"threshold_uncertainty_score":0.7183217},"labels":[],"label_agreement":null},{"id":"W2336837379","doi":"10.55016/ojs/jet.v42i1.52475","title":"Equity in Multicultural Student Assessment","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Equity (law); Multiculturalism; Multicultural education; Psychology; Pedagogy; Mathematics education; Political science","score_opus":0.07106421306515492,"score_gpt":0.513175145370691,"score_spread":0.44211093230553605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336837379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85670155,0.00011654054,0.000016836915,0.013551226,0.0025751633,0.00012414374,8.956594e-7,0.0000034665572,0.12691018],"genre_scores_gemma":[0.98325604,0.00007544109,0.007693833,0.000196557,0.0041447086,0.0000040561476,0.0000012659262,0.000004281076,0.004623841],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99831814,0.00015468133,0.00038054472,0.00009223569,0.0008355044,0.00021891999],"domain_scores_gemma":[0.9987845,0.00026414648,0.00028039012,0.00006664715,0.00048842584,0.00011591888],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013751274,0.00007449891,0.00014846868,0.00011403935,0.0002220671,0.00011120599,0.0003899421,0.00004549683,0.0014518562],"category_scores_gemma":[0.00020746875,0.000058975067,0.000080440695,0.00030361407,0.00017284462,0.00038334975,0.000064832166,0.00017124256,0.00004497461],"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":[0.000036933736,0.001389867,0.7269172,0.0000058237356,0.00007643363,0.0000047880544,0.03549716,0.00000804923,0.00056723465,0.20893829,0.024712706,0.00184551],"study_design_scores_gemma":[0.00044396,0.00009452365,0.92341906,0.00004091145,0.000014872096,0.000003401169,0.015205251,0.0000045789843,0.000024970226,0.0025633073,0.058095284,0.00008987807],"about_ca_topic_score_codex":0.00009683787,"about_ca_topic_score_gemma":0.0006591783,"teacher_disagreement_score":0.20637499,"about_ca_system_score_codex":0.00053857017,"about_ca_system_score_gemma":0.00084438984,"threshold_uncertainty_score":0.99946094},"labels":[],"label_agreement":null},{"id":"W2341533239","doi":"10.1007/978-3-319-23398-7_7","title":"Current Policies Surrounding Assessment in Alberta: Future Implications","year":2015,"lang":"en","type":"book-chapter","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Current (fluid); Environmental planning; Political science; Environmental resource management; Geography; Environmental science; Geology; Oceanography","score_opus":0.05835413965550165,"score_gpt":0.39793250806224234,"score_spread":0.3395783684067407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2341533239","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001945736,0.002911821,0.0003145339,0.010847892,0.004669935,0.0018800998,0.000067834335,0.000098999124,0.97726315],"genre_scores_gemma":[0.72072995,0.004925223,0.00085488585,0.0002614987,0.0027291556,0.00024351025,0.00021658362,0.00019805506,0.2698411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952248,0.00022836833,0.0011002857,0.0007132317,0.0018944847,0.0008388471],"domain_scores_gemma":[0.9965998,0.0006078934,0.001008103,0.00093191525,0.0005945721,0.00025772682],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027720027,0.00061718805,0.0008981673,0.00055582577,0.00065580406,0.0003283455,0.0014086205,0.00044056211,0.0005776453],"category_scores_gemma":[0.00003042813,0.0005179504,0.0003867208,0.00037705043,0.00048670656,0.00031519268,0.00042191742,0.00133139,0.00004339775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012601211,0.00024241848,0.0114096245,0.000055293705,0.00020103226,0.0000033045194,0.008347915,0.00003304963,0.00001929423,0.9619102,0.014186392,0.0035789069],"study_design_scores_gemma":[0.00060162065,0.000101768244,0.016768934,0.00035324736,0.00016460996,0.0000013794222,0.008416737,0.000016292215,6.4566774e-7,0.020244237,0.95268345,0.00064706],"about_ca_topic_score_codex":0.0033253052,"about_ca_topic_score_gemma":0.013554602,"teacher_disagreement_score":0.94166595,"about_ca_system_score_codex":0.0018641475,"about_ca_system_score_gemma":0.0027089685,"threshold_uncertainty_score":0.9997272},"labels":[],"label_agreement":null},{"id":"W2345957802","doi":"10.7202/1035611ar","title":"Suivi des apprentissages au moyen d’évaluations formatives par questions à choix multiples diffusées sur le Web par le logiciel eTests","year":2014,"lang":"fr","type":"article","venue":"Revue internationale des technologies en pédagogie universitaire","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.05153691290710508,"score_gpt":0.3018681899848292,"score_spread":0.2503312770777241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345957802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94016385,0.0028585442,0.0050070714,0.021671131,0.00073231227,0.0005602071,0.00015749071,0.0011266763,0.027722746],"genre_scores_gemma":[0.91602665,0.006258401,0.006075613,0.000020509078,0.00018612393,0.0000439632,0.00008686064,0.000031977623,0.07126989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969819,0.00039267985,0.00048065098,0.00060662057,0.0005445259,0.0009936092],"domain_scores_gemma":[0.99694884,0.00150336,0.00040343168,0.0004586083,0.00054782076,0.00013794679],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0007940392,0.00043997267,0.0004579133,0.0004885216,0.0021086684,0.00024478897,0.0017448824,0.0005008552,0.00008513736],"category_scores_gemma":[0.002578197,0.0004927062,0.00032486938,0.0008555965,0.00379649,0.002159126,0.0007797678,0.00045642938,0.00011154333],"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":[0.000033912293,0.001628199,0.34946492,0.00034963866,0.00085592957,0.000061041894,0.04162476,0.0027026539,0.0018867719,0.20832671,0.005594888,0.38747057],"study_design_scores_gemma":[0.0034521786,0.00062640914,0.28472233,0.002363493,0.0004855494,0.000050876763,0.28630245,0.026018752,0.002824965,0.04755126,0.34356046,0.002041276],"about_ca_topic_score_codex":0.0026744076,"about_ca_topic_score_gemma":0.017424999,"teacher_disagreement_score":0.3854293,"about_ca_system_score_codex":0.0012863285,"about_ca_system_score_gemma":0.00078619923,"threshold_uncertainty_score":0.99975246},"labels":[],"label_agreement":null},{"id":"W2393663033","doi":"10.21083/nrsc.v0i9.3672","title":"The Power of Peer Evaluation: Rethinking Pedagogy in L2 Conversation Courses","year":2016,"lang":"en","type":"article","venue":"Nouvelle Revue Synergies Canada","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conversation; Peer evaluation; Peer review; Peer feedback; Power (physics); Pedagogy; Psychology; Peer assessment; Perception; Higher education; Engineering ethics; Mathematics education; Political science; Engineering","score_opus":0.027354771169304487,"score_gpt":0.3364956000897792,"score_spread":0.3091408289204747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2393663033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.863686,0.00054178515,0.000013364847,0.055941578,0.002282172,0.0004418484,0.000009486576,0.000019420624,0.07706429],"genre_scores_gemma":[0.9873159,0.00024287391,0.000029051474,0.000053653326,0.00011811402,0.000016210906,0.0000021250914,0.000006197671,0.012215887],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981676,0.00022010501,0.00023243732,0.00014298824,0.0010007324,0.00023615203],"domain_scores_gemma":[0.99856716,0.00069332984,0.00014827691,0.00016936183,0.0003818192,0.000040032246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015918057,0.000074681746,0.00012668545,0.000036637113,0.00028031773,0.000027833968,0.00027190012,0.000060645092,0.00071493356],"category_scores_gemma":[0.00074209034,0.00005002463,0.00003307078,0.00019292036,0.00018616194,0.00012010187,0.000037281152,0.000062814725,0.0000046313326],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013971463,0.00009556643,0.3052564,0.000057553698,0.0002072381,0.000025824824,0.31361884,0.00015851355,0.00102716,0.118903175,0.19007042,0.07043959],"study_design_scores_gemma":[0.0015411391,0.00006571431,0.08345705,0.0002443942,0.00006303844,0.000001125649,0.36069903,0.00015964256,0.0004194438,0.0027530564,0.5501596,0.00043679282],"about_ca_topic_score_codex":0.43105412,"about_ca_topic_score_gemma":0.9563297,"teacher_disagreement_score":0.5252756,"about_ca_system_score_codex":0.00052983634,"about_ca_system_score_gemma":0.002848469,"threshold_uncertainty_score":0.7828021},"labels":[],"label_agreement":null},{"id":"W2397824374","doi":"10.59236/td2014vol7iss21213","title":"How Am I Doing? Formative Feedback for Graduate Students Learning to Teach","year":2014,"lang":"en","type":"article","venue":"Transformative Dialogues Teaching and Learning Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Formative assessment; Graduate students; Psychology; Peer feedback; Pedagogy; Medical education; Mathematics education; Medicine","score_opus":0.0361386311556136,"score_gpt":0.3420188290598755,"score_spread":0.3058801979042619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397824374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8018611,0.00006415358,0.17201155,0.005262959,0.0006025429,0.00070000143,0.000004252606,0.00020833795,0.01928509],"genre_scores_gemma":[0.9893922,0.00015310518,0.0062650023,0.00030621616,0.0008418276,0.000034656656,0.000022000415,0.000030015713,0.0029549643],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99475753,0.002719105,0.00042432654,0.000274166,0.0010170864,0.0008077563],"domain_scores_gemma":[0.9978815,0.0010672585,0.00030913355,0.000074506795,0.00025297047,0.00041466055],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010999757,0.00031132705,0.0004589894,0.00028517356,0.007126049,0.0018174838,0.00046554807,0.00013578017,0.000010919338],"category_scores_gemma":[0.0015586036,0.0002710538,0.00020658081,0.00017434653,0.00018053396,0.001387787,0.0000527646,0.003004116,0.000021001253],"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":[0.00013926502,0.000098290286,0.015902227,0.000046872417,0.00016580464,0.000001337064,0.82718927,0.00033881032,0.0001442285,0.002989923,0.0010109777,0.15197301],"study_design_scores_gemma":[0.0031059075,0.0015997868,0.023316706,0.00034865315,0.00014159191,0.000015668133,0.40009412,0.0009286928,0.000041743166,0.00092963525,0.56871164,0.00076585397],"about_ca_topic_score_codex":0.00011864998,"about_ca_topic_score_gemma":0.00006654815,"teacher_disagreement_score":0.5677007,"about_ca_system_score_codex":0.00014688983,"about_ca_system_score_gemma":0.00006007271,"threshold_uncertainty_score":0.9999742},"labels":[],"label_agreement":null},{"id":"W2405113580","doi":"10.1177/0098628316649312","title":"The Impact of Participating in a Peer Assessment Activity on Subsequent Academic Performance","year":2016,"lang":"en","type":"article","venue":"Teaching of Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kwantlen Polytechnic University","funders":"","keywords":"Attendance; Psychology; Peer assessment; Peer evaluation; Medical education; Peer feedback; Academic achievement; Higher education; Mathematics education; Medicine","score_opus":0.10341006593162669,"score_gpt":0.524978013856735,"score_spread":0.4215679479251083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405113580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9671294,0.00001241385,0.00008045626,0.0030095836,0.00018839329,0.00014180341,0.0000016694986,0.000013483172,0.029422808],"genre_scores_gemma":[0.99941766,0.00008553526,0.000069636066,0.000022643084,0.000069633825,0.000033945555,2.000791e-7,0.0000057405114,0.00029497803],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983113,0.0005798497,0.0002584452,0.00015579358,0.0003688272,0.00032580824],"domain_scores_gemma":[0.99887383,0.0006199185,0.00024205651,0.00018546724,0.00003990235,0.0000387981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003826745,0.000082704646,0.00017304036,0.00006895312,0.00019400635,0.000007013327,0.00033279086,0.00008959958,0.00006641119],"category_scores_gemma":[0.00029745625,0.000045154316,0.00007396922,0.000104964136,0.0002671939,0.00011674371,0.000035709563,0.000358457,0.0000059583454],"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":[0.00008131635,0.00014354083,0.93312347,0.000002248518,0.000022208567,3.8668995e-7,0.005908958,0.0000102108515,0.0069889915,0.006004422,0.00046655492,0.04724768],"study_design_scores_gemma":[0.00046512685,0.00028870362,0.99759495,0.000052452247,0.0000044900544,1.8841656e-7,0.0005216843,0.00004050971,0.000110541005,0.00048691386,0.00037490076,0.000059564405],"about_ca_topic_score_codex":0.00086173223,"about_ca_topic_score_gemma":0.00013950617,"teacher_disagreement_score":0.064471446,"about_ca_system_score_codex":0.00016741308,"about_ca_system_score_gemma":0.00009360148,"threshold_uncertainty_score":0.18413395},"labels":[],"label_agreement":null},{"id":"W2408321301","doi":"10.5539/ies.v9n6p76","title":"The Influence of Educational Programme on Teachers’ Error Correction Preferences in the Speaking Skill: Insights from English as a Foreign Language Context","year":2016,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Mathematics education; Class (philosophy); Psychology; English as a foreign language; Curriculum; Error detection and correction; Foreign language; Corrective feedback; Teaching method; Language proficiency; Error analysis; Pedagogy; Computer science; Mathematics","score_opus":0.04945085154891508,"score_gpt":0.4092691588517989,"score_spread":0.3598183073028838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408321301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95215243,0.00061922777,0.0000020932844,0.0070961276,0.0030240465,0.0002934464,0.0000034933328,0.000013844612,0.036795314],"genre_scores_gemma":[0.9951222,0.00029129535,0.000032249223,0.00028604106,0.000657666,0.00024718395,0.0000075513863,0.000004454033,0.003351369],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99863434,0.0002040297,0.0002568158,0.00017919207,0.000588692,0.00013695771],"domain_scores_gemma":[0.9961449,0.0026064867,0.00022878208,0.00011963439,0.00087689044,0.000023321787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041687384,0.00009506887,0.00010006203,0.00008601961,0.00031665617,0.00009400647,0.00046897423,0.00003672694,0.00007995488],"category_scores_gemma":[0.00475019,0.00004862294,0.00004558117,0.00018835922,0.00033147796,0.00029354368,0.00003850916,0.000091850394,0.000030460069],"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":[0.000045009172,0.00050488114,0.20472269,0.0000020173493,0.00016093867,2.155274e-7,0.5975834,0.000005413491,0.000053223477,0.12505844,0.0045646788,0.06729905],"study_design_scores_gemma":[0.00021234527,0.000039305407,0.3661634,0.00017021576,0.000010189934,1.8505857e-7,0.57748735,0.0000010442129,0.000043465432,0.014501598,0.041290253,0.00008066678],"about_ca_topic_score_codex":0.0041667856,"about_ca_topic_score_gemma":0.010630797,"teacher_disagreement_score":0.16144072,"about_ca_system_score_codex":0.00023341115,"about_ca_system_score_gemma":0.00035719754,"threshold_uncertainty_score":0.6298961},"labels":[],"label_agreement":null},{"id":"W2408838614","doi":"","title":"Examining the examination: Canadian versus US certification exam.","year":2000,"lang":"en","type":"letter","venue":"PubMed","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Certification; Family medicine; Medical physics; Medical education; Management","score_opus":0.11618409775338881,"score_gpt":0.29285253471322986,"score_spread":0.17666843695984105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408838614","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032705953,0.00017407579,8.733731e-7,0.43348297,0.0026506758,0.0011120541,0.000013260536,0.0000772938,0.55921817],"genre_scores_gemma":[0.55944186,0.00048228048,0.000021481239,0.25661635,0.022130465,0.004616704,0.0004944133,0.000081526596,0.15611492],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99729043,0.0004602117,0.00022425262,0.00037767066,0.00080744893,0.00083999493],"domain_scores_gemma":[0.99879867,0.00046071838,0.00013641022,0.00037440108,0.000078162084,0.00015165473],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012026855,0.00019628457,0.00016987967,0.00019174303,0.0009774534,0.00046600527,0.0008283589,0.0005176169,0.0009215987],"category_scores_gemma":[0.00015956904,0.00016824582,0.00006707746,0.00043508265,0.00024318244,0.00018830512,0.000025058638,0.0007156989,0.00020463916],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042301563,0.000004871599,0.0013896398,0.0000042431875,0.00004585993,0.000021166878,0.0027576576,5.3202535e-7,4.661559e-8,0.00012077282,0.7861583,0.20949264],"study_design_scores_gemma":[0.0001261069,0.0000035487105,0.27953386,0.0000033054253,0.00004220354,2.0879396e-7,0.0006457503,8.812224e-7,3.8278614e-7,0.000019591855,0.7194656,0.00015855797],"about_ca_topic_score_codex":0.10291849,"about_ca_topic_score_gemma":0.18051459,"teacher_disagreement_score":0.5561713,"about_ca_system_score_codex":0.000752805,"about_ca_system_score_gemma":0.00033320437,"threshold_uncertainty_score":0.9999917},"labels":[],"label_agreement":null},{"id":"W2411843932","doi":"10.5539/elt.v9n7p129","title":"Be Creative and Collaborative: Strategies and Implications of Blogging in EFL Classes","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Immediacy; Psychology; Context (archaeology); Curriculum; Collaborative writing; Pedagogy; Mathematics education","score_opus":0.014874673134921329,"score_gpt":0.3516294710616509,"score_spread":0.3367547979267296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2411843932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91647375,0.00052221766,0.00007667765,0.00074266456,0.000035075554,0.00013108931,0.000009691762,0.000038608072,0.081970245],"genre_scores_gemma":[0.9985998,0.00015671966,0.00071543123,0.00002248302,0.00009108919,0.000010663739,0.0000015270504,0.000005023882,0.00039721097],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99928623,0.000201636,0.000118196636,0.0001406222,0.00011008197,0.00014320096],"domain_scores_gemma":[0.9993305,0.00046041363,0.00006461037,0.00006908831,0.00003785413,0.000037520025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005593148,0.00006698605,0.000121868536,0.00007304031,0.00018117635,0.00009734548,0.000083328574,0.000041548115,0.00003853196],"category_scores_gemma":[0.00054014905,0.000050663868,0.000010984532,0.0001253741,0.00019978834,0.0005522073,0.00004381841,0.000088936446,2.2764803e-7],"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":[0.000005292276,0.00002895972,0.15356357,0.000007262718,0.0000140116235,0.0000017369837,0.733717,3.1442843e-7,0.0052697733,0.09351671,0.00008165332,0.013793699],"study_design_scores_gemma":[0.0003697385,0.000022974546,0.097382806,0.000058362028,0.000008847263,1.3225578e-7,0.89983344,0.0000011990458,0.00016311997,0.0007001881,0.0013681852,0.00009100057],"about_ca_topic_score_codex":0.0012045065,"about_ca_topic_score_gemma":0.0037588493,"teacher_disagreement_score":0.16611643,"about_ca_system_score_codex":0.000033117278,"about_ca_system_score_gemma":0.00006860749,"threshold_uncertainty_score":0.20975262},"labels":[],"label_agreement":null},{"id":"W2441041702","doi":"10.1111/medu.12985","title":"Taking the sting out of assessment: is there a role for progress testing?","year":2016,"lang":"en","type":"review","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Ottawa","funders":"","keywords":"Context (archaeology); Curriculum; Test (biology); Standardized test; Assessment for learning; Educational assessment; Formative assessment; Unintended consequences; Educational measurement; Risk assessment; Computer science; Psychology; Engineering ethics; Mathematics education; Engineering; Pedagogy; Political science","score_opus":0.09766983136844255,"score_gpt":0.5079418249069397,"score_spread":0.4102719935384972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2441041702","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011006586,0.9589444,0.000112090296,0.0035380714,0.0014624355,0.0014546285,0.0000107156075,0.00003330337,0.03443335],"genre_scores_gemma":[0.0005814465,0.991585,0.0011821564,0.00029635403,0.0028820361,0.0009458302,0.000024580628,0.000033110744,0.0024694614],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99779767,0.00029137245,0.00045964142,0.00024703002,0.0009225763,0.000281695],"domain_scores_gemma":[0.9971698,0.0014290736,0.00087939115,0.0001994836,0.00023904882,0.00008321012],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021224811,0.00016544285,0.00049562147,0.000055925066,0.0003896286,0.000082394465,0.00071153184,0.00024697706,0.00093075534],"category_scores_gemma":[0.003268933,0.000090426045,0.00019947285,0.00026705142,0.0003170151,0.0000777006,0.00006961023,0.00021713348,0.000016631735],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[4.455939e-7,0.000097334756,0.0006429187,0.0010866541,0.000040070692,8.663489e-8,0.0029348815,7.312407e-10,2.5787813e-8,0.0021665918,0.0036627613,0.9893682],"study_design_scores_gemma":[0.00007098648,0.000021041702,0.00022896854,0.011684841,0.00017823675,3.6851367e-7,0.0017216475,0.0000063504863,4.7010225e-8,0.00041885374,0.9855533,0.00011533673],"about_ca_topic_score_codex":0.00021639612,"about_ca_topic_score_gemma":0.000069868576,"teacher_disagreement_score":0.98925287,"about_ca_system_score_codex":0.00016040071,"about_ca_system_score_gemma":0.0065002963,"threshold_uncertainty_score":0.99998254},"labels":[],"label_agreement":null},{"id":"W2461301006","doi":"10.5539/elt.v9n8p106","title":"Effectiveness of Using Screencast Feedback on EFL Students’ Writing and Perception","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Perception; Peer feedback; Constructive; Video feedback; Control (management); Mathematics education; Pedagogy; Computer science","score_opus":0.01930918518031864,"score_gpt":0.3550008529784101,"score_spread":0.33569166779809145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2461301006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856686,0.000057908797,0.00047404788,0.000021738522,0.00021308257,0.00023528039,0.000004462658,0.000084087515,0.013240795],"genre_scores_gemma":[0.998669,0.00001625751,0.00061851356,0.000014344022,0.00046980847,0.0000042474844,0.000001932218,0.000015947158,0.00018993222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980769,0.000742465,0.00017173612,0.00024342409,0.00050721073,0.00025826745],"domain_scores_gemma":[0.99898684,0.00067749515,0.00009425802,0.00012912479,0.00004276777,0.0000695273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029288514,0.00011972327,0.00018632317,0.00009498822,0.00038574057,0.0001002277,0.00021663292,0.000074509095,0.000085310894],"category_scores_gemma":[0.00062195776,0.00009282995,0.000053414915,0.00009291847,0.00013237324,0.00035004405,0.00009725403,0.00016307509,0.0000055925975],"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":[0.000076027296,0.00014689175,0.592762,0.00006901531,0.000048317506,0.000009646579,0.27457047,0.0000034366224,0.078613475,0.004332264,0.000013237336,0.04935524],"study_design_scores_gemma":[0.0020127068,0.00013866757,0.50988615,0.0015687167,0.000055047105,0.0000010510872,0.48477095,0.000021085778,0.00092587643,0.00008010784,0.00015429658,0.000385313],"about_ca_topic_score_codex":0.0008120852,"about_ca_topic_score_gemma":0.000053537773,"teacher_disagreement_score":0.2102005,"about_ca_system_score_codex":0.0001385975,"about_ca_system_score_gemma":0.000020518868,"threshold_uncertainty_score":0.37854955},"labels":[],"label_agreement":null},{"id":"W2464754146","doi":"","title":"The Untried Path: Exemplary Elementary School Teachers’ Understanding of and Experiences with Classroom Assessment","year":2016,"lang":"en","type":"dissertation","venue":"Brock University Digital Repository (Brock University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Path (computing); Pedagogy; Psychology; Sociology; Computer science","score_opus":0.017084391693825737,"score_gpt":0.25224128652641625,"score_spread":0.2351568948325905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2464754146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7325926,0.00015223304,0.00036460804,0.000019988604,0.0004938055,0.0006495775,0.000039075912,0.00012247883,0.26556566],"genre_scores_gemma":[0.550172,0.0003526755,0.00005177193,0.0000062221247,0.00008841166,6.999305e-7,0.000052994998,0.00002063493,0.44925463],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9975032,0.00021935289,0.00025568568,0.00057876814,0.0009427837,0.0005002023],"domain_scores_gemma":[0.998237,0.0003814751,0.00055842503,0.00028499716,0.00022259828,0.00031549856],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000015987074,0.00036725184,0.00037792925,0.00034572816,0.0026424818,0.00035421344,0.0008681375,0.00030417615,0.00001781464],"category_scores_gemma":[0.000029250925,0.0003153896,0.0001739466,0.000511108,0.00058808306,0.0016275198,0.00021079744,0.00033970102,0.0000035843932],"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":[0.004263544,0.0006926547,0.8532074,0.0002686796,0.0026588107,0.0005374594,0.02958898,0.000004307959,0.0047558188,0.008573576,0.09222975,0.0032190161],"study_design_scores_gemma":[0.0010155175,0.00022588708,0.009879366,0.00026519696,0.0002201018,0.0000030858303,0.93600243,3.0153572e-7,0.000056001052,0.00006297158,0.051825937,0.00044320963],"about_ca_topic_score_codex":0.0003841422,"about_ca_topic_score_gemma":0.0036930253,"teacher_disagreement_score":0.90641344,"about_ca_system_score_codex":0.0014886778,"about_ca_system_score_gemma":0.0010078275,"threshold_uncertainty_score":0.99992985},"labels":[],"label_agreement":null},{"id":"W2470295771","doi":"","title":"THE CONTRIBUTIONS OF DIGITAL CONCEPT MAPS TO ASSESSMENT FOR LEARNING PRACTICES","year":2013,"lang":"en","type":"article","venue":"Cognition and Exploratory Learning in Digital Age","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Variety (cybernetics); Computer science; Workload; Strengths and weaknesses; Digital learning; Multimedia; Assessment for learning; Human–computer interaction; Data science; Mathematics education; Artificial intelligence; Psychology","score_opus":0.040250405043100866,"score_gpt":0.36111613432163386,"score_spread":0.320865729278533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470295771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88822097,0.00026487687,0.002587254,0.004040922,0.00033996953,0.0019957812,0.00007285537,0.00019676874,0.1022806],"genre_scores_gemma":[0.99780107,0.00006098935,0.00006200674,0.000053202708,0.000086536864,0.00020709589,0.00009414449,0.000009255977,0.0016256964],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900806,0.00008747593,0.00022784575,0.00017187264,0.00024506895,0.0002596515],"domain_scores_gemma":[0.9982863,0.0010253453,0.000235656,0.000050732808,0.00029672252,0.00010524526],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004403409,0.00009365714,0.00013763922,0.00006061706,0.00067477755,0.0011208412,0.00011274752,0.000052615836,0.000029393637],"category_scores_gemma":[0.0028061357,0.000079329395,0.000045878343,0.00020647827,0.0002455191,0.0014237664,0.00006600398,0.00019977293,0.00004179917],"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":[0.00036105822,0.0012231751,0.3265345,0.00012379694,0.00038023756,0.000026990436,0.13211186,0.00042623424,0.004902026,0.09424803,0.020680543,0.41898152],"study_design_scores_gemma":[0.0023736493,0.00077737827,0.028740982,0.00020114824,0.000046795998,0.0000010304361,0.43306488,0.0002775209,0.00027092532,0.015159213,0.51848966,0.0005968033],"about_ca_topic_score_codex":0.000016484504,"about_ca_topic_score_gemma":0.000026233467,"teacher_disagreement_score":0.4978091,"about_ca_system_score_codex":0.000045749355,"about_ca_system_score_gemma":0.00008432993,"threshold_uncertainty_score":0.9999161},"labels":[],"label_agreement":null},{"id":"W2472075195","doi":"10.1017/s0261444815000233","title":"Review of washback research literature within Kane's argument-based validation framework","year":2015,"lang":"en","type":"article","venue":"Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Empirical research; Argument (complex analysis); Maturity (psychological); Systematic review; English language; Psychology; Political science; Epistemology; Mathematics education; Medicine; Philosophy; Law; Developmental psychology","score_opus":0.08897567591661655,"score_gpt":0.4676807480738409,"score_spread":0.3787050721572244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2472075195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69327265,0.09987199,0.0017397945,0.008966687,0.0014150912,0.001836243,0.000020715757,0.00035161266,0.1925252],"genre_scores_gemma":[0.97984964,0.0007700308,0.0151537955,0.0010367929,0.0006753333,0.000023094686,0.00007431699,0.000020170426,0.0023968292],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9968656,0.0013546755,0.00025249788,0.00020295227,0.0010323054,0.0002919937],"domain_scores_gemma":[0.9989012,0.00035559724,0.00013273311,0.0002900443,0.00019287637,0.00012757115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008405294,0.00009677374,0.00019306867,0.000107677675,0.00027553856,0.00014135665,0.00038227043,0.00011738526,0.0001927444],"category_scores_gemma":[0.0027836633,0.00008355034,0.000066247725,0.0005155813,0.00010024744,0.00023749797,0.000061730076,0.0007020785,0.000051148316],"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":[0.000060700684,0.00041028974,0.022731937,0.002547823,0.000070922375,0.0000511237,0.8282193,0.000025110563,0.0012152608,0.08848168,0.039240096,0.01694577],"study_design_scores_gemma":[0.0037631218,0.00090554456,0.0020456887,0.1229825,0.0003066562,0.000005826112,0.58727163,0.0005816926,0.0053159283,0.018550495,0.25612387,0.0021470378],"about_ca_topic_score_codex":0.00072694477,"about_ca_topic_score_gemma":0.00006574538,"teacher_disagreement_score":0.28657696,"about_ca_system_score_codex":0.00012972207,"about_ca_system_score_gemma":0.0001785059,"threshold_uncertainty_score":0.3407084},"labels":[],"label_agreement":null},{"id":"W2479837187","doi":"10.1007/978-3-319-39211-0","title":"Assessment for Learning: Meeting the Challenge of Implementation","year":2016,"lang":"en","type":"book","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":105,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Engineering ethics; Computer science; Engineering management; Engineering","score_opus":0.041019253824978785,"score_gpt":0.3993390365835251,"score_spread":0.3583197827585463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479837187","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073621806,0.0009855552,0.0049922676,0.007128504,0.0021591268,0.0041504884,0.00009335468,0.00010236576,0.9796521],"genre_scores_gemma":[0.6246248,0.0018535756,0.002097195,0.00015831551,0.0014479291,0.0005289683,0.00013994094,0.00015544861,0.36899385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99522156,0.00051091594,0.0011208595,0.0005454264,0.0019201187,0.00068109494],"domain_scores_gemma":[0.99444395,0.0020319622,0.0021061567,0.00061054574,0.00071754085,0.000089826506],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0060645505,0.00042616067,0.0007209726,0.00019562562,0.0010895213,0.0001453854,0.0012758627,0.0002925408,0.0007451876],"category_scores_gemma":[0.000058471964,0.00025904752,0.0005378406,0.00018572829,0.00052461546,0.00017806412,0.00029904587,0.00056005287,0.0000069181433],"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":[0.00015037884,0.00075458235,0.008483741,0.00085738034,0.003856692,0.000005424309,0.048169807,0.00012597226,0.001276515,0.8022463,0.08058632,0.053486913],"study_design_scores_gemma":[0.0015388601,0.0007409215,0.0020258417,0.0005755175,0.000587409,3.2332784e-7,0.029429417,0.000046380923,0.000049962877,0.0149391,0.9495035,0.0005628109],"about_ca_topic_score_codex":0.00025095348,"about_ca_topic_score_gemma":0.0006073341,"teacher_disagreement_score":0.8689171,"about_ca_system_score_codex":0.00073605106,"about_ca_system_score_gemma":0.0022906854,"threshold_uncertainty_score":0.9999862},"labels":[],"label_agreement":null},{"id":"W2481621308","doi":"10.4018/978-1-4666-0068-3.ch006","title":"Assessing Science Inquiry","year":2012,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Victoria","funders":"","keywords":"Summative assessment; Psychology; Mathematics education; Process (computing); Inquiry-based learning; Cognition; Pedagogy; Computer science; Formative assessment","score_opus":0.057102462581540815,"score_gpt":0.37366891643471717,"score_spread":0.31656645385317633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481621308","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093332294,0.098224506,0.0002588455,0.0061932467,0.0045762514,0.0007312294,0.000011002668,0.00041768586,0.88865393],"genre_scores_gemma":[0.06280626,0.52374345,0.122074574,0.0003103154,0.0031992772,0.0003298321,0.00006175933,0.000107688036,0.2873668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99800336,0.000023849001,0.00033658178,0.000477099,0.0007371559,0.00042196608],"domain_scores_gemma":[0.9989994,0.00026176957,0.00025831288,0.00019672982,0.00021874392,0.000065002314],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00058473175,0.000272467,0.00026846037,0.0005500584,0.0010383694,0.0002729685,0.00050265255,0.0003198651,0.00040893655],"category_scores_gemma":[0.00025525506,0.0002780332,0.000045734727,0.00022562296,0.006440448,0.007765133,0.00019772965,0.0004001641,0.000020161762],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009614943,0.000016264024,0.0007752476,0.000014541356,0.000008650094,6.116037e-7,0.0005481049,0.0000048045063,0.00002387743,0.89192885,0.000235254,0.10643416],"study_design_scores_gemma":[0.00006975538,0.000024187106,0.0022433724,0.0001141044,0.000011078196,0.000013140439,0.008145682,7.106026e-7,0.00003098827,0.37455523,0.61450416,0.00028761593],"about_ca_topic_score_codex":0.000012801025,"about_ca_topic_score_gemma":0.000038842896,"teacher_disagreement_score":0.6142689,"about_ca_system_score_codex":0.00046073872,"about_ca_system_score_gemma":0.0011008461,"threshold_uncertainty_score":0.99996716},"labels":[],"label_agreement":null},{"id":"W2485771798","doi":"10.4018/978-1-59140-732-4.ch010","title":"Self-Assessment During Online Discussion","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Perspective (graphical); Action (physics); Self-assessment; Process (computing); Action research; Citizen journalism; Psychology; Online assessment; Computer science; Mathematics education; Pedagogy; Formative assessment; World Wide Web; Artificial intelligence","score_opus":0.026535787720943914,"score_gpt":0.32138575955527415,"score_spread":0.29484997183433026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2485771798","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011735306,0.00010372127,0.000013124844,0.00023611258,0.0011035868,0.00057283114,0.00007688195,0.0003801807,0.99634004],"genre_scores_gemma":[0.26123568,0.0001544491,0.0022930545,0.00017938498,0.002067377,0.00002377492,0.00001934858,0.00007835116,0.7339486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750185,0.000051668194,0.00040236666,0.0005437674,0.00095493335,0.0005453887],"domain_scores_gemma":[0.9989098,0.00001944213,0.00029588927,0.00038699096,0.00011106347,0.00027682332],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021527063,0.0004317742,0.00045566834,0.000068954854,0.0005934659,0.00014069435,0.0006377362,0.0005024314,0.0005639268],"category_scores_gemma":[0.000005234185,0.0003273019,0.00029561986,0.000026085232,0.00016527966,0.00009453361,0.00031749677,0.00037601826,0.0002548351],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017487242,0.000058535905,0.0011973133,0.000027917116,0.00012824705,0.00004600672,0.0014948238,5.1754796e-8,0.00000519985,0.99366665,0.0008020706,0.0025556989],"study_design_scores_gemma":[0.0013840013,0.00017663592,0.015765913,0.00056339963,0.00048222893,0.0000069636358,0.0015676414,0.0000028364354,0.00000863913,0.47067806,0.5076418,0.001721888],"about_ca_topic_score_codex":0.00037439817,"about_ca_topic_score_gemma":0.0017181118,"teacher_disagreement_score":0.52298856,"about_ca_system_score_codex":0.0010122539,"about_ca_system_score_gemma":0.0005575094,"threshold_uncertainty_score":0.9999179},"labels":[],"label_agreement":null},{"id":"W2487148800","doi":"10.4018/978-1-59140-732-4.ch020","title":"Effects of Anonymity and Accountability During Online Peer Assessment","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Anonymity; Accountability; Peer feedback; Psychology; Peer assessment; Peer group; Online discussion; Quality (philosophy); Peer review; Social psychology; Mathematics education; Computer science; World Wide Web; Political science; Computer security","score_opus":0.025561739298318783,"score_gpt":0.33107803161382754,"score_spread":0.30551629231550875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2487148800","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123695225,0.00018916564,0.000008420643,0.000041970074,0.00044534242,0.0006744109,0.00008634895,0.000067094494,0.87479204],"genre_scores_gemma":[0.9205778,0.00005545239,0.00036657846,0.0000515597,0.00036355073,0.000011278989,0.0000046786586,0.00002286875,0.07854622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9977971,0.000066189576,0.00036596842,0.0004566624,0.0009711313,0.0003429909],"domain_scores_gemma":[0.99886256,0.00011651715,0.00030592096,0.00027953656,0.00026944588,0.00016600997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042588188,0.00032744568,0.0005440776,0.00004694437,0.00024314,0.000067072,0.00035901554,0.00041638478,0.00014585545],"category_scores_gemma":[0.00004779229,0.00032196296,0.0001798058,0.000020914405,0.00049607374,0.00008790215,0.00027829627,0.00028403237,0.000011682051],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054374694,0.000097613396,0.017126178,0.00024914448,0.00017413568,0.000021936174,0.0014356573,3.348422e-8,0.00007598235,0.9783034,0.0002688802,0.0021926963],"study_design_scores_gemma":[0.002285478,0.00026917233,0.5995153,0.00064458157,0.0007088293,0.0000044657,0.0008740143,0.0000011899873,0.00016860783,0.36824134,0.025941899,0.0013451161],"about_ca_topic_score_codex":0.0019095269,"about_ca_topic_score_gemma":0.0026041865,"teacher_disagreement_score":0.79688257,"about_ca_system_score_codex":0.00036846206,"about_ca_system_score_gemma":0.00031972173,"threshold_uncertainty_score":0.9999232},"labels":[],"label_agreement":null},{"id":"W2489507737","doi":"10.4018/978-1-59140-747-8.ch009","title":"Testing the Validity of the Post and Vote Model of Web-Based Peer Assessment","year":2006,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Peer assessment; Pearson product-moment correlation coefficient; Psychology; Product (mathematics); Correlation coefficient; Peer evaluation; Computer science; Mathematics education; Statistics; Mathematics; Higher education; Political science","score_opus":0.06111622158566674,"score_gpt":0.3232555010889074,"score_spread":0.2621392795032406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489507737","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016274989,0.000033260418,0.00006019141,0.00057475246,0.00022444646,0.0005045492,0.00020291173,0.000028644836,0.98209625],"genre_scores_gemma":[0.9607614,0.00000105807,0.0005378895,0.0001681452,0.00014293361,0.0000061569003,0.0000018074176,0.000015172261,0.038365435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99779886,0.000087612796,0.0003638254,0.0002487046,0.001261388,0.00023962652],"domain_scores_gemma":[0.9983892,0.00024626247,0.00049000443,0.00033506565,0.0004877143,0.000051750383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077630166,0.00023396558,0.00033081547,0.00002472823,0.00036369104,0.0000686862,0.00057369383,0.00022456353,0.000009570571],"category_scores_gemma":[0.00008089385,0.00014926022,0.00020264815,0.000035647954,0.00070609985,0.00003084794,0.00019329021,0.00023303396,0.0000012369901],"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":[0.000010242997,0.000026430489,0.02114882,0.000035383444,0.000056443416,0.0000012730223,0.00028001386,0.00016302032,0.00024373371,0.974595,0.0026768448,0.000762813],"study_design_scores_gemma":[0.003944289,0.0005573341,0.24155408,0.0016160416,0.00204414,0.0000044380317,0.0013971571,0.014639165,0.000192306,0.6954355,0.03632604,0.0022894775],"about_ca_topic_score_codex":0.0019581697,"about_ca_topic_score_gemma":0.0019715757,"teacher_disagreement_score":0.94448644,"about_ca_system_score_codex":0.0001567486,"about_ca_system_score_gemma":0.0009769786,"threshold_uncertainty_score":0.6086655},"labels":[],"label_agreement":null},{"id":"W2490078899","doi":"","title":"SYMPOSIUM: The Validity of Testing: Perceptions of Stakeholders","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Perception; Psychology; Computer science","score_opus":0.24014471523629496,"score_gpt":0.3671960779230274,"score_spread":0.12705136268673242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490078899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8165427,0.000012580697,0.0014276658,0.004427387,0.00025926254,0.00023882109,0.000024655445,0.000031849464,0.17703508],"genre_scores_gemma":[0.99355185,0.0001492319,0.00017996063,0.000019342366,0.00007338949,0.0000073423034,4.0409554e-7,0.000003753814,0.006014707],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99901444,0.00015130415,0.00018366071,0.00012326491,0.00034924617,0.00017809779],"domain_scores_gemma":[0.99864423,0.0006396754,0.0001519098,0.00020533342,0.00031140738,0.000047428268],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005381899,0.00006789997,0.00012437049,0.000028352742,0.00017384582,0.000020881147,0.00041813514,0.00004697196,0.0011245683],"category_scores_gemma":[0.0002634643,0.000036545793,0.000052589494,0.00015124667,0.0006907726,0.00013301933,0.000052324427,0.00004369314,0.000055898894],"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":[0.000011075261,0.00013286382,0.7741662,0.0000148019135,0.000033000502,5.3833816e-7,0.011980481,6.834846e-7,0.1389858,0.05503018,0.0072473176,0.012397032],"study_design_scores_gemma":[0.0011449053,0.0003679672,0.924099,0.0004862216,0.00012499465,7.959905e-7,0.037971415,0.000027661248,0.0046740267,0.010088572,0.02055263,0.00046180698],"about_ca_topic_score_codex":0.0009855132,"about_ca_topic_score_gemma":0.0003486647,"teacher_disagreement_score":0.17700918,"about_ca_system_score_codex":0.000024885823,"about_ca_system_score_gemma":0.00030554834,"threshold_uncertainty_score":0.9997885},"labels":[],"label_agreement":null},{"id":"W2491036265","doi":"10.4018/978-1-4666-4458-8.ch017","title":"Evaluation of Course Curriculum and Teaching","year":2013,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Curriculum; Checklist; Teaching method; Mathematics education; Medical education; Computer science; Psychology; Pedagogy; Medicine","score_opus":0.03734643498440647,"score_gpt":0.3990359738613538,"score_spread":0.3616895388769473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2491036265","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059331604,0.04001385,4.4205333e-7,0.0016265431,0.0033958792,0.0007334469,0.0000019878144,0.00001917999,0.9482755],"genre_scores_gemma":[0.03675429,0.009160019,0.0014601968,0.0001820009,0.00022293054,0.00016268922,0.00004598161,0.000015899499,0.95199597],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826825,0.00013763846,0.00033954656,0.00025463378,0.0008542956,0.00014564962],"domain_scores_gemma":[0.9991644,0.000081735205,0.00027931834,0.00007669492,0.00032921424,0.00006861689],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010950356,0.00018215805,0.00021997235,0.00010818143,0.00033412233,0.000036010762,0.00010281895,0.00016379239,0.0029832062],"category_scores_gemma":[0.000027517473,0.00016360744,0.000018299264,0.000021558655,0.00025175564,0.0010976417,0.0000678417,0.00021798765,0.000013670292],"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":[0.000007639933,0.00012015548,0.0125407735,0.00008365738,0.000030472058,1.5038238e-7,0.009222996,4.0944732e-7,0.0000023417722,0.86016446,0.002881696,0.11494526],"study_design_scores_gemma":[0.00017277972,0.000012504826,0.042572718,0.0006490626,0.000042703035,3.6434216e-7,0.0030307185,7.196607e-7,0.0000022713305,0.02827674,0.9250271,0.00021232142],"about_ca_topic_score_codex":0.000028503655,"about_ca_topic_score_gemma":0.00014902774,"teacher_disagreement_score":0.9221454,"about_ca_system_score_codex":0.00014141585,"about_ca_system_score_gemma":0.001425667,"threshold_uncertainty_score":0.9979282},"labels":[],"label_agreement":null},{"id":"W2492545673","doi":"10.4018/978-1-4666-9680-8.ch011","title":"Effective Feedback in Online Learning","year":2015,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Peer feedback; Quality (philosophy); Online learning; Multimedia; Component (thermodynamics); Psychology; Mathematics education","score_opus":0.026308220738459686,"score_gpt":0.33023002523297734,"score_spread":0.30392180449451767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492545673","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036002502,0.11779392,0.00008907058,0.009861743,0.0024156407,0.0020982083,0.000056664787,0.0005312979,0.8635532],"genre_scores_gemma":[0.019577453,0.3074978,0.030230083,0.000118472744,0.0011082843,0.00048410372,0.00024189315,0.000095131996,0.6406468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983576,0.000063607884,0.0003562866,0.00045639684,0.0004771976,0.00028890578],"domain_scores_gemma":[0.99901813,0.0004070522,0.00022440767,0.000120740806,0.00018622792,0.000043444143],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036344773,0.00029126843,0.0003619273,0.00046204464,0.0002732177,0.00005956352,0.00029262324,0.00042576168,0.00022898942],"category_scores_gemma":[0.00039620552,0.0003034734,0.000047407204,0.00016919187,0.0013413115,0.0014935309,0.0001285677,0.0006973376,0.000015358899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008019656,0.000042070824,0.0038411408,0.0000242696,0.000020416941,0.0000033828196,0.0006288737,0.00019175815,0.000003594379,0.88527375,0.0005684606,0.109322086],"study_design_scores_gemma":[0.00020848413,0.000093106275,0.0031053629,0.000166151,0.0000071496643,0.0000074380505,0.007719815,0.0000035835485,0.0000029787568,0.39890572,0.5895232,0.0002570196],"about_ca_topic_score_codex":0.000053910262,"about_ca_topic_score_gemma":0.00082007574,"teacher_disagreement_score":0.58895475,"about_ca_system_score_codex":0.00055790157,"about_ca_system_score_gemma":0.00044027838,"threshold_uncertainty_score":0.99994177},"labels":[],"label_agreement":null},{"id":"W2493216399","doi":"10.1007/978-3-319-17727-4_23-1","title":"Structural Assessment of Knowledge as, of, and for Learning","year":2016,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Summative assessment; Grading (engineering); Computer science; Knowledge survey; Knowledge transfer; Knowledge management; Engineering; Psychology; Mathematics education","score_opus":0.05211381892530292,"score_gpt":0.40406893827398954,"score_spread":0.3519551193486866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2493216399","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017409498,0.000262551,0.00011164821,0.00009460891,0.00020852755,0.0003542918,0.000009694465,0.0000183586,0.99719936],"genre_scores_gemma":[0.21734796,0.00028776826,0.00074291567,0.0000049797077,0.00021175732,0.000004470171,0.0000048832326,0.000013927763,0.78138137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916357,0.000021823118,0.00023679965,0.00017595712,0.00025798054,0.00014388426],"domain_scores_gemma":[0.999138,0.00029752767,0.00025449606,0.00007676638,0.00018246977,0.000050764233],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032530248,0.00013075721,0.00032079945,0.000073919255,0.0001407566,0.000017057759,0.00015385392,0.00017250075,0.00149866],"category_scores_gemma":[0.000032126525,0.000096956894,0.000108566135,0.000014068424,0.00028068633,0.00006575037,0.00007487034,0.000093480914,0.00000498258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060912357,0.0000035904927,0.003537597,0.000043653632,0.00006447267,1.17035015e-7,0.001032889,6.3894234e-8,0.000040314768,0.9802611,0.00035223874,0.014657879],"study_design_scores_gemma":[0.001664061,0.00068901,0.011408868,0.0005516866,0.00028244333,5.615317e-7,0.0033796027,0.00006709534,0.000055711324,0.14127898,0.83985406,0.00076791906],"about_ca_topic_score_codex":0.00006320836,"about_ca_topic_score_gemma":0.00019692711,"teacher_disagreement_score":0.8395018,"about_ca_system_score_codex":0.000045656037,"about_ca_system_score_gemma":0.00021721791,"threshold_uncertainty_score":0.9994141},"labels":[],"label_agreement":null},{"id":"W2493760347","doi":"","title":"Students' Perceptions of Assessment and Feedback in Higher Education","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Perception; Psychology; Higher education; Mathematics education; Medical education; Pedagogy; Political science; Medicine","score_opus":0.03813233689198699,"score_gpt":0.414825810401811,"score_spread":0.376693473509824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2493760347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84096515,0.000020345573,0.000026801274,0.003937403,0.00024174032,0.00015405696,7.6649064e-7,0.000014270391,0.15463948],"genre_scores_gemma":[0.95284784,0.00019673587,0.0005363043,0.00007965617,0.00008791921,0.000017381897,6.0011035e-7,0.0000032727212,0.046230316],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99924314,0.000071412134,0.00013571708,0.00011934065,0.00030609436,0.00012426636],"domain_scores_gemma":[0.99971664,0.00007187133,0.00003943134,0.00007697279,0.000046982208,0.000048107817],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003056047,0.000049793813,0.00008622176,0.000070609836,0.00007211484,0.000031082545,0.00013781092,0.000040597628,0.004506397],"category_scores_gemma":[0.000007247435,0.000034260174,0.00001980582,0.00014095659,0.00012559221,0.00018769746,0.000047606572,0.000028313196,0.000024706751],"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":[0.0000018137383,0.00017514368,0.93875635,0.0000018981927,0.000004896725,6.142479e-8,0.0013345889,1.8780371e-8,0.00065638754,0.050638784,0.0009855414,0.007444491],"study_design_scores_gemma":[0.00029346248,0.000017114415,0.9860652,0.00002379366,0.000005326599,3.2058203e-8,0.0075704567,1.4084996e-7,0.0000048524325,0.0010873638,0.0048766728,0.000055553424],"about_ca_topic_score_codex":0.000569399,"about_ca_topic_score_gemma":0.00075455365,"teacher_disagreement_score":0.11188268,"about_ca_system_score_codex":0.000109625355,"about_ca_system_score_gemma":0.0001343326,"threshold_uncertainty_score":0.99640363},"labels":[],"label_agreement":null},{"id":"W2494203092","doi":"10.4018/978-1-59904-337-1.ch010","title":"Assessment and Evaluation","year":2007,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Accountability; Peer assessment; Product (mathematics); Psychology; Online assessment; Authentic assessment; Quantitative assessment; Power (physics); Pedagogy; Public relations; Engineering ethics; Engineering; Political science; Formative assessment","score_opus":0.0740225412028311,"score_gpt":0.4119845652970274,"score_spread":0.33796202409419634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494203092","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00066109997,0.00035534325,0.000040529805,0.00010228831,0.0006862169,0.0006768317,0.000015375708,0.00007779468,0.99738455],"genre_scores_gemma":[0.59734917,0.00008481534,0.0011567271,0.0005495792,0.0016060291,0.00002869191,0.000012565856,0.000040334024,0.3991721],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976563,0.00004902718,0.00024665103,0.00035224287,0.0013922331,0.00030358485],"domain_scores_gemma":[0.9992205,0.000056444198,0.0001740663,0.0001832907,0.00020942092,0.0001562766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001273623,0.00022945898,0.00025340507,0.000056903933,0.0003313011,0.0001665997,0.00020196509,0.00037608255,0.00040824458],"category_scores_gemma":[0.000014297401,0.00023889482,0.000096604424,0.000017210767,0.0002317751,0.000055257435,0.00009337396,0.00019344912,0.00008143713],"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":[0.0000046553905,0.0000052579285,0.00087556464,0.0000046933947,0.000050325107,0.0000064154824,0.00032623738,1.1052144e-7,0.0000011978493,0.96999854,0.0013855377,0.027341492],"study_design_scores_gemma":[0.000701873,0.00008502097,0.014274923,0.00012682048,0.00034950674,0.000002456105,0.0007106439,0.00001818932,7.836474e-7,0.68185335,0.30126968,0.0006067334],"about_ca_topic_score_codex":0.00034270945,"about_ca_topic_score_gemma":0.0019076704,"teacher_disagreement_score":0.5982124,"about_ca_system_score_codex":0.0008018825,"about_ca_system_score_gemma":0.0006015768,"threshold_uncertainty_score":0.9741848},"labels":[],"label_agreement":null},{"id":"W2494774283","doi":"10.4018/978-1-4666-2110-7.ch016","title":"Community of Inquiry Framework, Digital Technologies, and Student Assessment in Higher Education","year":2012,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Mount Royal University","funders":"","keywords":"Peer assessment; Memorization; Mathematics education; Reflection (computer programming); Peer feedback; Higher education; Computer science; Pedagogy; Psychology; Political science","score_opus":0.07475372496962068,"score_gpt":0.38591376788283255,"score_spread":0.31116004291321187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494774283","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015237542,0.0012232999,0.0000068652357,0.0003568362,0.0009991648,0.00051658007,0.00002887087,0.00010653552,0.9815243],"genre_scores_gemma":[0.96410406,0.00009379773,0.00028583655,0.00005936867,0.00022857178,0.000024803394,0.0000068041813,0.000016146054,0.035180625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998439,0.00007173239,0.00037032075,0.00021379904,0.00060064247,0.00030452036],"domain_scores_gemma":[0.99903417,0.00011622884,0.00028959318,0.00038564904,0.00009382435,0.000080551516],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040257472,0.00026060554,0.00040440305,0.00010536839,0.0001782282,0.00014406275,0.0005748388,0.0006552247,0.00007736429],"category_scores_gemma":[0.00002543807,0.00026429427,0.00008065405,0.000045146575,0.00064568163,0.0001492131,0.0005083673,0.0007989358,0.000012402971],"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":[0.0000062783283,0.0001374382,0.043513943,0.00002276498,0.000048916412,0.0000011092847,0.0025745763,3.76398e-8,9.4866783e-7,0.9296056,0.00043948743,0.023648897],"study_design_scores_gemma":[0.0003006579,0.000111590874,0.09550755,0.00054056,0.000085153995,9.211576e-7,0.022840852,7.786452e-8,0.0000012075826,0.8127038,0.06740943,0.00049818493],"about_ca_topic_score_codex":0.0005584392,"about_ca_topic_score_gemma":0.0005355082,"teacher_disagreement_score":0.9488665,"about_ca_system_score_codex":0.0005951504,"about_ca_system_score_gemma":0.00043202747,"threshold_uncertainty_score":0.9999809},"labels":[],"label_agreement":null},{"id":"W2496700758","doi":"10.1007/978-3-319-39211-0_14","title":"Assessment for Learning: A Framework for Educators’ Professional Growth and Evaluation Cycles","year":2016,"lang":"en","type":"book-chapter","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Professional development; Professional learning community; Psychology; Engineering ethics; Knowledge management; Mathematics education; Computer science; Pedagogy; Engineering","score_opus":0.045348998370124655,"score_gpt":0.41359797986238844,"score_spread":0.3682489814922638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2496700758","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010732477,0.002545724,0.084785804,0.01995232,0.014787596,0.022087833,0.00031227176,0.00032643572,0.84446955],"genre_scores_gemma":[0.76465833,0.0008819079,0.028213844,0.0002959159,0.0021442159,0.0017018126,0.00013003348,0.00019013707,0.20178378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99609005,0.00021844897,0.00068416394,0.0006920942,0.0017448552,0.0005703809],"domain_scores_gemma":[0.9942132,0.0033386145,0.0010493282,0.00035079403,0.00088758447,0.0001604523],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0041223727,0.00045457942,0.00063115207,0.00023904195,0.001238494,0.00020726658,0.0005627285,0.00053988094,0.00046808063],"category_scores_gemma":[0.00024927047,0.00032531214,0.00036418813,0.00007667794,0.00043572902,0.00019761037,0.0001854867,0.00053346157,0.0000041476483],"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":[0.000064150874,0.0001374451,0.0022114082,0.00017467215,0.00038342638,3.3649096e-7,0.003396905,0.0000029306773,0.000088703644,0.9852453,0.0021246485,0.006170069],"study_design_scores_gemma":[0.0026481366,0.0009458947,0.008586664,0.0023292538,0.0011475026,0.0000010668413,0.015895823,0.0001976944,0.000026318989,0.6654832,0.30148536,0.0012530737],"about_ca_topic_score_codex":0.000027604552,"about_ca_topic_score_gemma":0.000055811277,"teacher_disagreement_score":0.75392586,"about_ca_system_score_codex":0.00046082516,"about_ca_system_score_gemma":0.002683265,"threshold_uncertainty_score":0.9999199},"labels":[],"label_agreement":null},{"id":"W2506618750","doi":"10.4018/978-1-59140-732-4.ch001","title":"Research Styles and the Internet","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"The Internet; Research data; Internet research; Online research methods; Computer science; Political science; Internet privacy; World Wide Web; Data science","score_opus":0.08498205871038783,"score_gpt":0.3763165802994835,"score_spread":0.2913345215890957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2506618750","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028489047,0.0007867934,0.000003893202,0.0003412463,0.0002815185,0.000479836,0.000011744311,0.00004914301,0.99776095],"genre_scores_gemma":[0.38413477,0.00011028943,0.000019215664,0.0001308923,0.00045790512,0.000013590893,5.8619895e-7,0.0000129776645,0.61511976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981552,0.00016606829,0.00018813083,0.00030289416,0.0008191271,0.0003686209],"domain_scores_gemma":[0.9991929,0.00020405499,0.000089678055,0.00024302228,0.00015528023,0.00011505226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001484099,0.00018003832,0.00025910133,0.00004693008,0.00040056946,0.0002502471,0.0006415299,0.00028945607,0.00036497114],"category_scores_gemma":[0.000041235693,0.00012462778,0.00010875265,0.000018882854,0.0021359867,0.000037361297,0.00039071275,0.0004145293,0.0003266726],"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":[0.00005797477,0.0000031520494,0.00014892587,0.0000042192755,0.000062577135,0.000007869552,0.0036794785,1.9193018e-9,1.0444938e-7,0.9798974,0.0131006725,0.0030376501],"study_design_scores_gemma":[0.00033707308,0.000029146047,0.00018844537,0.000060686078,0.000032125557,0.0000010279626,0.0012829608,2.7329264e-7,5.6074447e-7,0.6657105,0.3322206,0.00013654243],"about_ca_topic_score_codex":0.0040306845,"about_ca_topic_score_gemma":0.0053643147,"teacher_disagreement_score":0.3838499,"about_ca_system_score_codex":0.00014127052,"about_ca_system_score_gemma":0.00019153331,"threshold_uncertainty_score":0.78701323},"labels":[],"label_agreement":null},{"id":"W2509141998","doi":"10.1080/14926150309556551","title":"Developing classroom‐focused research in technology education","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Sociology; Engineering ethics; Engineering","score_opus":0.06727428818462765,"score_gpt":0.4098745844057686,"score_spread":0.34260029622114097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509141998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9529035,0.0008453169,0.00014478054,0.02480075,0.00080123084,0.00022457667,1.7442828e-7,0.000010237401,0.020269444],"genre_scores_gemma":[0.9697376,0.00011877938,0.029801995,0.000036751226,0.00004098046,0.000013435979,1.2917079e-7,0.000004954357,0.00024537326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987514,0.000042712076,0.00029790498,0.00015074905,0.00032477616,0.00043244852],"domain_scores_gemma":[0.9984845,0.000056656554,0.0001701866,0.00014160316,0.0009473406,0.00019974259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035080526,0.000067573164,0.00013584169,0.004580823,0.0009092373,0.00014347037,0.00053325575,0.00016467903,0.000023923538],"category_scores_gemma":[0.0016309243,0.0000661594,0.0000122235615,0.0051617343,0.0026284184,0.00030540416,0.000018619321,0.0003417998,0.000006724089],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[2.2132188e-7,0.00005023187,0.045298398,0.00000854624,0.0000020102632,0.0000013375715,0.0053969002,8.774694e-8,0.00023267753,0.9193,0.00018275675,0.029526807],"study_design_scores_gemma":[0.00012515816,0.000049993643,0.0026034834,0.0002488028,0.000005700388,0.00004397084,0.24887447,0.000006439589,0.00050593686,0.7209477,0.026465496,0.00012290044],"about_ca_topic_score_codex":0.0007125494,"about_ca_topic_score_gemma":0.01160481,"teacher_disagreement_score":0.24347757,"about_ca_system_score_codex":0.00078662473,"about_ca_system_score_gemma":0.030732676,"threshold_uncertainty_score":0.97476214},"labels":[],"label_agreement":null},{"id":"W2510347771","doi":"10.1021/acs.jchemed.6b00028","title":"Score Increase and Partial-Credit Validity When Administering Multiple-Choice Tests Using an Answer-Until-Correct Format","year":2016,"lang":"en","type":"article","venue":"Journal of Chemical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"Brock University","keywords":"Allotment; Test (biology); Post hoc; Multiple choice; Econometrics; Polytomous Rasch model; Statistics; Actuarial science; Computer science; Psychology; Mathematics; Economics; Medicine; Psychometrics; Internal medicine; Item response theory","score_opus":0.09711035673035426,"score_gpt":0.3936019198884978,"score_spread":0.2964915631581435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510347771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972838,0.00005995072,0.00021875132,0.0008303779,0.0010867981,0.00009769727,0.0000018684807,0.000013026735,0.0004077237],"genre_scores_gemma":[0.99620813,0.00004148002,0.0012477209,0.00009419795,0.002327796,0.000002452064,0.0000018066722,0.000008649216,0.000067755595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99886507,0.000099309946,0.00033309308,0.00012220285,0.00037813338,0.00020220641],"domain_scores_gemma":[0.99854714,0.00047517067,0.00035259506,0.00009644713,0.00023354474,0.00029511258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006335465,0.00009795926,0.00016968712,0.0000681263,0.00014421334,0.00012199056,0.00018844611,0.000083646155,0.00011091556],"category_scores_gemma":[0.001803716,0.00007257398,0.000059274604,0.00008948369,0.00011712811,0.0011800798,0.00003705895,0.000111822905,0.0000024295346],"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":[0.00013588686,0.00053022767,0.78271246,0.000028103836,0.000026728907,0.0000022724873,0.00927846,4.3925513e-7,0.17930432,0.00006148654,0.002554718,0.025364881],"study_design_scores_gemma":[0.009088639,0.0013754221,0.55010515,0.0035391303,0.0010990064,0.00038331622,0.034877345,0.001099271,0.22994198,0.0066856816,0.15918565,0.0026194176],"about_ca_topic_score_codex":0.00028998917,"about_ca_topic_score_gemma":0.000049677074,"teacher_disagreement_score":0.23260733,"about_ca_system_score_codex":0.00018907592,"about_ca_system_score_gemma":0.0005067624,"threshold_uncertainty_score":0.29594812},"labels":[],"label_agreement":null},{"id":"W251327719","doi":"10.55016/ojs/ajer.v58i4.55670","title":"What assessment knowledge and skills do initial teacher education programs address? A Western Canadian perspective","year":2013,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Perspective (graphical); Psychology; Pedagogy; Knowledge level; Mathematics education; Perspective-taking; Teacher education; Educational assessment; Social psychology","score_opus":0.07173820836995133,"score_gpt":0.500320049850776,"score_spread":0.42858184148082473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W251327719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6705212,0.001714974,2.4726805e-7,0.04659949,0.0010034126,0.000544305,4.2834847e-7,7.0623247e-7,0.27961522],"genre_scores_gemma":[0.93395984,0.000754816,0.000102377075,0.00010418142,0.0017774794,0.000102339334,0.0000066686803,0.000012952794,0.063179314],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976114,0.00056927925,0.0002887122,0.000204679,0.0008346577,0.0004912716],"domain_scores_gemma":[0.99399817,0.0024899514,0.0001364386,0.0001221566,0.0025708762,0.0006823993],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014019851,0.000110047215,0.00015950327,0.0004974652,0.0006670593,0.0012999936,0.00042694862,0.00009962485,0.010958286],"category_scores_gemma":[0.0016469586,0.00009801841,0.00006331521,0.00046697524,0.0004025498,0.0016959739,0.000058513782,0.0005008577,0.00029684204],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010549961,0.0017031941,0.8083157,0.000011417787,0.00009912324,4.347536e-7,0.07874511,1.8176249e-7,0.000013900011,0.05828365,0.03854536,0.014271379],"study_design_scores_gemma":[0.0003583576,0.00020812634,0.6991064,0.0002694165,0.000027853257,0.000014401882,0.1968759,0.000003419189,0.0000025406646,0.0073401723,0.09560769,0.00018572122],"about_ca_topic_score_codex":0.34531385,"about_ca_topic_score_gemma":0.44660044,"teacher_disagreement_score":0.26343864,"about_ca_system_score_codex":0.0012793136,"about_ca_system_score_gemma":0.012981649,"threshold_uncertainty_score":0.9997367},"labels":[],"label_agreement":null},{"id":"W2517561083","doi":"10.22329/celt.v9i0.4442","title":"Is Fine Tuning Possible with Grade-Focused Students?","year":2016,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Formative assessment; Psychology; Summative assessment; Allegiance; Mathematics education; Pedagogy","score_opus":0.02298403361912248,"score_gpt":0.329031261894698,"score_spread":0.3060472282755755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517561083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89327484,0.00006010859,0.0005641093,0.0021422617,0.00013490397,0.00020557598,0.0000012855907,0.0002727682,0.10334415],"genre_scores_gemma":[0.9320561,0.000059163074,0.00041979345,0.000081866616,0.0001519807,0.000014506307,0.0000016328322,0.000024249972,0.06719069],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99791026,0.0004765073,0.00016236729,0.00036180776,0.0006545771,0.00043446198],"domain_scores_gemma":[0.9990113,0.000551981,0.00011795142,0.00011388125,0.000059891823,0.00014503021],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00094099954,0.00017787535,0.0002147505,0.00017234097,0.0023686655,0.00034956657,0.0002455414,0.000093057126,0.0002412646],"category_scores_gemma":[0.00033711139,0.000119352706,0.0000411605,0.0002805713,0.00014745968,0.00021425307,0.00007025736,0.0004562338,0.000030241641],"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":[0.00010919871,0.0001535388,0.9337226,0.000008003304,0.00010648173,0.000015648699,0.02673574,0.0000067790293,0.0007500185,0.008203588,0.0016783737,0.02851002],"study_design_scores_gemma":[0.020607397,0.0039197267,0.54251206,0.0031292066,0.00035211653,0.0000145611575,0.041409016,0.00057361147,0.00062277756,0.0024634493,0.3813541,0.0030419917],"about_ca_topic_score_codex":0.00033071963,"about_ca_topic_score_gemma":0.00024481976,"teacher_disagreement_score":0.39121056,"about_ca_system_score_codex":0.00010165862,"about_ca_system_score_gemma":0.000085701984,"threshold_uncertainty_score":0.9989301},"labels":[],"label_agreement":null},{"id":"W2520023658","doi":"","title":"Language Assessment Literacy as Professional Competence: The Case of Canadian Admissions Decision Makers","year":2016,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Literacy; Competence (human resources); Language assessment; Professional development; Psychology; Medical education; Pedagogy; Medicine; Social psychology","score_opus":0.18758794809744395,"score_gpt":0.6183511057041936,"score_spread":0.43076315760674966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520023658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9544618,0.002211287,0.000058891143,0.00377798,0.0012320232,0.0007447375,0.000080898215,0.000019016403,0.03741333],"genre_scores_gemma":[0.9921783,0.0032231365,0.0005312342,0.00041141876,0.00021168074,0.0000351939,0.000004595902,0.000021951113,0.0033824507],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967479,0.00064883835,0.0007020017,0.0003293402,0.0010664624,0.0005054345],"domain_scores_gemma":[0.99602896,0.0016411253,0.0006641686,0.0004333581,0.00047237854,0.00076001475],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026945255,0.00022091926,0.00044623148,0.0008916688,0.0012212038,0.0007859006,0.002666033,0.00012121757,0.03892067],"category_scores_gemma":[0.00093771983,0.00012628944,0.00018806744,0.0015087536,0.00032007077,0.0017967273,0.0006095351,0.0003046151,0.000028079654],"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":[0.0001595021,0.0003816128,0.73029447,0.000026582282,0.0002173669,0.0009164848,0.012304947,0.0000054476063,0.018891761,0.0068042553,0.10762938,0.12236818],"study_design_scores_gemma":[0.0010027384,0.000021768594,0.88540554,0.0013363549,0.00009876752,0.000053480355,0.015566028,0.00001671484,0.0010078256,0.0076290215,0.087411575,0.0004501745],"about_ca_topic_score_codex":0.18359074,"about_ca_topic_score_gemma":0.07587477,"teacher_disagreement_score":0.15511107,"about_ca_system_score_codex":0.00027342114,"about_ca_system_score_gemma":0.0021510106,"threshold_uncertainty_score":0.9619579},"labels":[],"label_agreement":null},{"id":"W2523280788","doi":"10.1080/10627197.2016.1236677","title":"Approaches to Classroom Assessment Inventory: A New Instrument to Support Teacher Assessment Literacy","year":2016,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Accountability; Literacy; Construct (python library); Educational assessment; Psychology; Construct validity; Mathematics education; Standards for Educational and Psychological Testing; Standardized test; Standards-based assessment; Process (computing); Authentic assessment; Pedagogy; Psychometrics; Higher education; Computer science; Political science; Education theory; Curriculum","score_opus":0.1328510477980371,"score_gpt":0.4138136676963231,"score_spread":0.28096261989828597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523280788","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30927852,0.000033405107,0.014911635,0.36437052,0.0045100856,0.003225704,0.00005206717,0.00025590978,0.30336216],"genre_scores_gemma":[0.82009065,0.000029956174,0.067322545,0.0022806055,0.0026613267,0.0011042957,0.00009056259,0.00006454351,0.106355526],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99369234,0.0005027596,0.00086074014,0.0011637593,0.0025868574,0.0011935503],"domain_scores_gemma":[0.9966627,0.00045192652,0.00030388124,0.0007284671,0.00026234594,0.0015906955],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002028214,0.00052702887,0.00049784157,0.0004921709,0.0007090205,0.00068553135,0.0011602287,0.00018273835,0.01548139],"category_scores_gemma":[0.0001594285,0.00044023775,0.00024995767,0.000910048,0.00014109148,0.0009534593,0.000465869,0.00033858125,0.00086905464],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002856046,0.0016464771,0.4679083,0.000016602367,0.00020546667,0.0000033929766,0.007234884,0.000015375812,0.0005151807,0.24789315,0.21180186,0.06273077],"study_design_scores_gemma":[0.0009153515,0.00040994148,0.5247065,0.00010793844,0.00005839437,0.0000015967586,0.003616989,0.000023775132,0.000027674914,0.004222504,0.46525434,0.00065501116],"about_ca_topic_score_codex":0.00081102573,"about_ca_topic_score_gemma":0.00052938797,"teacher_disagreement_score":0.5108121,"about_ca_system_score_codex":0.0042622015,"about_ca_system_score_gemma":0.008313227,"threshold_uncertainty_score":0.99990886},"labels":[],"label_agreement":null},{"id":"W2523536876","doi":"10.5539/ijel.v6n5p54","title":"The Effect of Using Automated Essay Evaluation on ESL Undergraduate Students’ Writing Skill","year":2016,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Grammar; Computer science; Mathematics education; Test (biology); Software; Second language writing; Relation (database); Academic writing; Artificial intelligence; Natural language processing; Psychology; Second language; Linguistics; Programming language","score_opus":0.02576910350022154,"score_gpt":0.41499898338215163,"score_spread":0.3892298798819301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523536876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94192034,0.00010263853,0.00021021602,0.00024866706,0.023674034,0.00023326828,0.000008671441,0.000044600383,0.033557564],"genre_scores_gemma":[0.99299246,0.0001036525,0.00016266013,0.000018477682,0.0066028517,0.0000013608828,0.000001034817,0.000009840178,0.0001076759],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99649566,0.00044694342,0.0005225205,0.00008907583,0.0022843215,0.00016146833],"domain_scores_gemma":[0.98409784,0.0023605204,0.00071717496,0.000081147664,0.0126869045,0.000056438275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043463856,0.00009506929,0.00015834763,0.00011638048,0.00020686079,0.00016260099,0.00067963626,0.000054202632,0.000027136432],"category_scores_gemma":[0.08951544,0.00005572595,0.000114157185,0.00010689898,0.00014384718,0.00007944053,0.000060600498,0.00012231797,0.0000029091052],"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":[0.0010702165,0.0004916848,0.8714366,0.000023127324,0.0020416495,0.000055285433,0.013888243,0.0023135755,0.00054978527,0.0742238,0.00830557,0.025600445],"study_design_scores_gemma":[0.051085092,0.005941637,0.36527732,0.009251968,0.0034135107,0.000010220363,0.029625848,0.020007668,0.013940064,0.03930961,0.45945463,0.0026824167],"about_ca_topic_score_codex":0.00002515029,"about_ca_topic_score_gemma":0.000021414016,"teacher_disagreement_score":0.5061593,"about_ca_system_score_codex":0.00045489235,"about_ca_system_score_gemma":0.00022982991,"threshold_uncertainty_score":0.91815394},"labels":[],"label_agreement":null},{"id":"W2527389382","doi":"10.26522/brocked.v25i1.483","title":"Knowledge Mobilization and Educational Research: Politics, Languages, and Responsibilities","year":2016,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"CLARITY; Mobilization; Politics; China; Political science; Political mobilization; Sociology; Law","score_opus":0.08644552274295823,"score_gpt":0.4706870418880458,"score_spread":0.38424151914508753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527389382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93477905,0.0041916235,0.000043502307,0.020532819,0.0007697163,0.00019417466,0.0000031727755,0.000014340398,0.039471593],"genre_scores_gemma":[0.86359286,0.0015610806,0.00043999974,0.000085033826,0.0018317885,0.000013718757,0.0000020457485,0.000007619409,0.13246584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873024,0.00044477073,0.00015827801,0.00013906835,0.00029790966,0.00022974556],"domain_scores_gemma":[0.99821335,0.00084560364,0.000058442696,0.000076310534,0.00054314843,0.00026314627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008206666,0.00005898117,0.00006553176,0.00022115142,0.00097614137,0.00021831138,0.00010514196,0.000051539377,0.0007249545],"category_scores_gemma":[0.0021519226,0.00004488977,0.00001645836,0.00016526299,0.00031672846,0.00036737384,0.000038282895,0.00010635136,0.000033891592],"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":[0.000030163103,0.00039868525,0.32208723,0.000028592747,0.000025906003,3.1268237e-7,0.06294484,6.257871e-8,0.001936892,0.36457872,0.20773642,0.04023218],"study_design_scores_gemma":[0.00038351238,0.00006475153,0.39500734,0.00016032436,0.00001235059,0.00003070623,0.14285313,6.448643e-7,0.00006011074,0.055707157,0.405558,0.00016198121],"about_ca_topic_score_codex":0.000112429065,"about_ca_topic_score_gemma":0.00022623071,"teacher_disagreement_score":0.30887157,"about_ca_system_score_codex":0.00018848352,"about_ca_system_score_gemma":0.0021478415,"threshold_uncertainty_score":0.7937743},"labels":[],"label_agreement":null},{"id":"W2530098379","doi":"","title":"What are the Learning Values of Grades? Exploring Grading Policies in Canada and China","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Internationalization; China; Christian ministry; Political science; Globalization; Academic achievement; Immigration; Mathematics education; Pedagogy; Psychology; Business","score_opus":0.06302609960879271,"score_gpt":0.3195045298828628,"score_spread":0.25647843027407013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530098379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922412,0.00017053008,0.000007366326,0.0039845197,0.00019675432,0.00006167334,1.6798367e-7,0.0000102299655,0.0033275678],"genre_scores_gemma":[0.99666244,0.0020374423,0.00001001752,0.00002901851,0.000060247734,0.000005358098,5.5094866e-8,0.0000031470217,0.001192279],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993279,0.00008463191,0.00009698457,0.00007947411,0.00023505311,0.00017595696],"domain_scores_gemma":[0.9996352,0.000218994,0.000055729808,0.00004707862,0.0000130856915,0.000029908995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031187167,0.000048874244,0.000088252345,0.000032439588,0.00021105917,0.00006488857,0.00012478564,0.000011881281,0.00003605649],"category_scores_gemma":[0.00007941124,0.000026200614,0.000014095918,0.00013715572,0.000099801386,0.00047349968,0.000045438384,0.000047579117,4.4170702e-7],"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":[0.0000011567239,0.0000025454478,0.9686283,0.0000021317246,0.000004745015,5.642083e-7,0.02178561,0.0000024452963,0.00008752809,0.0049019405,0.000057723704,0.004525348],"study_design_scores_gemma":[0.00008459198,0.0000052182327,0.74932265,0.00007124517,0.0000023767739,7.78436e-8,0.24904808,0.000004762411,0.00014963665,0.0006168106,0.000647582,0.0000469357],"about_ca_topic_score_codex":0.9150859,"about_ca_topic_score_gemma":0.9689428,"teacher_disagreement_score":0.22726248,"about_ca_system_score_codex":0.00011417734,"about_ca_system_score_gemma":0.00010263766,"threshold_uncertainty_score":0.16233179},"labels":[],"label_agreement":null},{"id":"W2530320759","doi":"10.5539/elt.v9n11p38","title":"Students and the Teacher’s Perceptions on Incorporating the Blog Task and Peer Feedback into EFL Writing Classes Through Blogs","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Task (project management); Psychology; Perception; Construct (python library); Collaborative writing; Second language writing; Peer feedback; Mathematics education; English as a foreign language; Focus group; Pedagogy; Computer science; Second language; Linguistics","score_opus":0.01755278614143207,"score_gpt":0.3458826899913446,"score_spread":0.3283299038499125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530320759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93913025,0.00024379442,0.00015292036,0.0054719513,0.00025300682,0.00037227003,0.000003259005,0.00014775741,0.054224823],"genre_scores_gemma":[0.99415416,0.00008305513,0.00059343094,0.0005059341,0.0014426936,0.00003737823,0.0000033247356,0.00002309285,0.0031569512],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9969837,0.0012310673,0.0002607372,0.00034813676,0.0007944871,0.00038187418],"domain_scores_gemma":[0.9975912,0.0018560208,0.0001555742,0.00026282526,0.00006229789,0.00007210084],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005163801,0.00019962786,0.00021471838,0.000040699153,0.002580598,0.0006726574,0.0005208304,0.00010275594,0.00007175604],"category_scores_gemma":[0.0026206928,0.00010009223,0.00006550238,0.00011771745,0.0007921928,0.0004774236,0.00035558784,0.0005675089,0.00001186944],"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":[0.000021328176,0.000064721506,0.12681836,0.0000062696267,0.000050779738,0.0000031826892,0.79347336,5.1892334e-7,0.00044690125,0.0622324,0.0005790663,0.016303094],"study_design_scores_gemma":[0.0018174857,0.00005367504,0.027654082,0.00014192752,0.00007375888,0.000001515748,0.9619134,0.000018052271,0.00001104299,0.0038586797,0.0041855318,0.00027084618],"about_ca_topic_score_codex":0.001783879,"about_ca_topic_score_gemma":0.0013311575,"teacher_disagreement_score":0.16844001,"about_ca_system_score_codex":0.00008602293,"about_ca_system_score_gemma":0.000028586175,"threshold_uncertainty_score":0.9987179},"labels":[],"label_agreement":null},{"id":"W2546528314","doi":"10.5430/jnep.v7n3p94","title":"Nurse teachers’ conceptions and practices of written feedback in Karachi","year":2016,"lang":"en","type":"article","venue":"Journal of Nursing Education and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workload; Nurse educator; Medical education; Sample (material); Psychology; Nurse education; Distraction; Nursing; Medicine; Pedagogy; Computer science","score_opus":0.09877677895829202,"score_gpt":0.4965999707333705,"score_spread":0.39782319177507847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546528314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83006585,0.0015393532,0.00005134679,0.09982646,0.0008346006,0.000103625986,6.560843e-7,0.0000041781127,0.06757394],"genre_scores_gemma":[0.99337363,0.0018664981,0.0029668584,0.00016674172,0.00033220643,0.0000011138349,2.1474135e-7,0.000004004413,0.0012887357],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9988442,0.00047992615,0.0002601984,0.00007728531,0.00024015328,0.000098236014],"domain_scores_gemma":[0.9970638,0.0014891833,0.00106442,0.000051101506,0.0002470262,0.000084428815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017311913,0.00005269065,0.00011921859,0.00012381782,0.00017355772,0.00005852235,0.00007999457,0.000053090043,0.00006525506],"category_scores_gemma":[0.0029666158,0.000039434355,0.000021875021,0.00015380088,0.0002455696,0.0015597262,0.000006193576,0.00013113659,0.000001961449],"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":[0.00031711473,0.0024040565,0.13023515,0.000011788099,0.000056454355,0.0000024461124,0.37648457,3.3330352e-7,0.003350269,0.012568327,0.010685787,0.4638837],"study_design_scores_gemma":[0.0008528777,0.00016346919,0.3964962,0.00057983777,0.00014799318,0.00013259996,0.47265947,0.0000011127557,0.000018758808,0.001475716,0.1273652,0.00010675228],"about_ca_topic_score_codex":0.00014177793,"about_ca_topic_score_gemma":0.000038442293,"teacher_disagreement_score":0.46377695,"about_ca_system_score_codex":0.00009435987,"about_ca_system_score_gemma":0.00040511505,"threshold_uncertainty_score":0.35515305},"labels":[],"label_agreement":null},{"id":"W2547886194","doi":"","title":"Exploring Assessment Literacy","year":2016,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Literacy; Dual (grammatical number); Service (business); Professional development; Pedagogy; Mathematics education; Psychology; Engineering ethics; Sociology; Computer science; Linguistics; Business; Engineering","score_opus":0.10488469311012355,"score_gpt":0.44300809837082267,"score_spread":0.3381234052606991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547886194","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32343262,0.000019832398,0.00004034661,0.0041567995,0.0025663946,0.00012897888,0.000001154655,0.000042711836,0.66961116],"genre_scores_gemma":[0.9750173,0.00005202243,0.0006919351,0.00010237494,0.0007251194,0.000042254975,3.6845938e-7,0.0000040952646,0.023364494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984976,0.000058324767,0.00016432995,0.00020246232,0.0008057389,0.00027153685],"domain_scores_gemma":[0.9992489,0.00007798718,0.00012576449,0.00010059127,0.0003480384,0.00009869706],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007957697,0.000062152416,0.00008892538,0.0001173896,0.00074141996,0.00009834169,0.00043655132,0.00002536735,0.001320856],"category_scores_gemma":[0.000040678184,0.000047793732,0.000042125543,0.00083131547,0.00086943,0.00159283,0.000054986824,0.000036938272,0.000044566958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016150578,0.00010912846,0.02520227,0.0000024605295,0.0000024646833,5.027843e-8,0.013239485,8.952708e-9,0.0070437784,0.92175156,0.00076688675,0.031880297],"study_design_scores_gemma":[0.00008341116,0.000010395793,0.7685863,0.000019461375,0.00000408909,2.2330768e-8,0.002537124,5.706346e-8,0.00029108583,0.0016503929,0.22674063,0.00007707438],"about_ca_topic_score_codex":0.00018348046,"about_ca_topic_score_gemma":0.0000019448746,"teacher_disagreement_score":0.92010117,"about_ca_system_score_codex":0.00033100366,"about_ca_system_score_gemma":0.0011395109,"threshold_uncertainty_score":0.99959207},"labels":[],"label_agreement":null},{"id":"W2552734705","doi":"10.3968/8877","title":"An Overview of Studies Conducted on Washback, Impact and Validity","year":2016,"lang":"en","type":"article","venue":"Studies in literature and language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test of English as a Foreign Language; Language assessment; Test (biology); Psychology; English language; Mathematics education; China; Pedagogy; Political science","score_opus":0.1500407982298959,"score_gpt":0.49733186619505443,"score_spread":0.3472910679651585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552734705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8551471,0.14290215,1.5831614e-7,0.00033575908,0.00017096313,0.00012951787,0.00001847117,0.00001586552,0.001279978],"genre_scores_gemma":[0.9528309,0.0463759,0.00004386759,0.00010924775,0.00017428347,0.0000070140563,0.0000020087618,0.0000047568064,0.0004520089],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9990832,0.00021040613,0.00014743056,0.00019861294,0.00017607967,0.0001842597],"domain_scores_gemma":[0.9993147,0.00036172927,0.000061909595,0.0001222193,0.00009338002,0.000046044242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051449344,0.0001251318,0.00030723604,0.00007059696,0.00013169168,0.00003455707,0.000083374245,0.000059555274,0.00002298985],"category_scores_gemma":[0.00025460063,0.00006711943,0.00003481997,0.00021421326,0.00046217698,0.00025528867,0.000059855978,0.00007526092,8.5815265e-7],"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":[0.0001111743,0.00014613094,0.13881578,0.00029484808,0.00036314566,0.000054736374,0.82400745,7.4921445e-8,0.0031689112,0.019674674,0.0029579042,0.010405156],"study_design_scores_gemma":[0.004053362,0.0018261943,0.42729387,0.0052214013,0.00016175704,0.0000053244057,0.538206,0.0000010323392,0.0008473154,0.011638209,0.009865802,0.0008797824],"about_ca_topic_score_codex":0.00005510808,"about_ca_topic_score_gemma":0.00041598908,"teacher_disagreement_score":0.28847808,"about_ca_system_score_codex":0.000039716662,"about_ca_system_score_gemma":0.00001481465,"threshold_uncertainty_score":0.2737051},"labels":[],"label_agreement":null},{"id":"W2554401887","doi":"10.5539/elt.v9n12p79","title":"Graduate Students’ Needs and Preferences for Written Feedback on Academic Writing","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Graduate students; Preference; Constructive; Mathematics education; Academic writing; English for academic purposes; Medical education; Higher education; Pedagogy; Computer science; Process (computing); Medicine","score_opus":0.0443805151304807,"score_gpt":0.36799825618220555,"score_spread":0.32361774105172486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554401887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97051495,0.0001932212,0.00014975473,0.00079291005,0.00044801968,0.00043167942,0.000011911619,0.00023867005,0.027218856],"genre_scores_gemma":[0.99353904,0.0001305216,0.000425101,0.00021452772,0.001764033,0.00005012346,0.0000051093107,0.000023181161,0.0038483546],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99810207,0.00026396543,0.00024168941,0.0002980868,0.0006123843,0.00048177992],"domain_scores_gemma":[0.9985471,0.0010204918,0.000111717076,0.00014302843,0.000046086392,0.00013160633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023697305,0.00017160532,0.00020229345,0.00013589577,0.0006681151,0.00022817877,0.0004902594,0.00012929566,0.00005440067],"category_scores_gemma":[0.0012795931,0.00012447627,0.00006590591,0.00011454502,0.00012692694,0.00044248672,0.000120148754,0.00038307323,0.000014634557],"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":[0.000044136363,0.00006979619,0.22048998,0.000021804504,0.000062117986,0.000003578315,0.63347244,3.0678066e-7,0.0012452311,0.017034296,0.001888311,0.125668],"study_design_scores_gemma":[0.002551927,0.00022906452,0.05182575,0.000526224,0.0000737203,6.0331195e-7,0.9255206,0.000005952041,0.00031362515,0.0014915278,0.016796466,0.0006645317],"about_ca_topic_score_codex":0.00021727914,"about_ca_topic_score_gemma":0.000109233806,"teacher_disagreement_score":0.29204816,"about_ca_system_score_codex":0.000081378246,"about_ca_system_score_gemma":0.000029129933,"threshold_uncertainty_score":0.51386684},"labels":[],"label_agreement":null},{"id":"W2555293682","doi":"10.5539/hes.v6n4p181","title":"Students’ and Teacher’s Experiences of the Validity and Reliability of Assessment in a Bioscience Course","year":2016,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Reliability (semiconductor); Recall; Validity; Perception; Mathematics education; Alternative assessment; Quality (philosophy); Medical education; Test validity; Psychometrics; Developmental psychology; Medicine; Cognitive psychology","score_opus":0.09076394953386803,"score_gpt":0.4697572589009536,"score_spread":0.3789933093670856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555293682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99404097,0.00053883105,0.0000012197496,0.0031970658,0.00070034,0.00019250253,8.114403e-7,0.000005190528,0.0013230947],"genre_scores_gemma":[0.99714404,0.0007401257,0.00011222402,0.000028870916,0.000038808506,0.000060000923,4.163026e-8,0.0000016389426,0.0018742192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99891484,0.00020683356,0.00019349916,0.0001717811,0.00040614067,0.00010693124],"domain_scores_gemma":[0.99931693,0.00023714232,0.00014149095,0.00012521837,0.00015139132,0.00002780938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093588565,0.000062191015,0.00014513277,0.000029763652,0.00016343758,0.0000162729,0.00019295595,0.000025354846,0.000045555207],"category_scores_gemma":[0.00008348546,0.000033593533,0.00001904366,0.00021959958,0.0013319165,0.00015677963,0.00014167733,0.000034722623,2.577932e-7],"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":[0.0000021539659,0.00025598868,0.9468699,0.000009593054,0.0000050353387,1.4589997e-8,0.049945414,1.830086e-8,0.00010260317,0.0022743028,0.00030998175,0.00022499352],"study_design_scores_gemma":[0.00011177352,0.000019619672,0.81800264,0.000045828907,0.000008663002,2.7148047e-8,0.1801967,6.273946e-8,0.000049962673,0.0005865112,0.0009401964,0.000038004924],"about_ca_topic_score_codex":0.00020371754,"about_ca_topic_score_gemma":0.00008947105,"teacher_disagreement_score":0.13025129,"about_ca_system_score_codex":0.00006337015,"about_ca_system_score_gemma":0.00019499831,"threshold_uncertainty_score":0.4907502},"labels":[],"label_agreement":null},{"id":"W2556416203","doi":"10.5430/jnep.v7n4p55","title":"Effect of peer evaluation training on senior nursing students’ performance enrolled in nursing administration course","year":2016,"lang":"en","type":"article","venue":"Journal of Nursing Education and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Checklist; Nursing; Nurse education; Test (biology); Medicine; Psychology; Scale (ratio); Medical education","score_opus":0.09115151949713247,"score_gpt":0.5404954326644517,"score_spread":0.4493439131673192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556416203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9436591,0.00022170083,0.000064830114,0.021434452,0.0018182143,0.0002941036,3.6437726e-7,0.0000052380187,0.032501947],"genre_scores_gemma":[0.9984032,0.00020381586,0.0004782054,0.000056258643,0.0004700016,0.0000044699914,0.0000011262501,0.000007646159,0.00037528202],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967621,0.001300039,0.00039933788,0.00011873944,0.0012595018,0.0001603046],"domain_scores_gemma":[0.9968107,0.001672681,0.00075137615,0.00007250471,0.00060663855,0.000086134016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008712206,0.00009659661,0.00020168476,0.00020328604,0.00028126562,0.00008806364,0.00011928033,0.00009633771,0.00004394008],"category_scores_gemma":[0.0024841547,0.000073231895,0.000044828143,0.00023376849,0.00015226952,0.0010874628,0.00000272972,0.00020211555,0.000001986686],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014720213,0.0019029931,0.008672939,0.00000882295,0.000022228727,7.452639e-7,0.10721216,0.0000051265583,0.00096209336,0.00053330744,0.00088594935,0.8783216],"study_design_scores_gemma":[0.009838432,0.0056932806,0.6450662,0.019560602,0.0014787082,0.0003104681,0.30963755,0.00024122992,0.002036324,0.0010698255,0.0045443997,0.00052298],"about_ca_topic_score_codex":0.000005186608,"about_ca_topic_score_gemma":0.0000026880018,"teacher_disagreement_score":0.8777986,"about_ca_system_score_codex":0.00056190486,"about_ca_system_score_gemma":0.000973265,"threshold_uncertainty_score":0.3019494},"labels":[],"label_agreement":null},{"id":"W2559480382","doi":"10.5539/ijel.v6n7p99","title":"The Impact of Student-Based Instruction on Improving IBT TOEFL Scores of Iranian Students","year":2016,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test of English as a Foreign Language; Class (philosophy); Psychology; Mathematics education; Test (biology); Significant difference; Qualitative research; Control (management); Qualitative property; Medical education; English language; Computer science; Medicine; Sociology","score_opus":0.023862006187260646,"score_gpt":0.38996538785848867,"score_spread":0.366103381671228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559480382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9812356,0.00003764288,0.00011098406,0.00004714062,0.010362308,0.000094151386,0.000019039808,0.0000075456073,0.008085549],"genre_scores_gemma":[0.9944631,0.00010042553,0.00017055243,0.000010770522,0.005172549,7.675771e-7,7.046216e-7,0.000008468782,0.00007269044],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99752504,0.000102624,0.00057261233,0.000082626284,0.0015705118,0.0001465866],"domain_scores_gemma":[0.98771584,0.00068607484,0.00092458795,0.000099335346,0.01050768,0.000066456174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009770774,0.0000947099,0.000175085,0.00015686243,0.000109530585,0.00009738601,0.00096302474,0.000052352072,0.000042995667],"category_scores_gemma":[0.021440245,0.000054619715,0.00020737709,0.00010190733,0.00021465003,0.000076921424,0.000058417638,0.00012331238,0.0000011807017],"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":[0.0005510686,0.0004937704,0.97099435,0.0000056385666,0.00052295305,0.000008845362,0.004122739,0.00021103516,0.00040610344,0.011587197,0.00088572415,0.010210553],"study_design_scores_gemma":[0.0055867885,0.0013736332,0.9707166,0.0005727267,0.000114657116,4.4978665e-7,0.006632534,0.000029837709,0.0019390613,0.0017079224,0.011083056,0.00024272343],"about_ca_topic_score_codex":0.0001560743,"about_ca_topic_score_gemma":0.000068585636,"teacher_disagreement_score":0.020463169,"about_ca_system_score_codex":0.00027519613,"about_ca_system_score_gemma":0.00030065727,"threshold_uncertainty_score":0.9868026},"labels":[],"label_agreement":null},{"id":"W2568968076","doi":"10.1177/1362168816684366","title":"Developing the assessment literacy of teachers in Chinese language classrooms: A focus on assessment task design","year":2017,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Calgary","funders":"","keywords":"Task (project management); Literacy; Psychology; Mathematics education; Professional development; Pedagogy; Task analysis; Authentic assessment; Quality (philosophy); Faculty development; Language assessment; Curriculum","score_opus":0.09606259991720532,"score_gpt":0.5312202756607064,"score_spread":0.43515767574350106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568968076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8886061,0.00020536227,0.002660341,0.0070430865,0.00020669293,0.0010643173,0.000005694693,0.00006248024,0.10014596],"genre_scores_gemma":[0.9879083,0.000059057074,0.008476843,0.000072405484,0.000361044,0.00012118935,0.000006750198,0.00003148512,0.0029629061],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99192184,0.0042880597,0.00041086393,0.00046715012,0.0020173315,0.0008947812],"domain_scores_gemma":[0.99612117,0.0023685996,0.0002550959,0.0010218552,0.00011104793,0.00012220957],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.021264248,0.00022787199,0.0003526236,0.0003606108,0.0024294374,0.0008925637,0.002118654,0.00014351786,0.00017113531],"category_scores_gemma":[0.0023105536,0.00015752613,0.00011531936,0.00034584713,0.0005158896,0.00050491985,0.0005113065,0.0019209512,0.000023521581],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044493878,0.00045130838,0.29160884,0.000036125493,0.000086686574,0.00016942139,0.5341461,0.000021534812,0.003746394,0.037501782,0.00049778447,0.13168956],"study_design_scores_gemma":[0.0016330046,0.00026926963,0.773909,0.00047843932,0.000017737339,0.0000015177849,0.21695861,0.0006885606,0.00015427875,0.0035022048,0.0019388011,0.0004485746],"about_ca_topic_score_codex":0.017825747,"about_ca_topic_score_gemma":0.0043269824,"teacher_disagreement_score":0.48230013,"about_ca_system_score_codex":0.0008858742,"about_ca_system_score_gemma":0.0007146316,"threshold_uncertainty_score":0.99886924},"labels":[],"label_agreement":null},{"id":"W2584951375","doi":"10.5539/ies.v10n2p84","title":"The Psychological Effect of Errors in Standardized Language Test Items on EFL Students’ Responses to the Following Item","year":2017,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Test (biology); Affect (linguistics); Social psychology; Stratified sampling; Test of English as a Foreign Language; Mathematics education; Personality; Language assessment; Statistics","score_opus":0.0729122271749704,"score_gpt":0.5470174107587235,"score_spread":0.4741051835837531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584951375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9662521,0.00038576534,0.0000013595256,0.016811943,0.0045395815,0.00037941049,0.000005939799,0.000012671398,0.011611227],"genre_scores_gemma":[0.9926299,0.0001974891,0.000025772692,0.00020799879,0.00030529848,0.00015659613,0.0000012149823,0.0000045630313,0.0064711776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984164,0.00026101532,0.00021201222,0.00016491837,0.0008041713,0.000141461],"domain_scores_gemma":[0.9960873,0.0032422852,0.00016725648,0.00024080218,0.00023481333,0.000027540675],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023922177,0.0000890357,0.00014992445,0.00007336915,0.00097237,0.00024214642,0.001001962,0.000028160393,0.000021510336],"category_scores_gemma":[0.0140309855,0.00004818428,0.000085453714,0.00009937286,0.0001998272,0.000103065526,0.00014977939,0.00009689715,0.000025866757],"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":[0.0002263885,0.00019937858,0.9556207,0.0000020565276,0.00012914013,0.0000016845463,0.025495248,0.0000013874826,0.000073415686,0.0011645621,0.007345395,0.0097406255],"study_design_scores_gemma":[0.0004555783,0.00014138698,0.9228879,0.000085349064,0.000012818001,1.4859482e-7,0.042969305,9.3284166e-7,0.00008113779,0.00012478959,0.033172775,0.00006784722],"about_ca_topic_score_codex":0.00030475744,"about_ca_topic_score_gemma":0.0010310331,"teacher_disagreement_score":0.03273279,"about_ca_system_score_codex":0.00016153765,"about_ca_system_score_gemma":0.000057790832,"threshold_uncertainty_score":0.99427426},"labels":[],"label_agreement":null},{"id":"W2586705862","doi":"10.5430/jct.v6n1p14","title":"A Comparison between Students' Self-Assessment and Teachers' Assessment","year":2017,"lang":"en","type":"article","venue":"Journal of Curriculum and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Self-assessment; Psychology; Mathematics education; Medical education; Pedagogy; Medicine","score_opus":0.033138408901531385,"score_gpt":0.4507190949126307,"score_spread":0.4175806860110993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586705862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98133016,0.00022003183,0.0005416612,0.0014009239,0.00044028866,0.00016881769,9.375156e-7,0.000022354181,0.015874844],"genre_scores_gemma":[0.9920096,0.00025425604,0.0066844285,0.000029605619,0.0008760509,0.0000023780137,6.2495906e-7,0.000010056376,0.00013299528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976633,0.0003801944,0.000484216,0.00017989312,0.0009914779,0.00030087153],"domain_scores_gemma":[0.9983981,0.00016245777,0.00091032375,0.00016913711,0.00009373458,0.00026621963],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0040891943,0.00016352178,0.0004668459,0.00010443524,0.0024230983,0.0013535095,0.0006202614,0.0000946474,0.000019725414],"category_scores_gemma":[0.000075763826,0.00013177094,0.00009804474,0.000025904317,0.00014783422,0.0008591107,0.0002593563,0.00077392196,0.0000010560364],"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":[0.0000015808132,0.0002503622,0.96382964,0.0000073090864,0.0001498393,0.000009756127,0.013857297,2.6358165e-7,0.000021699308,0.005467972,0.00043786995,0.015966434],"study_design_scores_gemma":[0.001006964,0.00017100706,0.9631685,0.0000957449,0.00018799427,0.0000049700884,0.023705993,0.00003137003,0.0000012982547,0.00036745952,0.011096113,0.00016255958],"about_ca_topic_score_codex":0.0005004253,"about_ca_topic_score_gemma":0.000078691366,"teacher_disagreement_score":0.015803875,"about_ca_system_score_codex":0.00019789656,"about_ca_system_score_gemma":0.00016001648,"threshold_uncertainty_score":0.9996832},"labels":[],"label_agreement":null},{"id":"W2586976612","doi":"10.1093/pch/17.suppl_a.26a","title":"Running: How is it Taught and Evaluated in British Columbian Schools?","year":2012,"lang":"en","type":"article","venue":"Paediatrics & Child Health","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics education; Medical education; Medicine; Psychology","score_opus":0.034796460936936335,"score_gpt":0.3528587779920568,"score_spread":0.31806231705512045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586976612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8499865,0.018461747,0.000019408475,0.109069,0.0012465416,0.0012219562,0.00003487119,0.000106166655,0.019853806],"genre_scores_gemma":[0.9830758,0.010166084,0.0003093879,0.004053881,0.0013947078,0.000018804876,0.00001826296,0.000017581933,0.0009454624],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99760145,0.00024083375,0.00027523504,0.00028106195,0.00069428,0.0009071458],"domain_scores_gemma":[0.99906486,0.00008856982,0.00012946608,0.00013303226,0.000072126175,0.0005119349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024797232,0.00011782896,0.00026787395,0.00013574382,0.00081281696,0.00033653073,0.00021297635,0.00014076485,0.00025913064],"category_scores_gemma":[0.00021995758,0.00016324082,0.000050193536,0.0009085654,0.000078771875,0.0004696984,0.00008295861,0.00040387944,0.000049020826],"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":[0.0000022159059,0.00008906427,0.91575444,0.000019609864,0.000006151051,0.0000013641352,0.015743537,1.172889e-7,2.2309966e-7,0.00040007845,0.0643023,0.0036808772],"study_design_scores_gemma":[0.00075342564,0.00004028538,0.8934897,0.000039212628,0.000014174456,0.0000019381946,0.015037243,0.000017349787,2.5706842e-7,0.0001489284,0.09025546,0.00020201466],"about_ca_topic_score_codex":0.016142,"about_ca_topic_score_gemma":0.028984047,"teacher_disagreement_score":0.13308932,"about_ca_system_score_codex":0.00028513977,"about_ca_system_score_gemma":0.00040265202,"threshold_uncertainty_score":0.9904096},"labels":[],"label_agreement":null},{"id":"W2587410353","doi":"10.3968/9141","title":"Study on Training Strategies for Effective Peer Review","year":2016,"lang":"en","type":"article","venue":"Cross-cultural communication","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Popularity; Peer review; Training (meteorology); Peer feedback; Computer science; Medical education; Best practice; Psychology; Mathematics education; Medicine; Political science","score_opus":0.14356662356351346,"score_gpt":0.4964878632974721,"score_spread":0.3529212397339586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587410353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.886772,0.001184826,0.000063050014,0.01710633,0.00020188875,0.0032264953,0.000012041036,0.00017621262,0.091257155],"genre_scores_gemma":[0.9937348,0.00075079285,0.00011523575,0.00020570192,0.000098222976,0.00046615233,0.00001884551,0.000007406651,0.0046028597],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987303,0.0003075013,0.00018326029,0.00016389557,0.00041944376,0.00019562017],"domain_scores_gemma":[0.99805516,0.00060955674,0.00012127312,0.0003344197,0.0008390915,0.000040518436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017479362,0.000103127444,0.00016367262,0.000017567158,0.00090870855,0.0003972491,0.0005358186,0.000047984217,0.000048451],"category_scores_gemma":[0.0008759686,0.00006185806,0.00008163428,0.00013055974,0.00032510058,0.00085899874,0.000059172675,0.00008285208,0.000048441776],"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":[0.00021499884,0.000804832,0.043072257,0.00015416517,0.00026733064,0.0000012387678,0.34957525,0.000002327004,0.0023958962,0.2720675,0.044488773,0.28695545],"study_design_scores_gemma":[0.002482259,0.00065320445,0.28238785,0.0012202611,0.00010519624,4.372047e-7,0.23344107,0.0000014819324,0.00008294481,0.007006534,0.4721367,0.00048205975],"about_ca_topic_score_codex":0.00008225602,"about_ca_topic_score_gemma":0.0002910623,"teacher_disagreement_score":0.42764792,"about_ca_system_score_codex":0.00012941619,"about_ca_system_score_gemma":0.000053260028,"threshold_uncertainty_score":0.69891435},"labels":[],"label_agreement":null},{"id":"W2588954709","doi":"10.4236/ojn.2017.72016","title":"Pass/Fail and Discretionary Grading: A Snapshot of Their Influences on Learning","year":2017,"lang":"en","type":"article","venue":"Open Journal of Nursing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Grading (engineering); Snapshot (computer storage); Subjectivity; Computer science; Psychology; Mathematics education; Epistemology; Engineering; Philosophy","score_opus":0.1097130137790854,"score_gpt":0.4472999753315051,"score_spread":0.33758696155241974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588954709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8971206,0.00019063587,0.0000118562875,0.004237268,0.00030943356,0.00007654583,4.7297425e-7,0.0000016447875,0.098051555],"genre_scores_gemma":[0.9989942,0.00024526598,0.0002902281,0.00001846274,0.00018823975,4.4743885e-7,3.848102e-7,0.0000041199396,0.00025869306],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99915993,0.00012748997,0.0002044056,0.00007925673,0.000296231,0.00013270983],"domain_scores_gemma":[0.9990272,0.0001248182,0.0005985721,0.000081157516,0.00009131417,0.0000769476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010553737,0.000063895845,0.0001871366,0.00005483764,0.0011159723,0.0005164112,0.00060441846,0.00003540196,0.000089038964],"category_scores_gemma":[0.00016197265,0.000048332422,0.000050572864,0.00004560826,0.00038454696,0.0008586951,0.000056617602,0.00017305794,7.518541e-7],"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":[0.00029772878,0.00020768274,0.7640017,0.000008671351,0.00010963856,0.000020668267,0.095215864,0.000034754128,0.002755348,0.020933418,0.0015971428,0.11481738],"study_design_scores_gemma":[0.0009454255,0.0006161786,0.8653337,0.0017038124,0.000057712332,0.000015622241,0.110141896,0.000045489167,0.00028519586,0.013277605,0.007394822,0.00018253837],"about_ca_topic_score_codex":0.00008606273,"about_ca_topic_score_gemma":0.000015576017,"teacher_disagreement_score":0.11463484,"about_ca_system_score_codex":0.000043508575,"about_ca_system_score_gemma":0.00008082847,"threshold_uncertainty_score":0.858327},"labels":[],"label_agreement":null},{"id":"W2590462553","doi":"10.1111/jcal.12178","title":"Short answers to deep questions: supporting teachers in large‐class settings","year":2017,"lang":"en","type":"article","venue":"Journal of Computer Assisted Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Grading (engineering); Mathematics education; Class (philosophy); Context (archaeology); Praxis; Psychology; Computer science; Pedagogy; Artificial intelligence; Engineering","score_opus":0.024637365506783682,"score_gpt":0.37571994380463364,"score_spread":0.35108257829784995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590462553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96487105,0.000055909302,0.017001413,0.0064714085,0.0010481434,0.00015951329,2.5398916e-7,0.000039556246,0.010352767],"genre_scores_gemma":[0.9876233,0.0000138998885,0.010825517,0.00023588807,0.00080307625,0.0000017863237,7.7273205e-7,0.000013332917,0.00048245984],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99787563,0.00034915967,0.0005551192,0.00016511144,0.0006119204,0.00044306944],"domain_scores_gemma":[0.99862874,0.00016980228,0.0006464032,0.00014402473,0.00021070521,0.0002003102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037964804,0.00012147601,0.00030170695,0.00025333127,0.0010669627,0.0006355573,0.00065698166,0.00009819467,0.000055585024],"category_scores_gemma":[0.000731689,0.000119598495,0.00014460021,0.00017311469,0.000070933995,0.0006475367,0.00013271923,0.00071727706,0.000012204342],"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":[0.000015656613,0.000069803085,0.8635829,0.0000048780157,0.000048795722,0.00008951916,0.028054662,0.00096169935,0.00007907198,0.00016330923,0.0008446476,0.10608502],"study_design_scores_gemma":[0.00045786792,0.00010639246,0.9358323,0.00022140049,0.000025734033,0.000009908403,0.011437968,0.001403669,0.0000042446563,0.000024225343,0.050309107,0.00016716473],"about_ca_topic_score_codex":0.00011281225,"about_ca_topic_score_gemma":0.00047051575,"teacher_disagreement_score":0.105917856,"about_ca_system_score_codex":0.00023185051,"about_ca_system_score_gemma":0.00014407205,"threshold_uncertainty_score":0.8206323},"labels":[],"label_agreement":null},{"id":"W2593362570","doi":"10.18260/p.27121","title":"Using a Delphi Approach to Develop Rubric Criteria","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"American Association for the Advancement of Science","keywords":"Rubric; Delphi method; Delphi; Computer science; Teamwork; Outcome (game theory); Work (physics); Medical education; Management science; Knowledge management; Psychology; Process management; Mathematics education; Engineering; Medicine; Artificial intelligence; Political science","score_opus":0.15513021429365023,"score_gpt":0.41844162254475975,"score_spread":0.26331140825110955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593362570","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2989992,0.000010060705,0.06301991,0.001592091,0.0003117641,0.00024202555,0.0000010450759,0.00010845261,0.6357155],"genre_scores_gemma":[0.93136436,0.000008118647,0.056949865,0.00037619408,0.00026070696,0.000009577269,3.83109e-7,0.0000072529183,0.011023568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909276,0.00006370267,0.00010943146,0.0001719202,0.00028092647,0.00028123712],"domain_scores_gemma":[0.9996024,0.000053575088,0.000021523165,0.00008830074,0.000119968376,0.00011425219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043740077,0.00006707463,0.00008588254,0.00005835675,0.00024837613,0.000083498446,0.00022393971,0.00004322174,0.00069463305],"category_scores_gemma":[0.00013307486,0.000043606706,0.000021303493,0.00053242553,0.000055777087,0.0001843727,0.00007805244,0.000019166659,0.00022000387],"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":[0.00006266345,0.0004995468,0.16943377,0.000019792546,0.00012226785,0.000007130877,0.118882336,0.0000025878057,0.036571704,0.5322788,0.093765765,0.04835369],"study_design_scores_gemma":[0.0021764792,0.00010998801,0.1870703,0.00012989315,0.0000818245,0.0000049636265,0.08299874,0.00026750535,0.000937962,0.005972479,0.7182724,0.0019775063],"about_ca_topic_score_codex":0.00049133366,"about_ca_topic_score_gemma":0.00012287081,"teacher_disagreement_score":0.63236517,"about_ca_system_score_codex":0.00009840045,"about_ca_system_score_gemma":0.00013362843,"threshold_uncertainty_score":0.76057446},"labels":[],"label_agreement":null},{"id":"W2593520074","doi":"10.1057/978-1-137-46484-2_3","title":"How Do We Assess?","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology","score_opus":0.09308519081929405,"score_gpt":0.36970893093176066,"score_spread":0.2766237401124666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593520074","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002520346,0.0008024981,0.00003232515,0.010174954,0.0011870039,0.00025198763,0.000005830923,0.000109843546,0.987433],"genre_scores_gemma":[0.0033849964,0.005725997,0.00021788062,0.00006736842,0.0017353714,0.0000054273987,0.000006079757,0.000029190298,0.9888277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984757,0.000017654927,0.000115854156,0.00032199602,0.00078230636,0.00028653015],"domain_scores_gemma":[0.9990268,0.00007927079,0.00023267255,0.00042768478,0.000109597255,0.00012399581],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00031268463,0.00022601892,0.00029850594,0.00007360234,0.0007565678,0.0013845867,0.0008190595,0.00042445475,0.006810864],"category_scores_gemma":[0.00003868848,0.00019766144,0.00019598223,0.000007399086,0.00033430764,0.000301647,0.00014301762,0.00025917168,0.00078121445],"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":[0.0000014878975,0.0000056315166,0.00021739892,0.000005508386,0.00005096231,0.000010758726,0.0006566145,3.495913e-9,0.0000010947307,0.90961784,0.07358965,0.015843054],"study_design_scores_gemma":[0.00009547903,0.000013080597,0.00010315056,0.000065627195,0.000040350005,1.6033671e-7,0.0006674381,1.4439117e-7,7.824708e-7,0.05645888,0.94228554,0.00026934425],"about_ca_topic_score_codex":0.00013532,"about_ca_topic_score_gemma":0.0014112714,"teacher_disagreement_score":0.8686959,"about_ca_system_score_codex":0.00008991108,"about_ca_system_score_gemma":0.00020497196,"threshold_uncertainty_score":0.9999968},"labels":[],"label_agreement":null},{"id":"W2593712670","doi":"10.24908/pceea.v0i0.6465","title":"Testing Inter-Rater Reliability in Rubrics for Large Scale Undergraduate Independent Projects","year":2017,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Rubric; Deliverable; Reliability (semiconductor); Peer assessment; Consistency (knowledge bases); Supervisor; Inter-rater reliability; Psychology; Computer science; Work (physics); Mathematics education; Engineering; Rating scale; Political science; Systems engineering; Artificial intelligence","score_opus":0.022010159642869193,"score_gpt":0.29583113541512635,"score_spread":0.27382097577225717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593712670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96099174,0.000012405316,0.000018890229,0.015864689,0.0018729899,0.0010007692,0.000017423692,0.000043712025,0.02017736],"genre_scores_gemma":[0.99506676,0.0000036651627,0.0010244527,0.00008106647,0.0002179078,0.00009920762,0.0000027952315,0.000014946081,0.0034891707],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988786,0.000010254636,0.00022714259,0.00018819497,0.00031907667,0.00037675863],"domain_scores_gemma":[0.9986012,0.00009281977,0.00041257087,0.0001148574,0.00066067174,0.00011790659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001616312,0.000097770186,0.0001332899,0.00015504716,0.0007046426,0.00035715837,0.00050329795,0.0001309753,0.0000064221927],"category_scores_gemma":[0.0055668307,0.00009846439,0.000060428723,0.0002457126,0.00002518688,0.0004074905,0.000048427257,0.00016341683,0.0000027834305],"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":[0.0000013106533,0.000049588678,0.9864773,0.000053024032,0.000010120299,1.3995139e-8,0.0049449555,0.000013139115,0.00012287387,0.005139172,0.0029544758,0.0002340233],"study_design_scores_gemma":[0.00026381295,0.000012095174,0.97688615,0.00012679935,0.000019154984,1.014142e-7,0.0030478018,0.0008508119,0.00013663345,0.0011785142,0.017319456,0.00015868491],"about_ca_topic_score_codex":0.03513374,"about_ca_topic_score_gemma":0.16346836,"teacher_disagreement_score":0.12833461,"about_ca_system_score_codex":0.0027018583,"about_ca_system_score_gemma":0.0009965551,"threshold_uncertainty_score":0.97129136},"labels":[],"label_agreement":null},{"id":"W2595424209","doi":"","title":"Impact on Learning - Designing Assessment","year":2014,"lang":"en","type":"article","venue":"Murdoch Research Repository (Murdoch University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Curriculum; Quality (philosophy); Task (project management); Presentation (obstetrics); Quality assurance; Mathematics education; Computer science; Psychology; Pedagogy; Medical education; Engineering; Operations management; Medicine","score_opus":0.06543662287441881,"score_gpt":0.41411004948605745,"score_spread":0.34867342661163864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2595424209","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43584043,0.00001530031,0.0007876326,0.00027719588,0.000267101,0.0003405202,6.916513e-7,0.00018725547,0.5622839],"genre_scores_gemma":[0.92481387,0.00007006963,0.0005005537,0.000019389645,0.0006644461,0.000004430441,0.0000063333955,0.000028596642,0.07389234],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99163985,0.003925361,0.00022593129,0.0006801087,0.0022711612,0.0012575694],"domain_scores_gemma":[0.99677306,0.0015000559,0.00013280993,0.0004515069,0.00058253936,0.00056000525],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0039044544,0.00025936269,0.00031613102,0.0009736452,0.0044197007,0.00056473695,0.0010653323,0.00021531334,0.00028748516],"category_scores_gemma":[0.00037335473,0.00025871728,0.0002422404,0.0016605579,0.00063870684,0.0005911814,0.00028408592,0.0013110866,0.00019350101],"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":[0.0006485761,0.0011276271,0.6578554,0.000059693266,0.0005055388,0.0009167684,0.01434703,0.0015190641,0.022309883,0.27506557,0.01287796,0.012766918],"study_design_scores_gemma":[0.0029039038,0.0031960993,0.32154253,0.00028794655,0.00009496939,0.000009232138,0.037815932,0.002255105,0.0014980948,0.0007751412,0.6283292,0.0012918347],"about_ca_topic_score_codex":0.002756877,"about_ca_topic_score_gemma":0.00010639792,"teacher_disagreement_score":0.6154512,"about_ca_system_score_codex":0.0017603082,"about_ca_system_score_gemma":0.0008114456,"threshold_uncertainty_score":0.9999865},"labels":[],"label_agreement":null},{"id":"W2597652891","doi":"","title":"Assessment as a Learning Project: Online Surveys with Immediate Formative Feedback","year":2017,"lang":"en","type":"article","venue":"Purdue e-Pubs (Purdue University System)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Computer science; Online assessment; Online learning; Psychology; Mathematics education; Multimedia","score_opus":0.025218442993307874,"score_gpt":0.3127259221443371,"score_spread":0.2875074791510292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597652891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56653565,0.000033368146,0.0011110571,0.0011584342,0.0007498004,0.0015253247,0.00007688939,0.00036856788,0.4284409],"genre_scores_gemma":[0.97091705,0.00011124988,0.0009355999,0.000023014403,0.00038954435,0.000007781299,0.00010575638,0.00003345116,0.027476557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955768,0.0014034733,0.00030796,0.00060647464,0.0012189454,0.00088636455],"domain_scores_gemma":[0.9974399,0.0002834823,0.00078892626,0.00063271384,0.00052495906,0.00032999573],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0031463732,0.0003729928,0.00059294427,0.00029333573,0.0045385296,0.0007752259,0.0014558064,0.00023073344,0.0001047344],"category_scores_gemma":[0.00021595403,0.0003583579,0.00018302207,0.00041778423,0.0005841783,0.002008049,0.0004275718,0.0005944462,0.00023131447],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005091434,0.00092499726,0.80149776,0.000639388,0.001159429,0.0009800895,0.09454301,0.00009036689,0.00015226292,0.09067183,0.0032031448,0.005628577],"study_design_scores_gemma":[0.004201698,0.00049790915,0.5545581,0.00061775633,0.00023018119,0.000016506303,0.35412437,0.00043183946,0.000021553133,0.00003725066,0.084340505,0.0009223602],"about_ca_topic_score_codex":0.017524077,"about_ca_topic_score_gemma":0.009057495,"teacher_disagreement_score":0.4043814,"about_ca_system_score_codex":0.001147956,"about_ca_system_score_gemma":0.0011070028,"threshold_uncertainty_score":0.9998868},"labels":[],"label_agreement":null},{"id":"W2598237572","doi":"10.24908/pceea.v0i0.6537","title":"Group and individual evaluation in engineering project courses","year":2017,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Conestoga College","funders":"","keywords":"Praise; Group work; Group (periodic table); Diversity (politics); Task (project management); Psychology; Mathematics education; Work (physics); Computer science; Point (geometry); Social psychology; Engineering; Sociology; Mathematics","score_opus":0.029063601637837187,"score_gpt":0.3164027994406403,"score_spread":0.28733919780280315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2598237572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98468834,0.00009679824,0.0000011697431,0.004077404,0.0012543957,0.00064910285,0.000007555909,0.000029594945,0.009195614],"genre_scores_gemma":[0.9987425,0.000027507276,0.00028421436,0.00003925566,0.00022364514,0.00007329756,0.00000387001,0.000011997628,0.0005937027],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988749,0.000010190821,0.00016633654,0.0001427362,0.00054878305,0.0002570694],"domain_scores_gemma":[0.9992171,0.0000467521,0.0002858713,0.00007425286,0.00028334232,0.00009267432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017508044,0.000091094815,0.00011180761,0.00025515823,0.00046529557,0.00039999044,0.0003677137,0.000118171425,0.000013498313],"category_scores_gemma":[0.0025743183,0.000096351374,0.00003331919,0.00021200281,0.000030710766,0.0004920496,0.000035282235,0.00014662962,0.000001192093],"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":[0.0000010811967,0.00003072342,0.9628,0.000050287796,0.00003693326,2.9885953e-8,0.009349074,0.0000363336,0.00025477086,0.022348447,0.0034967489,0.0015955714],"study_design_scores_gemma":[0.00020994597,0.0000060730895,0.98758465,0.00010321276,0.00003868468,1.9485674e-7,0.0021226106,0.00085222936,0.000044684566,0.00016243977,0.008744902,0.00013036172],"about_ca_topic_score_codex":0.04493015,"about_ca_topic_score_gemma":0.07699027,"teacher_disagreement_score":0.032060124,"about_ca_system_score_codex":0.0015253039,"about_ca_system_score_gemma":0.00083306583,"threshold_uncertainty_score":0.9614297},"labels":[],"label_agreement":null},{"id":"W2599956837","doi":"10.1177/0265532216684576","title":"Book Review: Focus on Assessment","year":2016,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Focus (optics); Psychology; Linguistics; Philosophy; Optics","score_opus":0.032919987551438844,"score_gpt":0.3820371374063785,"score_spread":0.3491171498549397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599956837","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063560978,0.049841147,0.00031162592,0.019971998,0.00035572206,0.00056498474,0.0000044667613,0.0004652489,0.92212874],"genre_scores_gemma":[0.74898744,0.011241683,0.008742928,0.053436033,0.0033476981,0.00017588933,0.0000060360226,0.00008353755,0.17397878],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988451,0.00014989104,0.00014152589,0.00017956948,0.0003998061,0.0002841098],"domain_scores_gemma":[0.9990121,0.00061920885,0.000084784544,0.00016497685,0.00004506898,0.000073854666],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007457504,0.00008741454,0.00012604444,0.00002854758,0.00023416654,0.00003564494,0.000208229,0.0000322609,0.0027160947],"category_scores_gemma":[0.0007724354,0.000057213198,0.0000431595,0.00018121215,0.000058264603,0.00013711031,0.000042467265,0.000069687645,0.00027905605],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003486994,0.00011815684,0.04055792,0.000075834934,0.000029923309,0.00009783427,0.0050381594,1.5776098e-7,0.004292534,0.0073035294,0.49328735,0.4491951],"study_design_scores_gemma":[0.0011973215,0.00026540563,0.05647068,0.005692355,0.0000871443,0.000003092869,0.003840892,0.000010299217,0.000522372,0.00070564065,0.93042296,0.00078182144],"about_ca_topic_score_codex":0.00024996576,"about_ca_topic_score_gemma":0.00005375852,"teacher_disagreement_score":0.74814993,"about_ca_system_score_codex":0.00011009288,"about_ca_system_score_gemma":0.00006975269,"threshold_uncertainty_score":0.9981955},"labels":[],"label_agreement":null},{"id":"W2600733185","doi":"10.1080/0969594x.2017.1297010","title":"Developing assessment capable teachers in this age of accountability","year":2017,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Accountability; Psychology; Medical education; Political science; Medicine","score_opus":0.12258459740226811,"score_gpt":0.5148076355503635,"score_spread":0.39222303814809534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600733185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51093733,0.000066206274,0.000067570625,0.021986337,0.00038390333,0.00048762502,0.000002447362,0.0000147035,0.46605387],"genre_scores_gemma":[0.9771204,0.0013645903,0.018533807,0.0004878001,0.00021069136,0.000103527345,0.000012399338,0.000010207601,0.0021566076],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99757373,0.00073537685,0.00049928593,0.00033454315,0.00049624534,0.0003608429],"domain_scores_gemma":[0.99732774,0.0013517789,0.000623671,0.0004520884,0.00015483775,0.00008987364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054570246,0.00015117052,0.00025988888,0.00025102822,0.0006227701,0.0003924616,0.000512693,0.00012797126,0.0001255186],"category_scores_gemma":[0.003231292,0.00016249882,0.00003586689,0.00028708766,0.00031588157,0.0020273414,0.00020188901,0.0003605561,0.0000038865965],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001524136,0.00051975343,0.5562643,0.000033390053,0.000018636298,0.0000015851964,0.029716179,0.000005175718,0.00009025372,0.4065339,0.000073007046,0.0067285793],"study_design_scores_gemma":[0.00034756982,0.000019983006,0.7810145,0.00007257796,0.000016582175,0.0000010205812,0.054676525,0.000014785074,0.000011315349,0.003633609,0.1600303,0.00016124127],"about_ca_topic_score_codex":0.09320701,"about_ca_topic_score_gemma":0.018439839,"teacher_disagreement_score":0.46618304,"about_ca_system_score_codex":0.0012492697,"about_ca_system_score_gemma":0.0057436004,"threshold_uncertainty_score":0.9998929},"labels":[],"label_agreement":null},{"id":"W2602102095","doi":"","title":"Ontario's Grade 6 Learners' Mathematics Achievement Profiles Underlying the EQAO Junior Division Assessment","year":2016,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Division (mathematics); Mathematics; Psychology; Arithmetic","score_opus":0.04426223872004224,"score_gpt":0.348418480087242,"score_spread":0.30415624136719976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602102095","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37234998,0.00020358193,0.0003775826,0.0028027447,0.0008946087,0.0010791501,0.0000100209045,0.00007557902,0.62220675],"genre_scores_gemma":[0.7307683,0.0006337527,0.001866685,0.000010912873,0.000054329146,0.0000022943434,0.00007134563,0.000018938841,0.26657343],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9978279,0.00018351438,0.0001702792,0.00033487374,0.0010985255,0.00038492656],"domain_scores_gemma":[0.9986787,0.00018245264,0.0005378934,0.0003520397,0.00014106398,0.00010789249],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006731503,0.00025002754,0.00038289715,0.000050520626,0.0014121652,0.000081518345,0.00090566906,0.00026485664,0.016956044],"category_scores_gemma":[0.00001712526,0.00021451469,0.00024585173,0.00007530508,0.0001989637,0.00047162495,0.00013562772,0.00026500635,0.000038398422],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010576097,0.00076179067,0.015806852,0.00028058272,0.00076506427,0.0000141856335,0.85892045,0.0000022716242,0.0015778524,0.058843188,0.0037306072,0.059191395],"study_design_scores_gemma":[0.0004603475,0.000090626854,0.4534585,0.00026209085,0.00020525523,6.773975e-8,0.5355358,0.000009062953,0.000010133619,0.0002500226,0.009443384,0.00027471376],"about_ca_topic_score_codex":0.6006248,"about_ca_topic_score_gemma":0.9243142,"teacher_disagreement_score":0.43765163,"about_ca_system_score_codex":0.001665118,"about_ca_system_score_gemma":0.00066643284,"threshold_uncertainty_score":0.9998879},"labels":[],"label_agreement":null},{"id":"W2602322515","doi":"10.5539/jedp.v7n1p229","title":"Exploring Correlates of Business Undergraduates’ Closed Versus Open Grading Assessment Learning Perceptions","year":2017,"lang":"en","type":"article","venue":"Journal of Educational and Developmental Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Grading (engineering); Reputation; Variance (accounting); Stepwise regression; Perception; Explained variation; Applied psychology; Confirmatory factor analysis; Social psychology; Mathematics education; Statistics; Mathematics; Structural equation modeling; Engineering; Social science; Accounting; Sociology","score_opus":0.2591831070170039,"score_gpt":0.4751121751058542,"score_spread":0.21592906808885026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602322515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9344074,0.00006219016,0.00008138117,0.010814912,0.0023164172,0.00008868252,6.1206396e-7,0.0000023614516,0.05222603],"genre_scores_gemma":[0.9902284,0.0011282695,0.0076397792,0.000038187303,0.00024629707,0.0000054619527,0.0000042691277,0.0000057299976,0.0007035707],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991238,0.0000623081,0.00029693177,0.00012154133,0.0002484226,0.00014695893],"domain_scores_gemma":[0.9988531,0.00027102485,0.0004915446,0.00006233447,0.00023336356,0.00008863952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006213324,0.00007861163,0.00018538516,0.00009492748,0.0012017016,0.00018176046,0.00046498128,0.000041499457,0.0007329726],"category_scores_gemma":[0.00025662655,0.00007489172,0.00003882277,0.000086668806,0.00028045208,0.00081537623,0.0001170646,0.00017372069,0.000012097318],"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":[0.00011874761,0.00023663806,0.96757096,0.000006406977,0.000118407224,0.0000016706158,0.010004806,0.000005022062,0.0004447577,0.012931378,0.0017314,0.0068298336],"study_design_scores_gemma":[0.0010806976,0.00006764862,0.9722472,0.000054270255,0.000020498508,0.000010674312,0.019994084,0.0000019205002,0.000002341947,0.0038758328,0.0025569778,0.000087877364],"about_ca_topic_score_codex":0.00018724187,"about_ca_topic_score_gemma":0.00013791461,"teacher_disagreement_score":0.05582102,"about_ca_system_score_codex":0.00009472694,"about_ca_system_score_gemma":0.00050856645,"threshold_uncertainty_score":0.92426383},"labels":[],"label_agreement":null},{"id":"W2603140028","doi":"","title":"The knowledge connections analyzer","year":2012,"lang":"en","type":"article","venue":"View","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Formative assessment; SQL; Usability; Asynchronous communication; World Wide Web; Knowledge management; Human–computer interaction; Mathematics education; Database; Psychology","score_opus":0.06088683430738525,"score_gpt":0.40721072893110305,"score_spread":0.3463238946237178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603140028","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02003718,0.015404899,0.000049527433,0.0038918545,0.0016551723,0.00016503895,5.6147087e-7,0.00006575484,0.95873004],"genre_scores_gemma":[0.9769058,0.0019089624,0.000025442325,0.00008611651,0.0007019096,0.000014968671,4.3790723e-7,0.0000030001029,0.02035336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995004,0.000096322154,0.00005880668,0.00004174362,0.00010178499,0.00020094591],"domain_scores_gemma":[0.9996542,0.00016233012,0.000019280304,0.000075722346,0.000030367233,0.000058150308],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062078,0.00003191697,0.000044382494,0.000011516231,0.0008855381,0.000053353055,0.00012416455,0.000020164227,0.00051383406],"category_scores_gemma":[0.000057310084,0.000020365214,0.000038587703,0.00022394708,0.00008825084,0.00010676853,0.000022270136,0.00004032919,0.00094913086],"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":[0.0000014018344,0.00011366872,0.11231876,0.0000042471656,0.000045978137,1.2070022e-7,0.020424938,6.1409935e-8,0.000017343045,0.74253535,0.06492075,0.05961738],"study_design_scores_gemma":[0.000030749787,0.0000025835404,0.035655778,0.0000033124832,0.000011686124,6.4797405e-8,0.002969982,9.3399166e-7,0.0000018645694,0.00022741285,0.96106184,0.000033818367],"about_ca_topic_score_codex":0.000109527966,"about_ca_topic_score_gemma":0.0010233922,"teacher_disagreement_score":0.95686865,"about_ca_system_score_codex":0.00002811513,"about_ca_system_score_gemma":0.000031866362,"threshold_uncertainty_score":0.99982876},"labels":[],"label_agreement":null},{"id":"W2604298682","doi":"","title":"Enseignement et évaluation structurés","year":2010,"lang":"fr","type":"article","venue":"Canadian Family Physician","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Computer science; Library science; Philosophy","score_opus":0.03546237938090538,"score_gpt":0.3113231019364217,"score_spread":0.2758607225555163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604298682","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.305922,0.00073131995,0.000014549898,0.010495416,0.00883202,0.0003868696,0.00008550339,0.00003226392,0.67350006],"genre_scores_gemma":[0.8943035,0.00014340051,0.00080756465,0.08814629,0.0026992168,0.000024452196,0.00008245435,0.000042027143,0.013751085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777347,0.00021692523,0.00023378828,0.00037243598,0.00057911774,0.0008242532],"domain_scores_gemma":[0.99873406,0.00006264662,0.00011060449,0.00031086509,0.0001427575,0.0006390665],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059530244,0.00024566505,0.00021756723,0.00014106576,0.0006972045,0.00023547294,0.00041783144,0.00023221287,0.00029186593],"category_scores_gemma":[0.000016934217,0.00029671544,0.00013126763,0.0005518648,0.000432095,0.00039697188,0.000031281805,0.0004886221,0.001009064],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004290514,0.00008641624,0.00086990785,0.000018694443,0.00011462089,0.00002152412,0.016535329,0.000018992861,0.008009814,0.41930866,0.22637734,0.3286344],"study_design_scores_gemma":[0.00030796663,0.00004813789,0.09671686,0.000029903045,0.00007481147,1.2854395e-7,0.009815472,0.00014289263,0.000054821103,0.01019142,0.8822115,0.00040609294],"about_ca_topic_score_codex":0.19992873,"about_ca_topic_score_gemma":0.63245064,"teacher_disagreement_score":0.659749,"about_ca_system_score_codex":0.00051045907,"about_ca_system_score_gemma":0.002525074,"threshold_uncertainty_score":0.9999485},"labels":[],"label_agreement":null},{"id":"W2607048716","doi":"","title":"Investigating the Effectiveness of Peer Reviewing in a Moroccan University EFL Writing Class","year":2016,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Paragraph; Psychology; Peer feedback; Context (archaeology); Test (biology); Class (philosophy); Second language writing; Relevance (law); Mathematics education; Session (web analytics); Quality (philosophy); Arabic; Task (project management); English as a foreign language; Medical education; Pedagogy; Computer science; Second language; Linguistics","score_opus":0.03971718920983726,"score_gpt":0.37040377560353266,"score_spread":0.3306865863936954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607048716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8368095,0.000041334883,0.0000075642342,0.0020301703,0.0003209932,0.00018910035,9.2736354e-7,0.0000088034285,0.1605916],"genre_scores_gemma":[0.997964,0.000017036202,0.00010451637,0.000036627185,0.000114598864,0.0000033035544,2.2470081e-7,0.00000221735,0.0017574232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99850965,0.00042097943,0.00014991844,0.00014841103,0.0005911093,0.00017994909],"domain_scores_gemma":[0.9988608,0.00048220862,0.00017656521,0.00007433906,0.00036518386,0.00004090763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046073757,0.000048613598,0.000114174894,0.00007667372,0.0004793056,0.000023067887,0.0004355868,0.000033210432,0.00006251062],"category_scores_gemma":[0.0004127128,0.000034840803,0.00003624061,0.0012489374,0.0014054308,0.000373814,0.000063756095,0.000053749693,0.000002527843],"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":[0.000003859526,0.0000491858,0.3070542,0.000030247937,0.0000025970749,5.0847255e-8,0.012202587,2.794894e-7,0.017038578,0.6599885,0.000109240595,0.0035206561],"study_design_scores_gemma":[0.00012120236,0.0000069790935,0.97844166,0.00022349827,0.0000059800154,2.3487672e-8,0.011238419,4.3594648e-7,0.00044962217,0.0014771869,0.007979419,0.00005556563],"about_ca_topic_score_codex":0.0009874768,"about_ca_topic_score_gemma":0.000027925786,"teacher_disagreement_score":0.6713875,"about_ca_system_score_codex":0.00029216753,"about_ca_system_score_gemma":0.0008616328,"threshold_uncertainty_score":0.51783687},"labels":[],"label_agreement":null},{"id":"W2611549767","doi":"10.18806/tesl.v34i1.1260","title":"Post-Admission Language Assessment of University Students (J. Read (ed.), 2016)","year":2017,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Language assessment; Psychology; Linguistics; Mathematics education; Pedagogy; Philosophy","score_opus":0.01633748164551186,"score_gpt":0.3578796298138933,"score_spread":0.34154214816838147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611549767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.928418,0.0009209007,0.0000273125,0.003598474,0.0016080939,0.00016719104,0.00003072426,0.000015642918,0.06521367],"genre_scores_gemma":[0.9837885,0.00027453262,0.0002757188,0.00072680117,0.00026592612,1.7610398e-7,0.000002205109,0.0000065713107,0.014659594],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981333,0.00015909107,0.00015973422,0.00010936841,0.0011768241,0.0002616679],"domain_scores_gemma":[0.9988491,0.00007337817,0.00038101745,0.00021777092,0.00021134119,0.00026738382],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009886282,0.00008388082,0.00015669521,0.000050386905,0.0016562629,0.00018018585,0.001057781,0.000048003247,0.009986556],"category_scores_gemma":[0.0001897257,0.00007747197,0.000057799352,0.000046853984,0.00011054754,0.00029540077,0.00014764727,0.00021299323,0.000002570652],"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":[0.000120098965,0.00032833134,0.6872406,0.000021527827,0.00027975693,0.00091749616,0.0075422376,0.0000047111503,0.0026600899,0.0027340085,0.28897268,0.009178438],"study_design_scores_gemma":[0.00082396955,0.00006917325,0.8485399,0.00006874721,0.00004641705,0.0000042088177,0.020257311,0.000006411291,0.000032434233,0.000030777243,0.12996683,0.00015382546],"about_ca_topic_score_codex":0.4825199,"about_ca_topic_score_gemma":0.3863938,"teacher_disagreement_score":0.16129927,"about_ca_system_score_codex":0.00056415476,"about_ca_system_score_gemma":0.0032492534,"threshold_uncertainty_score":0.99964345},"labels":[],"label_agreement":null},{"id":"W2611871119","doi":"","title":"Instructor Comments on Student Writing: Learner Response to Electronic Written Feedback","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Writing process; Legibility; Thematic analysis; Psychology; Peer feedback; Process (computing); Qualitative research; Multimedia; Computer science; Mathematics education","score_opus":0.025483229253907346,"score_gpt":0.36045114603416256,"score_spread":0.3349679167802552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611871119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8826768,0.000010228315,0.00003804554,0.029081754,0.00027041516,0.00042038359,0.0000024236342,0.00013503923,0.08736491],"genre_scores_gemma":[0.9369863,0.000055400684,0.00012297563,0.0024179989,0.00028705003,0.000033757977,7.353644e-7,0.00001910827,0.060076665],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972776,0.0004363285,0.00025149278,0.00036757073,0.0008884691,0.00077850284],"domain_scores_gemma":[0.9988788,0.00046149065,0.00006191596,0.0002668461,0.00008540177,0.0002455892],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014883104,0.00016929548,0.00018643473,0.00013243269,0.00043878233,0.00015791946,0.0005900226,0.00008711955,0.002117353],"category_scores_gemma":[0.00017497361,0.00011604771,0.000081880586,0.00031240634,0.0001133876,0.0001917384,0.00015430192,0.0001249949,0.0020531307],"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":[0.0029176609,0.0011947069,0.58225685,0.0000057906786,0.00028079835,0.000020397969,0.042945772,0.0000018384073,0.016089555,0.19002882,0.090235695,0.07402213],"study_design_scores_gemma":[0.0020225695,0.00068721373,0.5398732,0.000058093894,0.000015780575,4.202094e-7,0.019256098,4.088857e-7,0.00040914887,0.0005362255,0.4367312,0.00040967867],"about_ca_topic_score_codex":0.00020667541,"about_ca_topic_score_gemma":0.0005660168,"teacher_disagreement_score":0.3464955,"about_ca_system_score_codex":0.0005641324,"about_ca_system_score_gemma":0.00016069258,"threshold_uncertainty_score":0.99879485},"labels":[],"label_agreement":null},{"id":"W2615639425","doi":"","title":"PAPER: Measuring Teachers’ Assessment Literacy and Conceptions of Assessment in a High Performative Canadian Context: A Construct Validity Study","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Performative utterance; Psychology; Literacy; Context (archaeology); Construct (python library); Construct validity; Mathematics education; Pedagogy; Psychometrics; Computer science; Developmental psychology","score_opus":0.06347086988825551,"score_gpt":0.3642921981591032,"score_spread":0.3008213282708477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615639425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735556,0.000034476445,0.00021651539,0.0015913589,0.00023566118,0.000846194,0.00007134222,0.000026709075,0.023422124],"genre_scores_gemma":[0.9987574,0.00016295812,0.0004137175,0.000057153735,0.00005312171,0.00008425936,0.0000041023877,0.00000847936,0.0004588002],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99745417,0.0007943056,0.00043826835,0.00033215928,0.0005293044,0.00045177474],"domain_scores_gemma":[0.9985779,0.00048055296,0.00020730359,0.0002244985,0.00024325031,0.000266525],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016239885,0.00019121366,0.0003735815,0.00018199666,0.0004095314,0.00015143791,0.00032065224,0.000091532704,0.0013935344],"category_scores_gemma":[0.00012111214,0.00014436727,0.000038331476,0.0001810391,0.00052930036,0.0008351086,0.00008833069,0.00025271453,0.000015390284],"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":[0.0000074952923,0.00014456129,0.90734804,0.0000058244764,0.000044141634,0.000006021572,0.043360785,1.4300763e-7,0.00036677392,0.024255592,0.000090078844,0.024370544],"study_design_scores_gemma":[0.0018445962,0.00018916815,0.92934096,0.00017679967,0.000034990484,7.6917064e-7,0.06501064,0.000016651104,0.000017440603,0.000843911,0.0022818935,0.00024221481],"about_ca_topic_score_codex":0.24541543,"about_ca_topic_score_gemma":0.3824903,"teacher_disagreement_score":0.13707487,"about_ca_system_score_codex":0.0005345712,"about_ca_system_score_gemma":0.0022653146,"threshold_uncertainty_score":0.99951935},"labels":[],"label_agreement":null},{"id":"W2618977613","doi":"10.5539/ies.v10n6p159","title":"The Effect of Peer Assessment on the Evaluation Process of Students","year":2017,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University","keywords":"Peer assessment; Credibility; Process (computing); Scope (computer science); Standards-based assessment; Psychology; Peer evaluation; Peer feedback; Peer review; Educational assessment; Alternative assessment; Formative assessment; Mathematics education; Higher education; Computer science; Political science","score_opus":0.12447706384515944,"score_gpt":0.6008781695317235,"score_spread":0.476401105686564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618977613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9103512,0.00015672091,0.00000283503,0.017278858,0.0036755144,0.00046345792,0.0000022536474,0.0000048432144,0.068064295],"genre_scores_gemma":[0.99481034,0.00018741266,0.0000128112715,0.000039861116,0.00023779283,0.00024107123,0.000002516223,0.0000032953872,0.0044648745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99727565,0.00022174667,0.00020334187,0.000105942505,0.0021110452,0.000082302875],"domain_scores_gemma":[0.9953488,0.0009234434,0.00046594386,0.00021719463,0.0030303989,0.00001422405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00391955,0.0000680698,0.0001065312,0.000035948946,0.0010827575,0.00014753605,0.0009212612,0.000020183157,0.000070048896],"category_scores_gemma":[0.004930774,0.00003619067,0.000054744112,0.00004959472,0.00039837038,0.00014321801,0.00009184797,0.00006488362,0.000007120323],"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":[0.000045084533,0.00022684218,0.92153126,0.000012771092,0.00051215495,3.9441748e-8,0.014485478,0.000011871764,0.000026625172,0.03653809,0.0104769915,0.016132765],"study_design_scores_gemma":[0.0003850091,0.00011363517,0.9376859,0.000096228585,0.00007028961,5.587685e-8,0.044254206,0.000028714016,0.0004916104,0.003930005,0.012879503,0.00006481225],"about_ca_topic_score_codex":0.00013917597,"about_ca_topic_score_gemma":0.00012289386,"teacher_disagreement_score":0.08445914,"about_ca_system_score_codex":0.00014162509,"about_ca_system_score_gemma":0.0002451576,"threshold_uncertainty_score":0.8327804},"labels":[],"label_agreement":null},{"id":"W2619779668","doi":"10.1016/j.nedt.2017.05.016","title":"A qualitative study on feedback provided by students in nurse education","year":2017,"lang":"en","type":"article","venue":"Nurse Education Today","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Focus group; Peer feedback; Qualitative research; Medical education; Psychology; Narrative; Nurse education; Student nurse; Pedagogy; Medicine; Sociology","score_opus":0.04196839473542503,"score_gpt":0.49293822241707674,"score_spread":0.4509698276816517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619779668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8704854,0.00005569055,0.0000020590328,0.010394717,0.0036504245,0.0019054998,0.0000046965974,0.00004542236,0.11345604],"genre_scores_gemma":[0.9428256,0.000013740342,0.00006431624,0.00033589717,0.00049974123,0.00057943433,0.00002791937,0.0000205173,0.05563285],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9970643,0.00072622055,0.0003596771,0.0004928563,0.0009936859,0.00036325192],"domain_scores_gemma":[0.9984128,0.00016168041,0.0004020673,0.00060943206,0.00024050506,0.00017351726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014605116,0.00020780685,0.00023693,0.00018469259,0.001023219,0.0006708124,0.0010390998,0.00011136856,0.00032094072],"category_scores_gemma":[0.0006016518,0.00021140724,0.00005871077,0.00023651232,0.00018644895,0.0007146102,0.000030903182,0.00022673339,0.00043842412],"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":[0.00005284118,0.0102970535,0.2921088,0.000005481306,0.000027014496,3.5238173e-7,0.6038112,1.3027476e-7,0.00005746705,0.00929993,0.07295468,0.01138501],"study_design_scores_gemma":[0.00060534175,0.000120581564,0.40024042,0.000059346396,0.000018093813,4.8814947e-8,0.5884625,3.9608295e-7,0.000021234175,0.001066467,0.009233716,0.00017186465],"about_ca_topic_score_codex":0.0051514055,"about_ca_topic_score_gemma":0.002164145,"teacher_disagreement_score":0.1081316,"about_ca_system_score_codex":0.00056935684,"about_ca_system_score_gemma":0.0014526836,"threshold_uncertainty_score":0.86209375},"labels":[],"label_agreement":null},{"id":"W2620495706","doi":"10.5539/elt.v10n6p37","title":"Building a Positive Environment in Classrooms through Feedback and Praise","year":2017,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Praise; Psychology; Incentive; Perception; Mathematics education; Order (exchange); Pedagogy; Social psychology","score_opus":0.015840281702753478,"score_gpt":0.3369877777825241,"score_spread":0.3211474960797706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620495706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84570765,0.00031585438,0.00023163958,0.0005641632,0.00025902537,0.00023290335,0.0000033769986,0.000058130885,0.15262724],"genre_scores_gemma":[0.99311996,0.00009103607,0.004876826,0.00008439761,0.0006040431,0.0000127893645,0.0000027700892,0.0000151026325,0.001193069],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9986528,0.00022189757,0.00015028795,0.00029382738,0.0003173719,0.00036380786],"domain_scores_gemma":[0.9993798,0.00014834221,0.00012654069,0.0002644476,0.000007897729,0.00007296771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010791047,0.00013239353,0.00017121031,0.000044038436,0.001144087,0.00045443635,0.00036962092,0.000090307694,0.00011940773],"category_scores_gemma":[0.0007224404,0.00013339186,0.000041822048,0.000026583446,0.00020792973,0.00085583975,0.00022468646,0.0003972751,0.000010376125],"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":[0.000012445723,0.00007990028,0.08710966,0.0000062931667,0.00002118931,0.000046277837,0.8564379,0.0000034683048,0.00064614264,0.032619264,0.000095079,0.02292237],"study_design_scores_gemma":[0.002479552,0.00008893823,0.22303867,0.00026856485,0.000049694907,0.0000018063926,0.7219609,0.00008115256,0.0002200833,0.002113777,0.048897434,0.00079944223],"about_ca_topic_score_codex":0.0048644673,"about_ca_topic_score_gemma":0.0010726793,"teacher_disagreement_score":0.15143417,"about_ca_system_score_codex":0.00013994686,"about_ca_system_score_gemma":0.00002526721,"threshold_uncertainty_score":0.87995076},"labels":[],"label_agreement":null},{"id":"W2622935668","doi":"10.3138/jvme.0616-113r","title":"Adaptive Comparative Judgment: A Tool to Support Students' Assessment Literacy","year":2017,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ranking (information retrieval); Cohort; Task (project management); Psychology; Process (computing); Work (physics); Mathematics education; Medical education; Computer science; Applied psychology; Information retrieval; Statistics; Medicine; Mathematics; Engineering","score_opus":0.156100825334503,"score_gpt":0.5426009298816273,"score_spread":0.38650010454712436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2622935668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97046375,0.00004143359,0.00043840334,0.008374297,0.0034842629,0.00030235873,0.0000016049388,0.000008648417,0.016885234],"genre_scores_gemma":[0.99241227,0.00010474429,0.0035243668,0.00090396416,0.0015016755,0.00002174217,0.000002442869,0.0000065734766,0.0015222081],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99689025,0.00022544662,0.0005074413,0.00015227565,0.001983294,0.00024126619],"domain_scores_gemma":[0.99809086,0.00010701091,0.00063363474,0.00021892892,0.00047241093,0.0004771796],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020734188,0.00011872876,0.0002841866,0.00012670973,0.00068749674,0.00045524788,0.001143751,0.00011014934,0.001621277],"category_scores_gemma":[0.0005510042,0.00010260092,0.00011266312,0.00009160454,0.00016940404,0.0009496092,0.00018920803,0.00039653128,0.00005318632],"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":[0.0012187664,0.008354378,0.24092823,0.000050252627,0.0005597769,0.00036440708,0.21223554,0.0000037862508,0.0005339279,0.00941043,0.12207374,0.40426677],"study_design_scores_gemma":[0.0011603712,0.0033604128,0.72013915,0.00036161047,0.00006428964,0.000050186776,0.01775181,0.000019924979,0.000009417327,0.0004497734,0.25639883,0.00023425015],"about_ca_topic_score_codex":0.00011711978,"about_ca_topic_score_gemma":0.00002739468,"teacher_disagreement_score":0.47921088,"about_ca_system_score_codex":0.00034736618,"about_ca_system_score_gemma":0.0025602218,"threshold_uncertainty_score":0.99929136},"labels":[],"label_agreement":null},{"id":"W2624412722","doi":"10.3102/0034654316689306","title":"Rethinking the Use of Tests: A Meta-Analysis of Practice Testing","year":2017,"lang":"en","type":"article","venue":"Review of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":536,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Psychology; Meta-analysis; Test (biology); Best practice; Presentation (obstetrics); Mathematics education; Applied psychology; Medicine","score_opus":0.7954275058930537,"score_gpt":0.643213236651155,"score_spread":0.15221426924189863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624412722","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036064453,0.2325587,0.000012370887,0.36995274,0.00025727059,0.0027968069,0.00006019995,0.000007462227,0.35829002],"genre_scores_gemma":[0.8991355,0.07381168,0.017730024,0.00052136567,0.00027243493,0.0001530594,0.000014889101,0.000013422925,0.008347641],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9963712,0.0011282855,0.00041948553,0.00014113008,0.0017764948,0.00016337729],"domain_scores_gemma":[0.96716857,0.028140178,0.0007928132,0.00061048206,0.003246295,0.000041635154],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013333561,0.00005219842,0.0004587626,0.00014120959,0.0006692388,0.00008326961,0.0009011544,0.000027880555,0.0014831005],"category_scores_gemma":[0.15438932,0.000033183813,0.00035849118,0.0012198512,0.0007048753,0.00039567286,0.00015722889,0.00017719268,0.0000074816535],"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":[0.000027442975,0.001441232,0.21500508,0.00393856,0.07487441,8.058294e-7,0.031116033,0.00002031982,0.00036984094,0.6287912,0.035854336,0.00856071],"study_design_scores_gemma":[0.00016403988,0.00013539445,0.52324986,0.002957338,0.11978017,9.2548026e-7,0.0073676957,0.000081377184,0.00005583377,0.010516028,0.33539802,0.00029332534],"about_ca_topic_score_codex":0.006231942,"about_ca_topic_score_gemma":0.00043368308,"teacher_disagreement_score":0.863071,"about_ca_system_score_codex":0.000046700072,"about_ca_system_score_gemma":0.0011232425,"threshold_uncertainty_score":0.9994297},"labels":[],"label_agreement":null},{"id":"W2707915995","doi":"10.7213/1981-416x.17.052.ds06","title":"Autoavaliação e avaliação pelos pares: uma análise de pesquisas internacionais recentes","year":2017,"lang":"pt","type":"article","venue":"Revista Diálogo Educacional","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Psychology; Humanities; Pedagogy; Philosophy","score_opus":0.07031719651890204,"score_gpt":0.3937317090621989,"score_spread":0.32341451254329684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2707915995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87621254,0.0072099236,0.0002156298,0.0455483,0.01317656,0.0019941088,0.0005873366,0.0003615217,0.05469408],"genre_scores_gemma":[0.9086576,0.0042354325,0.00035212288,0.00060560345,0.004013143,0.000092400725,0.00013933258,0.00009584152,0.0818085],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99315983,0.0007928165,0.0010348022,0.0012824322,0.0018476846,0.0018824042],"domain_scores_gemma":[0.9952641,0.00050278875,0.0012223696,0.0015471979,0.00048476105,0.000978768],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025873675,0.0008218569,0.0009992195,0.00023455554,0.0038998737,0.002990447,0.0034599395,0.0005164376,0.013591478],"category_scores_gemma":[0.0019506725,0.0008297544,0.0008050818,0.00028416704,0.0013007143,0.0010765219,0.00091398525,0.00086192664,0.0023736865],"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":[0.00025539336,0.001504218,0.5175592,0.00036174626,0.0005962911,0.00012206214,0.035132047,0.0000023865482,0.00024350303,0.06477831,0.3664471,0.012997806],"study_design_scores_gemma":[0.0013600539,0.00019033022,0.19644547,0.0012754564,0.000373658,0.000023176062,0.019043403,0.00019963943,0.000041912146,0.0009907879,0.7787997,0.0012563936],"about_ca_topic_score_codex":0.0009564909,"about_ca_topic_score_gemma":0.0006596956,"teacher_disagreement_score":0.41235262,"about_ca_system_score_codex":0.0010376825,"about_ca_system_score_gemma":0.0018482148,"threshold_uncertainty_score":0.99941534},"labels":[],"label_agreement":null},{"id":"W2735739974","doi":"10.4018/978-1-5225-2953-8.ch004","title":"Technology and Teaching","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Implementation; Mathematics education; Student engagement; Student centered; Psychology; Work (physics); Pedagogy; Computer science; Engineering","score_opus":0.02251533609322583,"score_gpt":0.3289112032534644,"score_spread":0.3063958671602386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735739974","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000352532,0.055496767,0.00009080202,0.021260465,0.0010687335,0.0005491415,0.00001910714,0.0003335882,0.9208289],"genre_scores_gemma":[0.01267878,0.29036456,0.04789954,0.000092358285,0.00052543264,0.00018443206,0.00002617116,0.000047819525,0.6481809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871427,0.000020657626,0.00026391266,0.00045367065,0.00029562233,0.00025184304],"domain_scores_gemma":[0.99917805,0.00019478107,0.00027425226,0.00022909555,0.000090165326,0.000033641823],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0002635428,0.00026241218,0.0003031202,0.00060063996,0.0012183255,0.00013611696,0.00040263234,0.0005174558,0.00011807731],"category_scores_gemma":[0.0003416502,0.00026880388,0.0000339336,0.00003110476,0.0032268234,0.001738017,0.00020842158,0.0005776272,0.0000067116575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014224381,0.000008591707,0.0011210656,0.00001551326,0.000017052858,0.0000016837076,0.00015599173,9.3228437e-7,0.0000048637926,0.86384094,0.00031524737,0.1345039],"study_design_scores_gemma":[0.00006852472,0.000033567536,0.000343261,0.000096580006,0.000007709004,0.000016820053,0.0017062373,4.874337e-7,0.0000041955527,0.4800696,0.51748645,0.00016656026],"about_ca_topic_score_codex":0.000018984909,"about_ca_topic_score_gemma":0.0001573303,"teacher_disagreement_score":0.5171712,"about_ca_system_score_codex":0.00014255784,"about_ca_system_score_gemma":0.00028756313,"threshold_uncertainty_score":0.9999764},"labels":[],"label_agreement":null},{"id":"W2736595548","doi":"","title":"POSTER: A Validity Argument Approach to Collaborative Development of the Colleges Mathematics Assessment Program","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Argument (complex analysis); Test (biology); Mathematics education; Computer science; Psychology","score_opus":0.08059059746095346,"score_gpt":0.3733509050348911,"score_spread":0.2927603075739377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736595548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5015751,0.00002957166,0.0077163638,0.005548357,0.000671582,0.0047310945,0.000055451772,0.00013857958,0.47953388],"genre_scores_gemma":[0.94571674,0.000031403786,0.046641488,0.000049371054,0.000053346623,0.0003832296,0.0000013731276,0.0000095871765,0.0071134586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789023,0.00021713618,0.00037616264,0.00027944022,0.00087970664,0.00035729224],"domain_scores_gemma":[0.99862915,0.00018160148,0.00024669364,0.00030456134,0.000503567,0.00013441945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008781064,0.00017016113,0.00026140705,0.000049115086,0.0004083374,0.00010847879,0.0007081878,0.00007716592,0.00014971885],"category_scores_gemma":[0.00010647258,0.00009108636,0.000060013394,0.00040715226,0.00026287592,0.00013826841,0.0002574499,0.00006597025,0.00005158593],"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":[0.00010160263,0.0063780695,0.14502732,0.00020881074,0.00051230984,0.0000024876792,0.23388965,0.0000015659311,0.0127717005,0.41276556,0.019654948,0.16868596],"study_design_scores_gemma":[0.0038634138,0.00084798335,0.37214988,0.0017922749,0.00020443829,0.0000017565382,0.1001458,0.000051307157,0.02399788,0.008331245,0.486701,0.0019129973],"about_ca_topic_score_codex":0.000048309736,"about_ca_topic_score_gemma":0.00025699922,"teacher_disagreement_score":0.47242042,"about_ca_system_score_codex":0.00024362016,"about_ca_system_score_gemma":0.0017719534,"threshold_uncertainty_score":0.3714394},"labels":[],"label_agreement":null},{"id":"W2748587261","doi":"10.23977/aetp.2017.12002","title":"An Empirical Study on Learning-oriented Assessment","year":2017,"lang":"en","type":"article","venue":"Advances in Educational Technology and Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empirical research; Autonomy; Process (computing); Knowledge management; Management science; Psychology; Computer science; Mathematics education; Epistemology; Engineering; Political science","score_opus":0.038723680210979806,"score_gpt":0.5333790424297817,"score_spread":0.4946553622188019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2748587261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91071254,0.00021403626,0.00007256956,0.028209774,0.0010031941,0.00023955878,6.837224e-7,0.000049418366,0.05949821],"genre_scores_gemma":[0.997572,0.00052800355,0.0006863908,0.00032373468,0.00016341137,0.00010654258,0.0000042909764,0.0000056477124,0.000609954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99887806,0.00018047218,0.00015581747,0.000384676,0.00016256011,0.00023840519],"domain_scores_gemma":[0.9992893,0.00014463495,0.00012739225,0.0003374179,0.000050573668,0.000050702743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004995089,0.00009625936,0.00014454077,0.00023984969,0.0010431667,0.000038723345,0.0004635698,0.00016868771,0.00014919727],"category_scores_gemma":[0.00021750532,0.00009477182,0.000014226798,0.0002083443,0.00082012406,0.00032103324,0.00004329869,0.00039601387,0.000021294378],"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":[0.000019631814,0.0010287955,0.85858595,5.918619e-7,0.0000070163883,0.0000025580687,0.0016058465,0.0000016625821,0.0000076256397,0.1287757,0.00010315482,0.0098614665],"study_design_scores_gemma":[0.00050053676,0.00054071494,0.8835029,0.0000047532326,0.0000042373226,0.0000012294036,0.009801318,0.0000041182875,6.643783e-7,0.049796436,0.055748932,0.00009416305],"about_ca_topic_score_codex":0.000027245349,"about_ca_topic_score_gemma":0.0003849363,"teacher_disagreement_score":0.086859465,"about_ca_system_score_codex":0.00004414876,"about_ca_system_score_gemma":0.00008606065,"threshold_uncertainty_score":0.8023301},"labels":[],"label_agreement":null},{"id":"W2749119382","doi":"10.1080/87567555.2017.1349075","title":"Improving the Quality of Constructive Peer Feedback","year":2017,"lang":"en","type":"article","venue":"College Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Constructive; Quality (philosophy); Computer science; Peer feedback; Simple (philosophy); Order (exchange); Mathematics education; Management science; Engineering ethics; Psychology; Epistemology; Engineering; Process (computing); Business","score_opus":0.0595169331783962,"score_gpt":0.4026046221552969,"score_spread":0.34308768897690073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749119382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68056595,0.000027495165,0.0001516333,0.0026247797,0.00057095714,0.00024966616,0.000013970179,0.000028837374,0.3157667],"genre_scores_gemma":[0.99042314,0.000003822915,0.0007518705,0.000047520378,0.0003088654,0.000007012284,7.070251e-7,0.000006594477,0.0084504355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9983534,0.00039453298,0.00022567874,0.00016591336,0.0006265156,0.000233954],"domain_scores_gemma":[0.9985841,0.00039278544,0.00041018394,0.00041620532,0.0001470487,0.0000496784],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0042814617,0.00008622997,0.00018312287,0.000024848969,0.0038464747,0.00020559134,0.00084242976,0.000062178675,0.000094784315],"category_scores_gemma":[0.002289536,0.00006410171,0.000096107884,0.0000411504,0.00074324233,0.0003599187,0.00021285462,0.00026888243,0.000011816878],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000315972,0.00005589733,0.25625423,0.000014406686,0.000060069367,0.000001854501,0.043423243,6.532586e-7,0.0014132564,0.6812207,0.0025436094,0.014980477],"study_design_scores_gemma":[0.0013329699,0.00004225904,0.7277824,0.000050852475,0.000055606153,8.979621e-7,0.23320796,0.0001062266,0.00025725065,0.0060778577,0.0307113,0.00037436828],"about_ca_topic_score_codex":0.0073494785,"about_ca_topic_score_gemma":0.0015286102,"teacher_disagreement_score":0.6751428,"about_ca_system_score_codex":0.00007302071,"about_ca_system_score_gemma":0.0001505003,"threshold_uncertainty_score":0.99926066},"labels":[],"label_agreement":null},{"id":"W2752208322","doi":"10.5539/elt.v10n10p1","title":"Exploring Students’ Perspectives toward Clarity and Familiarity of Writing Scoring Rubrics: The Case of Saudi EFL Students","year":2017,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; CLARITY; Psychology; Mathematics education; Quality (philosophy); Set (abstract data type); Strengths and weaknesses; Medical education; Computer science; Social psychology; Medicine; Chemistry","score_opus":0.09083715100315995,"score_gpt":0.39897892087104897,"score_spread":0.308141769867889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752208322","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98785096,0.000698291,0.00004928983,0.00007659285,0.0003972074,0.0002999787,0.000007942186,0.000060991726,0.010558735],"genre_scores_gemma":[0.99849063,0.00027773244,0.00047975266,0.000009554122,0.0006116513,0.000015236658,9.459564e-7,0.000015272375,0.000099240184],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.997893,0.00043328904,0.00032204943,0.0003082513,0.000713495,0.00032992475],"domain_scores_gemma":[0.9985593,0.00043170794,0.0003638511,0.00045290895,0.00010967498,0.000082557475],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0044969087,0.00015971913,0.0003091582,0.000075561155,0.0019017785,0.0005173506,0.0010969914,0.000067879635,0.000015012917],"category_scores_gemma":[0.002627798,0.00013695886,0.000100337005,0.00008100994,0.000418762,0.0009649887,0.0008164802,0.0005867888,5.928071e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058570768,0.00008489204,0.4725464,0.000030649844,0.00005119369,0.00006145148,0.5199921,6.792164e-7,0.00012992027,0.0028523616,0.0000027107633,0.004241746],"study_design_scores_gemma":[0.00038110948,0.000021359281,0.2547546,0.00011516124,0.00004500692,0.0000023525427,0.74439526,0.000007944034,0.0000860532,0.000049009806,0.000024681858,0.000117480246],"about_ca_topic_score_codex":0.020269237,"about_ca_topic_score_gemma":0.0018805478,"teacher_disagreement_score":0.2244031,"about_ca_system_score_codex":0.00009357121,"about_ca_system_score_gemma":0.000031960444,"threshold_uncertainty_score":0.99939764},"labels":[],"label_agreement":null},{"id":"W2752466276","doi":"10.5430/wje.v7n4p117","title":"Constructing Quality Feedback to the Students in Distance Learning: Review of the Current Evidence with Reference to the Online Master Degree in Transplantation","year":2017,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Distance education; Diversity (politics); Quality (philosophy); Curriculum; Construct (python library); Mathematics education; Course (navigation); Psychology; Computer science; Transplantation; Instructional design; Cultural diversity; Medical education; Pedagogy; Engineering; Medicine; Sociology","score_opus":0.18350038372953567,"score_gpt":0.4812443724095541,"score_spread":0.2977439886800184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752466276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9449452,0.00319151,0.00009753171,0.047583822,0.0006645691,0.0006247572,0.0000019871256,0.000001447552,0.002889168],"genre_scores_gemma":[0.99516034,0.0039074337,0.00014693639,0.00026008402,0.00013045207,0.0000100358975,6.790652e-7,0.0000029060257,0.00038114164],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99813354,0.00053216185,0.00044548645,0.00009830029,0.0006690729,0.000121409095],"domain_scores_gemma":[0.9984806,0.00025465057,0.000775422,0.00021141784,0.00023793904,0.000039931834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029191626,0.00006806232,0.00015413138,0.000057404715,0.00029421478,0.000110129375,0.0009684905,0.000010948113,0.000021741123],"category_scores_gemma":[0.00076777226,0.000033967768,0.00003544766,0.00039010262,0.00009649895,0.00027400034,0.000041891355,0.00033006156,0.0000021894066],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005384399,0.00008124424,0.9252963,0.00011194227,0.0000046603086,1.635043e-7,0.010467797,0.000015776399,0.000007505193,0.00076542905,0.00016406643,0.06303127],"study_design_scores_gemma":[0.00012811308,0.000023288705,0.9695163,0.011180031,0.000021601463,8.0184145e-7,0.010383523,5.394767e-7,0.0000054167067,0.000044100398,0.008648219,0.00004806452],"about_ca_topic_score_codex":0.00048426108,"about_ca_topic_score_gemma":0.081650615,"teacher_disagreement_score":0.08116636,"about_ca_system_score_codex":0.00016812478,"about_ca_system_score_gemma":0.0003813652,"threshold_uncertainty_score":0.9351069},"labels":[],"label_agreement":null},{"id":"W2752920591","doi":"10.5430/wje.v7n4p85","title":"A Combination of Teacher-Led Assessment and Self-Assessment Drives the Learning Process in Online Master Degree in Transplantation","year":2017,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Peer assessment; Psychology; Diversity (politics); Formative assessment; Online assessment; Self-assessment; Educational assessment; Medical education; Test (biology); Mathematics education; Process (computing); Alternative assessment; Educational measurement; Pedagogy; Curriculum; Computer science; Medicine","score_opus":0.04002629537659467,"score_gpt":0.4148616437604832,"score_spread":0.3748353483838885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752920591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98679733,0.00007892113,0.00006629984,0.0041634804,0.00028784954,0.00021951187,2.6947114e-7,0.0000029091561,0.008383445],"genre_scores_gemma":[0.99854183,0.00043672908,0.0006003729,0.00001749416,0.00011459821,0.000008808644,0.000003156048,0.0000045299025,0.00027246802],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99883765,0.0002634835,0.00035583985,0.000081983235,0.00035363217,0.00010739938],"domain_scores_gemma":[0.99894416,0.00011259024,0.0006795933,0.00007165943,0.00016021474,0.000031797128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012889697,0.000066974244,0.00014532715,0.00023804193,0.00024602926,0.00011822459,0.00022258214,0.00003100512,0.00002684323],"category_scores_gemma":[0.000041654643,0.000052588355,0.000028612054,0.0001622539,0.00007115171,0.0005366494,0.000011897101,0.00026758978,1.7258917e-7],"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":[0.000018527331,0.0007363903,0.95521337,0.000024647765,0.000012347559,7.9219194e-7,0.029306723,0.00003451785,0.000109618566,0.002234593,0.000012204733,0.012296279],"study_design_scores_gemma":[0.00079190824,0.00006233971,0.9651971,0.00019142828,0.000029574283,0.0000011366678,0.03237852,0.00022832761,0.000011647809,0.00088332035,0.00017194363,0.000052776628],"about_ca_topic_score_codex":0.00022917603,"about_ca_topic_score_gemma":0.0059915935,"teacher_disagreement_score":0.012243503,"about_ca_system_score_codex":0.00021446178,"about_ca_system_score_gemma":0.0005418424,"threshold_uncertainty_score":0.33434498},"labels":[],"label_agreement":null},{"id":"W2755415388","doi":"10.20381/ruor-20914","title":"Assessment Strategies in Higher Education: A Case Study of Conestoga College’s Fitness and Health Promotion Program","year":2017,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Medical education; Psychology; Gerontology; Mathematics education; Medicine; Political science","score_opus":0.20814197588610014,"score_gpt":0.5135839410944316,"score_spread":0.30544196520833145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755415388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8669044,0.000053061,3.1625754e-7,0.0010450514,0.00026060885,0.002602411,0.000012007225,0.000017077897,0.12910509],"genre_scores_gemma":[0.9504513,0.00016961886,0.00020420837,9.355742e-7,0.000052518655,0.000018491226,0.00006845841,0.000008815092,0.04902562],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99738824,0.0006480287,0.00020314245,0.00035046547,0.0010889507,0.00032119267],"domain_scores_gemma":[0.9984148,0.00008900998,0.000403232,0.0002640756,0.0006942315,0.00013463461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021004933,0.00012807272,0.00039400897,0.0005652748,0.0011581643,0.000111220645,0.00047895932,0.00017954614,0.00031550712],"category_scores_gemma":[0.000020741112,0.000156643,0.000044960696,0.00049472554,0.00040575038,0.0004726719,0.00007001527,0.0003981043,0.0000014056516],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041114577,0.013467026,0.6436322,0.0015599945,0.0002163622,0.00068182434,0.13335758,0.0000018358959,0.000017487999,0.16482604,0.0035215195,0.038677044],"study_design_scores_gemma":[0.00060703105,0.0007758656,0.4842497,0.00012870267,0.000014968128,0.0000013790833,0.5108234,0.000003467529,2.85607e-7,0.00020855226,0.0031060472,0.00008055609],"about_ca_topic_score_codex":0.042928096,"about_ca_topic_score_gemma":0.37988472,"teacher_disagreement_score":0.37746584,"about_ca_system_score_codex":0.00034719554,"about_ca_system_score_gemma":0.0041111056,"threshold_uncertainty_score":0.9634451},"labels":[],"label_agreement":null},{"id":"W2755836585","doi":"10.31468/cjsdwr.604","title":"Designing Effective Training Programs for Discipline-Specific Peer Writing Tutors","year":2017,"lang":"en","type":"article","venue":"Discourse and Writing/Rédactologie","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Writing center; TUTOR; Scholarship; Discipline; Professional writing; Staffing; Pedagogy; Statement (logic); Academic writing; Medical education; Writing process; Set (abstract data type); Mathematics education; Psychology; Computer science; Sociology; Medicine; Political science","score_opus":0.22245111841040197,"score_gpt":0.4834576000515734,"score_spread":0.26100648164117146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755836585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96482044,0.00045643648,0.0022392196,0.0051127463,0.00063227967,0.0015553946,0.000016089001,0.00023735185,0.02493003],"genre_scores_gemma":[0.9941577,0.00013165698,0.0032905843,0.000038788698,0.0012765813,0.00029827654,0.000028890056,0.000032611348,0.0007449218],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9976209,0.000118888216,0.00032341137,0.0005533871,0.00048092773,0.0009025044],"domain_scores_gemma":[0.99822956,0.00078150764,0.00031621155,0.00029147306,0.00019783285,0.0001834183],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021651774,0.0002660437,0.0004055129,0.00007273772,0.004243893,0.0014775508,0.0005555182,0.00018436529,0.000023790337],"category_scores_gemma":[0.0006929658,0.00023789793,0.00017448165,0.00008447823,0.0009921651,0.0007390849,0.00017708953,0.00026347433,0.0000072325893],"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":[0.00008584827,0.00017325146,0.49483356,0.000052337924,0.00011568218,0.000038024526,0.04873118,0.0000017405009,0.0006765219,0.027566561,0.001136771,0.4265885],"study_design_scores_gemma":[0.0031230482,0.0004044397,0.30198437,0.00059439684,0.0002009885,0.000005810492,0.6681497,0.0001467663,0.0004418286,0.006739727,0.016913569,0.0012953202],"about_ca_topic_score_codex":0.00010989179,"about_ca_topic_score_gemma":0.00017620137,"teacher_disagreement_score":0.61941856,"about_ca_system_score_codex":0.00007708614,"about_ca_system_score_gemma":0.00010288312,"threshold_uncertainty_score":0.999559},"labels":[],"label_agreement":null},{"id":"W2756771427","doi":"10.20343/teachlearninqu.5.2.8","title":"ComPAIR: A New Online Tool Using Adaptive Comparative Judgement to Support Learning with Peer Feedback","year":2017,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Peer feedback; Computer science; Grading (engineering); Judgement; Context (archaeology); Ranking (information retrieval); Set (abstract data type); Peer assessment; Mathematics education; Multimedia; Psychology; Artificial intelligence; Engineering","score_opus":0.20071591484426815,"score_gpt":0.44677908830839524,"score_spread":0.2460631734641271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756771427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9641713,0.00003664615,0.013074443,0.010272505,0.0010504058,0.00048996264,0.0000013751762,0.0001682566,0.01073512],"genre_scores_gemma":[0.9604234,0.000015977676,0.010866203,0.00036082938,0.0033293252,0.0000039125575,0.0000061117166,0.000047379297,0.02494686],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99483806,0.0014691318,0.0005099665,0.00041717035,0.001851316,0.00091436994],"domain_scores_gemma":[0.9974515,0.00035074007,0.0010067399,0.00038281077,0.00038894755,0.00041929772],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005697999,0.0003753907,0.00053485046,0.00016653932,0.013174729,0.0022155293,0.0015163996,0.000106222215,0.0004920818],"category_scores_gemma":[0.0009176757,0.00024599326,0.00019462842,0.00015821328,0.0005566875,0.0009628727,0.00042050783,0.0032851277,0.00014166706],"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":[0.0007282533,0.00034309694,0.26622823,0.0000071490226,0.0007082631,0.000112138594,0.6286691,0.05450852,0.00041898646,0.002467649,0.021107582,0.02470103],"study_design_scores_gemma":[0.002943088,0.0021136084,0.16232151,0.00058913947,0.00036839632,0.00012641444,0.41526186,0.004833941,0.000018575562,0.00025573224,0.41007313,0.001094605],"about_ca_topic_score_codex":0.0016732151,"about_ca_topic_score_gemma":0.0005913562,"teacher_disagreement_score":0.38896555,"about_ca_system_score_codex":0.00054090034,"about_ca_system_score_gemma":0.0006963837,"threshold_uncertainty_score":0.9999992},"labels":[],"label_agreement":null},{"id":"W2758542300","doi":"","title":"Supporting Preservice Mathematics Teachers","year":2017,"lang":"en","type":"article","venue":"2017 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Curriculum; Representation (politics); Reform mathematics; Connected Mathematics; Pedagogy; Computer science; Psychology; Political science","score_opus":0.09918820151996563,"score_gpt":0.4122161335718016,"score_spread":0.313027932051836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758542300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9452752,0.000044089196,0.000018645283,0.010740175,0.0010397943,0.0018363687,0.000014727013,0.000006034051,0.041024998],"genre_scores_gemma":[0.9914214,0.000013735565,0.00034964716,0.00005692725,0.00013392868,0.00006176285,0.0000014493291,0.000005966747,0.007955199],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9991422,0.00003632935,0.00019380388,0.000107397274,0.0002971336,0.00022311701],"domain_scores_gemma":[0.99819094,0.00013472258,0.0006049287,0.00062886317,0.00036451075,0.00007606091],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0011862536,0.00007233152,0.00012745366,0.000013953688,0.0030684455,0.00017999319,0.0016625758,0.000056745892,0.000056412682],"category_scores_gemma":[0.00048887235,0.00004970548,0.00017021122,0.00005390628,0.00036674505,0.00016578379,0.00007495578,0.00008694975,0.0000014628457],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003525325,0.0003767927,0.12706266,0.000054467,0.0002935735,1.9300018e-8,0.8077611,0.000003549053,0.00008046183,0.019122684,0.039628237,0.0056129685],"study_design_scores_gemma":[0.00029114613,0.000044593784,0.2010905,0.00005287171,0.00020409723,7.6329954e-8,0.78192806,0.00014990229,0.000033200708,0.0035292453,0.01256788,0.00010844814],"about_ca_topic_score_codex":0.38953668,"about_ca_topic_score_gemma":0.74008924,"teacher_disagreement_score":0.35055253,"about_ca_system_score_codex":0.00012810472,"about_ca_system_score_gemma":0.0022227103,"threshold_uncertainty_score":0.99822944},"labels":[],"label_agreement":null},{"id":"W2759176870","doi":"10.19173/irrodl.v18i6.2804","title":"An Evaluation Framework and Instrument for Evaluating e-Assessment Tools","year":2017,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Class (philosophy); Evaluation methods; Empirical research; Human–computer interaction; Multimedia; Management science; Knowledge management; Artificial intelligence; Engineering","score_opus":0.3896306194989309,"score_gpt":0.6372387545112699,"score_spread":0.24760813501233897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759176870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.884092,0.0069329794,0.0017773444,0.05619396,0.00037488533,0.0062366445,0.00005796477,0.000013803642,0.044320457],"genre_scores_gemma":[0.9833716,0.014266246,0.0018087958,0.00006339503,0.00007963085,0.00025795706,0.00006723528,0.0000038953367,0.00008121451],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973083,0.0008738188,0.00023723156,0.00019360885,0.0012005398,0.00018647373],"domain_scores_gemma":[0.99770737,0.0012468769,0.00021064664,0.00019424816,0.00058391836,0.000056938447],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.027898327,0.000057305846,0.00015221952,0.000044087097,0.0012242497,0.001040702,0.0010615133,0.0000350422,0.00016039905],"category_scores_gemma":[0.008503228,0.000043081003,0.000023667342,0.00008839908,0.0002693996,0.0005786929,0.00045733698,0.0002824901,0.000001011265],"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":[0.00008636638,0.00011505487,0.3203178,0.0003610938,0.000051334624,7.5735704e-7,0.0016240025,0.000028302386,0.000082898834,0.1741043,0.00035577515,0.5028723],"study_design_scores_gemma":[0.002618124,0.0005793917,0.8084773,0.0148775205,0.00006852728,0.000001301858,0.039066684,0.028277,0.000024981313,0.06363035,0.042106275,0.00027255758],"about_ca_topic_score_codex":0.00092194555,"about_ca_topic_score_gemma":0.00012366191,"teacher_disagreement_score":0.5025997,"about_ca_system_score_codex":0.00015579679,"about_ca_system_score_gemma":0.0003286534,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W2759938145","doi":"10.4018/978-1-5225-3873-8.ch008","title":"Questioning the Role of Tomorrow's Teacher","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prince Albert Grand Council; MacEwan University","funders":"","keywords":"Implementation; Student engagement; Mathematics education; Student centered; Pedagogy; Psychology; Work (physics); Student achievement; Academic achievement; Computer science; Engineering","score_opus":0.018020372229429902,"score_gpt":0.3109477808437555,"score_spread":0.2929274086143256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759938145","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022793983,0.06636466,0.000038395763,0.0061982158,0.0008074201,0.0004638015,0.000014708103,0.000108207234,0.92577666],"genre_scores_gemma":[0.049357336,0.23765627,0.018313505,0.000060819497,0.0009091054,0.0002527514,0.00003858437,0.000050338436,0.6933613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988951,0.000028834054,0.00027130626,0.00026220887,0.00037137544,0.00017119636],"domain_scores_gemma":[0.99901974,0.00021958009,0.0003692684,0.0002317187,0.00014069794,0.000018969504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002886308,0.00018665513,0.00022591933,0.00014877711,0.0007424372,0.00007765832,0.00049124204,0.00026292057,0.000277321],"category_scores_gemma":[0.00025350734,0.00015413512,0.000053427437,0.000033359876,0.0025571738,0.0012001503,0.0001147692,0.00032352228,0.0000049727623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018728586,0.000011106085,0.0017764475,0.000008529113,0.000018899078,2.7307786e-7,0.00038410808,0.000007881951,0.000007975979,0.9190007,0.00022070749,0.07854463],"study_design_scores_gemma":[0.00003923895,0.000022570264,0.000882479,0.00008821932,0.000009322289,0.000004265584,0.0035021831,0.000001292526,0.000023404265,0.48997974,0.5053396,0.000107670785],"about_ca_topic_score_codex":0.00007507021,"about_ca_topic_score_gemma":0.00027238578,"teacher_disagreement_score":0.5051189,"about_ca_system_score_codex":0.00011592232,"about_ca_system_score_gemma":0.00037381792,"threshold_uncertainty_score":0.9422013},"labels":[],"label_agreement":null},{"id":"W2763216313","doi":"","title":"Examining Teacher Educators","year":2017,"lang":"en","type":"article","venue":"2017 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Literacy; Pedagogy; Teacher education; Mathematics education; Political science; Sociology; Psychology; Medical education; Medicine","score_opus":0.13190998328439435,"score_gpt":0.38739968457659785,"score_spread":0.2554897012922035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763216313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9458553,0.000060719336,0.0000039107076,0.005874389,0.0020382563,0.001093235,0.0000071025456,0.0000041869725,0.04506291],"genre_scores_gemma":[0.9883877,0.000020571359,0.00008758644,0.000060903825,0.00028414672,0.00007430486,0.0000012371405,0.0000063197986,0.011077219],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991873,0.0000519224,0.00015128203,0.00013185586,0.00026873412,0.00020889274],"domain_scores_gemma":[0.99850094,0.0001020192,0.00038966848,0.00062195596,0.00029715497,0.00008825406],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009074517,0.00007910677,0.00012579196,0.000020454343,0.0035417785,0.00017410482,0.001469559,0.00006194069,0.00008962006],"category_scores_gemma":[0.00036246926,0.00005461359,0.00014946207,0.000062276595,0.00055390963,0.00015542548,0.000058969556,0.00009647416,0.0000019009543],"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":[0.0000062526765,0.00038264616,0.5202968,0.000018242526,0.0002874677,1.44403955e-8,0.37170297,0.0000013496766,0.00006127485,0.015520939,0.07380722,0.01791478],"study_design_scores_gemma":[0.00018891484,0.00005049506,0.53646374,0.000027062406,0.00010925761,4.2822215e-8,0.44697925,0.000012554821,0.000013126005,0.00071480405,0.015362295,0.000078441924],"about_ca_topic_score_codex":0.42253184,"about_ca_topic_score_gemma":0.63992417,"teacher_disagreement_score":0.21739234,"about_ca_system_score_codex":0.00017630734,"about_ca_system_score_gemma":0.0035388784,"threshold_uncertainty_score":0.99775547},"labels":[],"label_agreement":null},{"id":"W2765391846","doi":"10.5539/ells.v7n4p66","title":"Error Correction in the Intensive Reading Class of English Majors","year":2017,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Corrective feedback; Negotiation; Class (philosophy); Reading (process); Mathematics education; Psychology; Empirical research; Pedagogy; Computer science; Mathematics; Linguistics; Sociology","score_opus":0.01941013569653671,"score_gpt":0.348323727994973,"score_spread":0.3289135922984363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765391846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.899756,0.005116444,3.359965e-7,0.00040256535,0.0032974442,0.00019834323,0.000006793197,0.000027371345,0.09119471],"genre_scores_gemma":[0.9955911,0.0007635633,0.000018721428,0.00011847926,0.0014348315,0.000013870705,0.0000055455616,0.0000048337265,0.0020490484],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9991735,0.0001471373,0.00013642544,0.00015729683,0.00020964596,0.00017595748],"domain_scores_gemma":[0.9987612,0.0002764412,0.00012718413,0.00018919019,0.00062446727,0.00002156506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007003108,0.00010014331,0.00019606612,0.00006126683,0.0006188745,0.0002618095,0.00024001492,0.0000808447,0.000009412612],"category_scores_gemma":[0.0064728404,0.00006654143,0.00004145619,0.00013315961,0.00030915873,0.00035221496,0.00008190651,0.00024698352,4.8461175e-7],"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":[0.00001311268,0.00001567749,0.01599871,0.00001334532,0.000036512687,0.000025950574,0.97287977,9.511765e-8,0.000009717744,0.0028844122,0.0074067884,0.0007159111],"study_design_scores_gemma":[0.00024689647,0.000029633837,0.01556713,0.00016891975,0.000019552372,3.504156e-7,0.9594411,0.000001349489,0.0000201822,0.00008215411,0.024339348,0.00008336165],"about_ca_topic_score_codex":0.00023558014,"about_ca_topic_score_gemma":0.001274556,"teacher_disagreement_score":0.09583511,"about_ca_system_score_codex":0.000021901988,"about_ca_system_score_gemma":0.000012733191,"threshold_uncertainty_score":0.7749062},"labels":[],"label_agreement":null},{"id":"W2767175506","doi":"10.5539/jel.v7n1p184","title":"Identifying New Jersey Teachers’ Assessment Literacy as Precondition for Implementing Student Growth Objectives","year":2017,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Competence (human resources); Psychology; Literacy; Mathematics education; Test (biology); Medical education; Data collection; Formative assessment; Pedagogy; Mathematics; Statistics; Medicine; Social psychology","score_opus":0.05151849873937381,"score_gpt":0.487412330567119,"score_spread":0.4358938318277452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767175506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97157437,0.00023743686,0.0013714803,0.0021910358,0.0013240423,0.00022527337,2.6242833e-7,0.000009709525,0.023066388],"genre_scores_gemma":[0.98392177,0.0002023107,0.0047790585,0.00006479935,0.0013939388,0.000007424783,0.0000029438738,0.000007997558,0.0096197715],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989276,0.0001683989,0.0002849403,0.00011696085,0.00031404628,0.00018803815],"domain_scores_gemma":[0.9984023,0.0001717794,0.0009295558,0.00006328764,0.00030594718,0.00012710785],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019400133,0.00007754311,0.00013942257,0.00012612627,0.002173098,0.0012802788,0.00021320874,0.0000387746,0.0002258392],"category_scores_gemma":[0.00064767036,0.00007507106,0.000085562104,0.000042473832,0.000043889122,0.00133929,0.0000424682,0.0002620517,0.0000024935543],"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":[0.000012290587,0.00014958871,0.64724463,0.000016448399,0.000098823024,5.798698e-7,0.24705724,0.000001526752,0.0004147696,0.006519097,0.0018307641,0.09665422],"study_design_scores_gemma":[0.000570841,0.00011981142,0.72664404,0.00011411113,0.00006532969,0.0000032108583,0.23146594,0.0000056962303,0.000023636383,0.0022681116,0.03862494,0.00009431043],"about_ca_topic_score_codex":0.00039273978,"about_ca_topic_score_gemma":0.00006626213,"teacher_disagreement_score":0.09655991,"about_ca_system_score_codex":0.00014448352,"about_ca_system_score_gemma":0.00062681775,"threshold_uncertainty_score":0.9997565},"labels":[],"label_agreement":null},{"id":"W2767233186","doi":"10.1007/978-3-319-66327-2_11","title":"Improving Teachers’ Assessment Literacy in Singapore Mathematics Classrooms: Authentic Assessment Task Design","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Competence (human resources); Authentic assessment; Literacy; Pedagogy; Task (project management); Psychology; Engineering; Curriculum","score_opus":0.05482641439953531,"score_gpt":0.37786931299253684,"score_spread":0.3230428985930015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767233186","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022448259,0.0001798296,0.022180965,0.0007250868,0.0010606365,0.0019765652,0.000014159789,0.00022357119,0.9734147],"genre_scores_gemma":[0.041976545,0.00035000418,0.06565129,0.00011188881,0.00067533326,0.00009837863,0.000061364495,0.00014963784,0.8909256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948664,0.0002216312,0.0011045394,0.0009601682,0.001881429,0.0009658442],"domain_scores_gemma":[0.99645615,0.0006114598,0.0013239015,0.0010772379,0.00023938571,0.00029186503],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035703538,0.0007912945,0.0010625055,0.00046007635,0.0010995249,0.0016607271,0.0015412838,0.00085417536,0.003478468],"category_scores_gemma":[0.00014013302,0.0007527339,0.00039556727,0.00006093683,0.0004945008,0.0009140511,0.00043276517,0.0013483142,0.00018415673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017203292,0.0008416721,0.0055833696,0.000309574,0.0005600518,0.00029945193,0.08303931,0.000010203662,0.00019197255,0.8180019,0.007520907,0.08362433],"study_design_scores_gemma":[0.0046177916,0.0007512962,0.009169402,0.0045299917,0.001568592,0.000011931369,0.02678497,0.0075650807,0.000010505034,0.261389,0.6772943,0.0063071656],"about_ca_topic_score_codex":0.0010400931,"about_ca_topic_score_gemma":0.0014329934,"teacher_disagreement_score":0.6697734,"about_ca_system_score_codex":0.001848157,"about_ca_system_score_gemma":0.0017232776,"threshold_uncertainty_score":0.99949235},"labels":[],"label_agreement":null},{"id":"W2767325736","doi":"10.1111/medu.13476","title":"Emotions and assessment: considerations for rater‐based judgements of entrustment","year":2017,"lang":"en","type":"review","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Formative assessment; Summative assessment; Scrutiny; Psychology; Context (archaeology); Cognition; Narrative; Educational assessment; Applied psychology; Medical education; Pedagogy; Medicine","score_opus":0.16881108364826525,"score_gpt":0.535704857181989,"score_spread":0.36689377353372377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767325736","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014485958,0.96803504,0.00051693467,0.0054734554,0.0030217257,0.0030225574,0.000053998,0.000031291434,0.019830512],"genre_scores_gemma":[0.00025815956,0.9937725,0.002570632,0.00026491407,0.00046787833,0.0006428252,0.0002434146,0.00001371029,0.0017659668],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983183,0.00023390651,0.00044719112,0.00024197529,0.0005721389,0.00018648582],"domain_scores_gemma":[0.99845886,0.0005314246,0.00046568274,0.0002258407,0.0001754006,0.00014276682],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010045362,0.00015084253,0.00056232145,0.00013021164,0.00067654165,0.00013737196,0.00022236932,0.00022517279,0.0011507709],"category_scores_gemma":[0.0017605819,0.00013214651,0.0001553807,0.00007479094,0.00029399167,0.00010530244,0.000038788963,0.00014696787,0.0000074930867],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[6.90605e-7,0.00045067575,0.00013558543,0.0019138029,0.000087301305,2.5160213e-7,0.00061693415,1.8787073e-8,2.9467115e-8,0.022379888,0.025638519,0.9487763],"study_design_scores_gemma":[0.00022608996,0.000026331412,0.00020562035,0.0023005018,0.0004064558,3.239228e-7,0.00030926886,0.000012072822,5.914694e-8,0.0008757645,0.9955219,0.00011561907],"about_ca_topic_score_codex":0.00015880055,"about_ca_topic_score_gemma":0.00016676699,"teacher_disagreement_score":0.9698834,"about_ca_system_score_codex":0.00016594675,"about_ca_system_score_gemma":0.009572543,"threshold_uncertainty_score":0.9997623},"labels":[],"label_agreement":null},{"id":"W2767495722","doi":"10.5539/hes.v7n4p71","title":"A Review of Protocols in Higher Education; How My Experience Made Me Question the Process","year":2017,"lang":"en","type":"review","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Syllabus; Appeal; Legitimacy; Higher education; Pedagogy; Process (computing); Mathematics education; Psychology; Academic standards; Public relations; Political science; Engineering ethics; Computer science; Engineering","score_opus":0.3590216986629853,"score_gpt":0.5980012229070725,"score_spread":0.2389795242440872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767495722","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008754498,0.9572142,9.961858e-8,0.0076922006,0.0026243369,0.014998676,0.0000032141247,0.000030788393,0.017427782],"genre_scores_gemma":[0.00007027763,0.8429113,0.000040776653,0.00037138816,0.0010993448,0.07935236,0.000015612106,0.000021532824,0.076117426],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972318,0.0006685763,0.00068211294,0.0004627231,0.00065377046,0.00030103655],"domain_scores_gemma":[0.99674964,0.00023559338,0.0014468939,0.0006360606,0.00086779584,0.000063999956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011371014,0.000357158,0.0012806425,0.00015243988,0.0005939162,0.00017618077,0.0010787508,0.00016653258,0.00041899394],"category_scores_gemma":[0.00022965061,0.00023537478,0.00022769097,0.0006978103,0.00059721124,0.0004247819,0.00011707965,0.0002649153,0.000038192742],"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":[0.0000073191295,0.0018619029,0.0031379154,0.2370196,0.00042119634,6.06862e-7,0.030646836,2.8253853e-8,2.9275202e-7,0.07304303,0.18302381,0.47083747],"study_design_scores_gemma":[0.000045587458,0.000011862597,0.0022525662,0.11393361,0.00017636702,3.5798422e-7,0.0060053626,2.6176339e-9,1.0916846e-7,0.00030324035,0.8770453,0.00022567567],"about_ca_topic_score_codex":0.00013650312,"about_ca_topic_score_gemma":0.000035920984,"teacher_disagreement_score":0.69402146,"about_ca_system_score_codex":0.00039571075,"about_ca_system_score_gemma":0.003074065,"threshold_uncertainty_score":0.9598305},"labels":[],"label_agreement":null},{"id":"W2770188235","doi":"10.1080/09585176.2017.1401550","title":"Student perspectives on assessment for learning","year":2017,"lang":"en","type":"article","venue":"The Curriculum Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics education; Thematic analysis; Terminology; Psychology; Portfolio; Coding (social sciences); Value (mathematics); Computer science; Qualitative research; Mathematics; Sociology","score_opus":0.038442820932403206,"score_gpt":0.43924623009331515,"score_spread":0.40080340916091195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770188235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7969167,0.00022887805,0.0012975818,0.014926429,0.0020277025,0.00053225626,0.000001080779,0.000044204917,0.18402511],"genre_scores_gemma":[0.9930295,0.00046032615,0.00042572655,0.00004771433,0.0021397925,0.000020498006,3.1947303e-7,0.000009274701,0.0038669019],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9984759,0.00026908494,0.00014522421,0.00013936218,0.00064091804,0.0003295227],"domain_scores_gemma":[0.9990409,0.00014482364,0.00032770884,0.00019483824,0.00019333704,0.00009837966],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0027405971,0.00009967885,0.00012881722,0.000036276026,0.008379923,0.0012788147,0.0009740979,0.000038945956,0.00021856505],"category_scores_gemma":[0.0002953215,0.00006155465,0.00015628159,0.00003841741,0.00022729792,0.0002544121,0.00008643037,0.000437949,0.000027473516],"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":[0.000029375617,0.00079691043,0.5256286,0.000004988092,0.00031598366,0.000016253374,0.1525251,0.00013026672,0.00009944267,0.28464657,0.016401237,0.019405263],"study_design_scores_gemma":[0.0010543182,0.00034509038,0.42726195,0.00005214727,0.000073489166,0.0000052687897,0.512233,0.00012462295,0.0000061999212,0.0028235142,0.055806223,0.00021415576],"about_ca_topic_score_codex":0.00009505637,"about_ca_topic_score_gemma":0.000055535642,"teacher_disagreement_score":0.35970795,"about_ca_system_score_codex":0.0002169047,"about_ca_system_score_gemma":0.000114925286,"threshold_uncertainty_score":0.99975795},"labels":[],"label_agreement":null},{"id":"W2770688448","doi":"10.3138/cmlr.599","title":"<scp>icy lee</scp> <i>Classroom Writing Assessment and Feedback in L2 School Contexts</i>","year":2017,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Physics; Computer science","score_opus":0.020499500489784463,"score_gpt":0.31604494254137944,"score_spread":0.295545442051595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770688448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85608625,0.06279314,0.00002780651,0.0022047518,0.00027314393,0.001007794,0.00016675705,0.00007441422,0.077365965],"genre_scores_gemma":[0.96725583,0.025335766,0.00070872717,0.001253482,0.0005144977,0.00009388526,0.00005295552,0.000066416,0.0047184224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996773,0.00037006478,0.00053172495,0.0006570666,0.0002297407,0.0014384146],"domain_scores_gemma":[0.99673605,0.00047676967,0.00033272814,0.0007668143,0.00017018488,0.0015174246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017623015,0.00039477588,0.0007549586,0.0002695322,0.0012777502,0.00069016666,0.0010172994,0.00021208095,0.00015349324],"category_scores_gemma":[0.0024416635,0.00041578917,0.0001574235,0.00024286381,0.00060608773,0.0006448931,0.00013769753,0.00048791192,0.00004136839],"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":[0.000007193933,0.00010098753,0.72645015,0.0031080416,0.00024113624,0.0041749286,0.081415474,0.0000032774667,0.0023331782,0.014204768,0.012258136,0.15570277],"study_design_scores_gemma":[0.0012780603,0.00008213389,0.7791774,0.009023377,0.00019291113,0.00009363111,0.046473462,0.0002741855,0.0000162268,0.0013894251,0.1612777,0.00072147],"about_ca_topic_score_codex":0.39801532,"about_ca_topic_score_gemma":0.9384726,"teacher_disagreement_score":0.5404573,"about_ca_system_score_codex":0.0012548834,"about_ca_system_score_gemma":0.0007717338,"threshold_uncertainty_score":0.9998294},"labels":[],"label_agreement":null},{"id":"W2774511859","doi":"10.1007/s41686-017-0012-2","title":"Exploring the Association Between Formative and Summative Assessments in a Pre-University Science Program","year":2017,"lang":"en","type":"article","venue":"Journal of Formative Design in Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Summative assessment; Formative assessment; Association (psychology); Psychology; Mathematics education","score_opus":0.13295555539503517,"score_gpt":0.4044958197641522,"score_spread":0.27154026436911705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774511859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9899196,0.000009894372,0.0020555167,0.00033189918,0.00013920927,0.0003688077,5.1608595e-7,0.000008294799,0.0071662595],"genre_scores_gemma":[0.9977716,0.00020291687,0.0018379487,0.000004080359,0.000061270635,0.0000049778714,1.924944e-7,0.0000032302144,0.000113747126],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977837,0.00075258216,0.0003083244,0.00008845684,0.00075043325,0.00031651117],"domain_scores_gemma":[0.9974845,0.000813616,0.0012700531,0.00006896727,0.00029660898,0.000066238405],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008998626,0.00008746868,0.00021498621,0.0003024673,0.0018303454,0.00048616147,0.0005881343,0.000039317652,0.0000036300842],"category_scores_gemma":[0.0014561821,0.00006874511,0.000041444506,0.00038234988,0.00036350923,0.0074985423,0.00013591452,0.00062906876,0.0000016747687],"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":[0.000047016983,0.000035997877,0.71203834,0.0000053136,0.00003440397,0.000005003853,0.26808703,0.00011261742,0.000023220258,0.0005803185,0.000010842622,0.01901993],"study_design_scores_gemma":[0.00066141534,0.00021822134,0.8997978,0.00014430135,0.000016936669,5.27887e-7,0.09763886,0.000573537,0.000052591695,0.00030381908,0.00051310554,0.00007888951],"about_ca_topic_score_codex":0.00021314344,"about_ca_topic_score_gemma":0.000117860065,"teacher_disagreement_score":0.18775947,"about_ca_system_score_codex":0.0009324517,"about_ca_system_score_gemma":0.0002537354,"threshold_uncertainty_score":0.99946916},"labels":[],"label_agreement":null},{"id":"W2775898509","doi":"","title":"Grading Policies and Practices in Canada: A Landscape Study","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Accountability; Formative assessment; Policy analysis; Geography; Political science; Pedagogy; Psychology; Public administration; Engineering","score_opus":0.06697337941789532,"score_gpt":0.4357721105361669,"score_spread":0.36879873111827155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775898509","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8984842,0.00013098623,7.4444856e-8,0.08331844,0.00018476773,0.000069872935,0.000004180656,3.1880327e-7,0.017807176],"genre_scores_gemma":[0.9984634,0.000064719716,0.000021796945,0.00022004593,0.00058424234,0.0000018103435,9.3666426e-7,0.0000021468504,0.0006409094],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994517,0.00005383373,0.00015998175,0.000058780166,0.0001409756,0.00013470305],"domain_scores_gemma":[0.9990109,0.00013741868,0.00037792744,0.00005220748,0.000081868035,0.00033964484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003327363,0.000047397414,0.00008318298,0.00016823647,0.0006801865,0.00034679694,0.00013907519,0.000018363678,0.00009703855],"category_scores_gemma":[0.0010969043,0.000046582583,0.000009274943,0.000065987355,0.000115530755,0.0003503041,0.000005446162,0.000078153294,4.668897e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038229396,0.000015859,0.9589181,0.0000017035966,0.000008520156,0.0000053999597,0.010393489,1.6783905e-7,9.848486e-7,0.029158076,0.0011591451,0.00033471387],"study_design_scores_gemma":[0.00017494251,0.00004372129,0.9480339,0.0000103161565,0.0000071187387,0.000012128596,0.042258784,0.0000013925801,5.2218223e-7,0.0008356073,0.008575124,0.000046426172],"about_ca_topic_score_codex":0.9847529,"about_ca_topic_score_gemma":0.9996393,"teacher_disagreement_score":0.099979214,"about_ca_system_score_codex":0.0002107644,"about_ca_system_score_gemma":0.029174186,"threshold_uncertainty_score":0.9763295},"labels":[],"label_agreement":null},{"id":"W277639878","doi":"","title":"Teachers' Perceptions of Gender Equity in Writing Assessment.","year":2001,"lang":"en","type":"article","venue":"English quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Gender equity; Perception; Psychology; Equity (law); Pedagogy; Writing assessment; Secondary education; Higher education; Sociology; Mathematics education; Gender studies; Political science","score_opus":0.044112345819574,"score_gpt":0.4051884317873846,"score_spread":0.3610760859678106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W277639878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6642051,0.000022140888,0.00018052095,0.00009885824,0.00023645972,0.000123617,0.0000017242062,0.000051616524,0.33508],"genre_scores_gemma":[0.9978154,0.000028260849,0.0007144276,0.000033500604,0.00048633653,0.000016311611,0.000005907631,0.000008668853,0.0008912053],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984325,0.00022059724,0.00028972366,0.0001919376,0.00046252145,0.00040271325],"domain_scores_gemma":[0.9994608,0.00011981626,0.00008103755,0.00014655468,0.00011444944,0.00007729605],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012774079,0.00009269744,0.00016697637,0.000111009744,0.00021681111,0.00009228277,0.00028073392,0.00009451225,0.0011768573],"category_scores_gemma":[0.000057535737,0.000102528815,0.00007689402,0.00037584902,0.00013040926,0.00042007316,0.000029775043,0.00021128975,0.00001823387],"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":[0.0000031734548,0.00017561155,0.71281165,0.0000048385327,0.000012337256,0.000004933907,0.2595804,0.0000027737942,0.00014108706,0.014021788,0.0006963415,0.012545056],"study_design_scores_gemma":[0.00039914768,0.000068287416,0.5933298,0.000014563436,0.0000098214305,1.6701023e-7,0.4025597,0.00002176973,7.28136e-7,0.0009873686,0.0024923708,0.00011628899],"about_ca_topic_score_codex":0.0008174471,"about_ca_topic_score_gemma":0.0015133319,"teacher_disagreement_score":0.33418882,"about_ca_system_score_codex":0.00016423114,"about_ca_system_score_gemma":0.00011902966,"threshold_uncertainty_score":0.9997362},"labels":[],"label_agreement":null},{"id":"W2777401606","doi":"10.5430/wje.v7n6p63","title":"Formative Value of an Active Learning Strategy: Technology Based Think-Pair-Share in an EFL Writing Classroom","year":2017,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Anadolu Üniversitesi","keywords":"Formative assessment; Rubric; Psychology; Mathematics education; Coding (social sciences); Grading (engineering); Qualitative research; Pedagogy; Medical education","score_opus":0.034334295241587674,"score_gpt":0.4022492978968033,"score_spread":0.36791500265521565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777401606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98387533,0.00006293947,0.000035468624,0.002189873,0.00033181437,0.00012302025,0.0000011815446,0.000010072034,0.013370322],"genre_scores_gemma":[0.99737656,0.0000140643015,0.002087323,0.000028142527,0.0002724876,0.0000031309512,0.0000049031723,0.000006250785,0.00020711325],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988925,0.00021530206,0.00033185232,0.00009350679,0.00029739793,0.00016946362],"domain_scores_gemma":[0.9982528,0.00008787208,0.0010506404,0.00016256476,0.00037737197,0.00006873677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010437012,0.00007529907,0.00017512268,0.00043411535,0.00051681226,0.00014826903,0.0005564786,0.000071116534,0.00008579737],"category_scores_gemma":[0.00029053987,0.000073163006,0.00004701859,0.00025096425,0.00015527123,0.0016752577,0.000029026773,0.00039808592,0.0000018197085],"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":[0.000107258704,0.0007678037,0.6847772,0.000022137783,0.000032747346,0.000003613038,0.058696717,0.00017515835,0.0013330507,0.014128986,0.00014662064,0.2398087],"study_design_scores_gemma":[0.0007608644,0.00043387403,0.63746715,0.00041446608,0.000033115062,0.0000015804033,0.3504334,0.00095510547,0.0010819146,0.0072766445,0.0009789245,0.00016296213],"about_ca_topic_score_codex":0.00017431968,"about_ca_topic_score_gemma":0.0021184895,"teacher_disagreement_score":0.2917367,"about_ca_system_score_codex":0.00019338522,"about_ca_system_score_gemma":0.00079144654,"threshold_uncertainty_score":0.39749545},"labels":[],"label_agreement":null},{"id":"W2777582008","doi":"10.1166/asl.2017.9796","title":"Competency Frameworks and Implications for Teacher Assessment","year":2017,"lang":"en","type":"article","venue":"Advanced Science Letters","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Psychology; Mathematics education; Medical education; Engineering ethics; Engineering; Medicine","score_opus":0.028069535469416044,"score_gpt":0.41606664144381283,"score_spread":0.3879971059743968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777582008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72527456,0.000064262225,0.037018284,0.18955003,0.0009678395,0.00095467694,0.000006695658,0.000100207595,0.04606342],"genre_scores_gemma":[0.9573131,0.000037690952,0.04009133,0.0019904133,0.00015702091,0.000087927336,0.0000011020628,0.0000060497355,0.00031534338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988054,0.000019384566,0.000113605485,0.00034909532,0.0002918813,0.00042064293],"domain_scores_gemma":[0.9991345,0.00011559896,0.00013825047,0.00040527456,0.000077372635,0.00012904528],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00075272855,0.00008582194,0.00010541396,0.00005727408,0.0048356215,0.00060967513,0.0008810405,0.00005399346,0.000017529183],"category_scores_gemma":[0.0002813972,0.0000820497,0.000036028494,0.00012623915,0.0019146696,0.0011295314,0.000112814465,0.00016845937,0.000003370663],"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":[0.0000068364266,0.000064669715,0.5796032,0.000005914933,0.000011751051,6.291526e-7,0.0037933846,0.000023494467,0.055135317,0.29298422,0.0017642266,0.066606365],"study_design_scores_gemma":[0.0003160419,0.000022630456,0.9727356,0.000014081558,0.000009783766,2.4399694e-7,0.0013238768,0.00008669587,0.00004189907,0.009457336,0.015819313,0.00017253986],"about_ca_topic_score_codex":0.000079331,"about_ca_topic_score_gemma":0.000095279356,"teacher_disagreement_score":0.3931324,"about_ca_system_score_codex":0.0001100285,"about_ca_system_score_gemma":0.00012722336,"threshold_uncertainty_score":0.99645996},"labels":[],"label_agreement":null},{"id":"W2781785512","doi":"10.26522/brocked.v26i2.610","title":"Book Review: Ipsative Assessment: Motivation Through Marking Progress","year":2017,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Psychology","score_opus":0.044413621072548565,"score_gpt":0.43272294765231784,"score_spread":0.38830932657976924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781785512","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0132890325,0.2198627,0.0019579553,0.16904847,0.012600831,0.0022974503,0.0000041034596,0.00014802079,0.5807914],"genre_scores_gemma":[0.45289972,0.2621254,0.013232997,0.043344654,0.015512056,0.0003250865,0.000047813544,0.00008823177,0.21242401],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984221,0.00022360569,0.00029504957,0.00016526233,0.0006350177,0.00025898044],"domain_scores_gemma":[0.998303,0.00006420259,0.00079038134,0.00022807572,0.00046445034,0.00014989756],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005098014,0.000111251466,0.00015545158,0.000048501173,0.003571518,0.00085700996,0.0005510853,0.000056560188,0.002458546],"category_scores_gemma":[0.00062812475,0.00010323004,0.00008790178,0.00009266584,0.00015382531,0.001962527,0.00005456408,0.00026488557,0.00004069021],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003582633,0.00013875148,0.102430195,0.0000334266,0.000029940402,7.2485653e-7,0.0035929182,1.5665275e-7,0.000007701462,0.0019945183,0.8736003,0.018167792],"study_design_scores_gemma":[0.0001558832,0.000017276758,0.24939841,0.00062780705,0.000031834006,0.0000049987525,0.003606575,0.0000011879563,0.000005182859,0.0011273884,0.7449115,0.00011198836],"about_ca_topic_score_codex":0.000042642485,"about_ca_topic_score_gemma":0.000010281987,"teacher_disagreement_score":0.43961072,"about_ca_system_score_codex":0.00027144948,"about_ca_system_score_gemma":0.0014415875,"threshold_uncertainty_score":0.9984533},"labels":[],"label_agreement":null},{"id":"W2781803835","doi":"10.5539/elt.v11n2p15","title":"The Impact of Assessment for Learning on Students’ Achievement in English for Specific Purposes A Case Study of Pre-Medical Students at Khartoum University: Sudan","year":2018,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Psychology; Medical education; Mathematics education; Perception; Formative assessment; Medicine","score_opus":0.020853037814295875,"score_gpt":0.39673396274399214,"score_spread":0.37588092492969627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781803835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99465734,0.000042088097,0.00010110152,0.000024604897,0.00051032146,0.002434803,0.00001635471,0.0000641756,0.0021492243],"genre_scores_gemma":[0.9976961,0.000022211561,0.00018322926,0.000008078048,0.0007500595,0.00004731277,0.00001177997,0.000024281031,0.0012569549],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99621326,0.0008836245,0.00044315177,0.00037802206,0.001583516,0.0004984045],"domain_scores_gemma":[0.99746835,0.0015826821,0.00032179395,0.00028884283,0.00020378338,0.00013453959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006238211,0.00020727923,0.00037038783,0.00017675631,0.001168812,0.00016886674,0.0011245003,0.00010197276,0.000061838655],"category_scores_gemma":[0.0012634258,0.00016514567,0.00019270378,0.0002303294,0.00019067492,0.00020111476,0.00043668505,0.00041478322,6.180847e-7],"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":[0.00030348529,0.0019315376,0.48391426,0.000011549682,0.00018516647,0.000062838364,0.510407,0.000026782212,0.000038782007,0.0003177737,0.00026695683,0.0025339175],"study_design_scores_gemma":[0.0045709624,0.0029163987,0.07030262,0.00008617463,0.000054969376,8.2560695e-7,0.91849345,0.000078463614,0.000024567737,0.0000067721085,0.0032697383,0.00019507075],"about_ca_topic_score_codex":0.0042418684,"about_ca_topic_score_gemma":0.010309981,"teacher_disagreement_score":0.41361162,"about_ca_system_score_codex":0.0006722762,"about_ca_system_score_gemma":0.00013460258,"threshold_uncertainty_score":0.8989675},"labels":[],"label_agreement":null},{"id":"W2781958120","doi":"10.1016/j.tate.2017.12.010","title":"Changing approaches to classroom assessment: An empirical study across teacher career stages","year":2018,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":87,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Set (abstract data type); Psychology; Mathematics education; Empirical research; Pedagogy; Computer science","score_opus":0.15926321810963798,"score_gpt":0.45656737289959937,"score_spread":0.2973041547899614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781958120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96887755,0.000046320984,0.0005988568,0.0033001415,0.0006548404,0.00068279676,0.000002266191,0.00020599857,0.025631227],"genre_scores_gemma":[0.97734374,0.0000016318885,0.0022360429,0.0003491013,0.0025668312,0.000117585776,0.000022323473,0.000031848438,0.017330918],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99688745,0.0011631366,0.00023844077,0.0005680025,0.0005395712,0.000603416],"domain_scores_gemma":[0.9991355,0.000081144535,0.000094932715,0.00032387354,0.00006987972,0.000294665],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004514802,0.00021839792,0.00021761323,0.00017235307,0.0023461243,0.0005697726,0.00034038824,0.00012760538,0.0001248514],"category_scores_gemma":[0.00016022177,0.0002065777,0.00004335192,0.00031300535,0.00016707189,0.0005481593,0.0001442375,0.0005521157,0.000038285965],"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":[0.0000065705385,0.0011139038,0.5245724,0.0000029785979,0.000020422623,2.1234705e-7,0.4029814,2.9458099e-7,0.000023265005,0.00040857162,0.0011917636,0.06967823],"study_design_scores_gemma":[0.00021383287,0.00024238124,0.50883776,0.000014270472,0.000035073605,4.5348224e-7,0.46823597,0.0000576681,0.0000027502042,0.00015231328,0.021972125,0.00023538877],"about_ca_topic_score_codex":0.0026818456,"about_ca_topic_score_gemma":0.0017971841,"teacher_disagreement_score":0.06944284,"about_ca_system_score_codex":0.00026027643,"about_ca_system_score_gemma":0.00025605827,"threshold_uncertainty_score":0.9989527},"labels":[],"label_agreement":null},{"id":"W2782375796","doi":"10.1016/j.stueduc.2017.12.008","title":"Re-conceptualizing classroom assessment fairness: A systematic meta-ethnography of assessment literature and beyond","year":2018,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":82,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Conceptualization; Accountability; Construct (python library); Educational assessment; Psychology; Ethnography; Standards-based assessment; Process (computing); Pedagogy; Alternative assessment; Mathematics education; Sociology; Computer science; Political science","score_opus":0.18245862922193032,"score_gpt":0.5132713437504184,"score_spread":0.33081271452848804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782375796","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6998417,0.053101085,0.00048979284,0.01513653,0.0064442647,0.0071364674,0.000037096095,0.00008246341,0.21773066],"genre_scores_gemma":[0.9896287,0.0008079219,0.00789719,0.00013721397,0.00041338633,0.00081937294,0.00002981615,0.000009182502,0.0002572415],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9961613,0.0011573137,0.0006193485,0.00034651207,0.0014766084,0.00023893137],"domain_scores_gemma":[0.9966658,0.0011431158,0.00041743528,0.00020199716,0.001520175,0.00005148473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060895164,0.00018118176,0.00052548986,0.00031394674,0.00047473962,0.00009028619,0.00019762611,0.000087457054,0.00026591762],"category_scores_gemma":[0.0008890752,0.00015140354,0.00011833532,0.00095576805,0.0008144926,0.00041693737,0.00008448522,0.00013966487,0.000003137873],"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":[0.000019786823,0.00063338166,0.13409217,0.003170358,0.003342903,5.6969833e-7,0.58134323,0.000024242034,0.000111972426,0.26980236,0.0062909364,0.001168078],"study_design_scores_gemma":[0.001213354,0.0003106268,0.18881425,0.0024664905,0.0028231142,7.7784125e-7,0.6834535,0.0007619327,0.000014968027,0.119139664,0.0005362915,0.00046503393],"about_ca_topic_score_codex":0.000080268655,"about_ca_topic_score_gemma":0.0010540592,"teacher_disagreement_score":0.28978702,"about_ca_system_score_codex":0.00042473103,"about_ca_system_score_gemma":0.00063644524,"threshold_uncertainty_score":0.6174057},"labels":[],"label_agreement":null},{"id":"W2782628217","doi":"","title":"The Check Engine Light is on. Diagnosing and Repairing Mathematics Education in Ontario: Portfolio of Learning","year":2018,"lang":"en","type":"article","venue":"Brock University Digital Repository (Brock University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Portfolio; Mathematics education; Computer science; Mathematics; Business; Finance","score_opus":0.010893129204634578,"score_gpt":0.22944287215297024,"score_spread":0.21854974294833565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782628217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.780474,0.000020264708,0.000031748365,0.000015722599,0.00016674754,0.00014337906,7.474606e-7,0.000044970908,0.21910243],"genre_scores_gemma":[0.5975945,0.000053612875,0.000076713644,0.0000076078063,0.00005057959,6.394179e-8,0.000001157601,0.000006019687,0.40220976],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901927,0.000056451667,0.00014425178,0.0002454389,0.00029577105,0.00023879917],"domain_scores_gemma":[0.9992051,0.000185464,0.00018184322,0.00015559609,0.00016522255,0.00010675661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000011992798,0.00012689532,0.00014994603,0.00025254991,0.0008989982,0.00012462701,0.00031850333,0.00009590875,0.000007561846],"category_scores_gemma":[0.00006388729,0.00013691586,0.00007824133,0.00040400567,0.0002173655,0.00074066984,0.00018732237,0.00019353905,0.0000067685373],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000873826,0.00026288765,0.9801882,0.000017217217,0.0000602677,0.000019403817,0.003948532,0.00000981725,0.00082967005,0.0016455565,0.011674825,0.0012562744],"study_design_scores_gemma":[0.000658437,0.00023028298,0.18549898,0.00026754497,0.0000745101,0.000005945863,0.2584866,0.000007975232,0.000540358,0.00013882564,0.5537278,0.0003627384],"about_ca_topic_score_codex":0.004307556,"about_ca_topic_score_gemma":0.038989894,"teacher_disagreement_score":0.7946892,"about_ca_system_score_codex":0.0005664898,"about_ca_system_score_gemma":0.0004612431,"threshold_uncertainty_score":0.978546},"labels":[],"label_agreement":null},{"id":"W2788510848","doi":"10.7202/1043983ar","title":"Logique du stagiaire dans son rapport à l’évaluation","year":2018,"lang":"fr","type":"article","venue":"Phronesis","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Philosophy; Political science; Valuation (finance); Business","score_opus":0.05840836912101833,"score_gpt":0.33848228309543765,"score_spread":0.28007391397441933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788510848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7444422,0.0010642142,0.0045388336,0.01735275,0.0053473213,0.0004984562,0.000012817427,0.0001529815,0.2265904],"genre_scores_gemma":[0.94390315,0.00095448946,0.0009512489,0.0003464787,0.004192641,0.000030424515,0.000012738199,0.000025829113,0.049583014],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976315,0.00046388674,0.00030259448,0.00039009968,0.00067641353,0.0005355137],"domain_scores_gemma":[0.99906886,0.00013289398,0.00017585015,0.00024047293,0.00023451525,0.00014740058],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016351248,0.00021148653,0.00023616213,0.00006379293,0.0007652579,0.00011119444,0.00035225833,0.00023877228,0.0054010865],"category_scores_gemma":[0.000099769924,0.00022378762,0.00013301353,0.0005730316,0.0010083053,0.00047074695,0.000089809204,0.00012650376,0.002079431],"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":[0.000065068765,0.0007560985,0.5152911,0.00006590362,0.00024157713,0.00002098649,0.13516334,0.0000066134853,0.0012147013,0.06640564,0.11985675,0.16091226],"study_design_scores_gemma":[0.00081116497,0.00044635189,0.6657177,0.000082289866,0.00034326408,0.0000031999245,0.03444695,0.0012739365,0.0011847101,0.0042571095,0.29075167,0.0006816474],"about_ca_topic_score_codex":0.002788639,"about_ca_topic_score_gemma":0.0021823654,"teacher_disagreement_score":0.19946091,"about_ca_system_score_codex":0.0002850568,"about_ca_system_score_gemma":0.00043417222,"threshold_uncertainty_score":0.9986976},"labels":[],"label_agreement":null},{"id":"W2792027373","doi":"10.5539/ijel.v8n3p345","title":"Investigating Saudi University EFL Teachers’ Assessment Literacy: Theory and Practice","year":2018,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Taif University","keywords":"Summative assessment; Memorization; Psychology; Context (archaeology); Mathematics education; Literacy; Formative assessment; Pedagogy; Medical education; Medicine","score_opus":0.025659876284601656,"score_gpt":0.3860961951589349,"score_spread":0.36043631887433325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792027373","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11609505,0.0001618367,0.0021677886,0.00074928673,0.022014443,0.00010986193,0.000010916518,0.00004315371,0.85864764],"genre_scores_gemma":[0.9568859,0.00019553759,0.021872863,0.00037116374,0.019899173,1.17399956e-7,0.0000019337913,0.000007642135,0.00076568016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834365,0.00047843767,0.00024831502,0.00010110084,0.00069458823,0.0001339134],"domain_scores_gemma":[0.9793854,0.0018781906,0.00047505743,0.00005901253,0.018072268,0.00013011812],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031188265,0.00007754029,0.00011324559,0.00011917908,0.00023611414,0.00023015072,0.00039747634,0.000060075738,0.00009273467],"category_scores_gemma":[0.14369425,0.0000786622,0.00004864147,0.000109538116,0.0003800023,0.00029438917,0.00010211153,0.00026427917,0.000002851155],"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":[0.00017572752,0.0002295188,0.089285746,0.000005587639,0.00053428445,0.00009583829,0.15347032,0.0000070063493,0.00004489962,0.73416847,0.013581903,0.008400691],"study_design_scores_gemma":[0.0005394893,0.0000981224,0.012200661,0.0000684282,0.000082090126,0.0000017259462,0.03536919,0.000016619902,0.000010767799,0.0052130283,0.9462954,0.0001044905],"about_ca_topic_score_codex":0.000056412176,"about_ca_topic_score_gemma":0.000024567484,"teacher_disagreement_score":0.9327135,"about_ca_system_score_codex":0.00021837639,"about_ca_system_score_gemma":0.0003217784,"threshold_uncertainty_score":0.8635188},"labels":[],"label_agreement":null},{"id":"W2796537024","doi":"10.2307/4126487","title":"Towards Coherence between Classroom Assessment and Accountability: 103rd Yearbook of the National Society for the Study of Education, Part II","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Yearbook; Accountability; Coherence (philosophical gambling strategy); Political science; Pedagogy; Mathematics education; Psychology; Sociology; Library science; Computer science; Law","score_opus":0.08536018163195189,"score_gpt":0.38251947441171646,"score_spread":0.2971592927797646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796537024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.980301,0.00023304058,0.000029221224,0.014957776,0.0017777621,0.0007559461,0.000024956405,0.0000018296632,0.001918435],"genre_scores_gemma":[0.99616396,0.000027540918,0.00057818484,0.0003280423,0.0014316565,0.000069857015,0.0000071816253,0.000008665353,0.0013848979],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987339,0.00014183258,0.0004928754,0.000138615,0.00023862609,0.0002541608],"domain_scores_gemma":[0.9968798,0.00028269057,0.0006421529,0.00017276718,0.0017217216,0.00030086905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023039149,0.00009501651,0.0001774849,0.00012266394,0.0006598845,0.00006447304,0.00046006398,0.00007152593,0.000104371386],"category_scores_gemma":[0.00055583136,0.00007798476,0.000113364535,0.00037333326,0.00021767865,0.00025581857,0.000014946842,0.00016305613,2.996661e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000620055,0.00045458673,0.5644143,0.00005601901,0.00020016111,2.564941e-8,0.3381,0.00005112753,0.000043354896,0.012091084,0.05140442,0.033178717],"study_design_scores_gemma":[0.00021426294,0.00009881286,0.6605611,0.00007257628,0.00015196536,0.0000023112286,0.2115887,0.000016729704,0.000012457278,0.0018819249,0.12530918,0.000090009475],"about_ca_topic_score_codex":0.036944963,"about_ca_topic_score_gemma":0.5307432,"teacher_disagreement_score":0.49379823,"about_ca_system_score_codex":0.0028154852,"about_ca_system_score_gemma":0.03048334,"threshold_uncertainty_score":0.9750129},"labels":[],"label_agreement":null},{"id":"W2797014392","doi":"10.1177/0829573518765010","title":"Developing Proficiency in Standardized Cognitive Assessment Scoring: How Much Is Enough?","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Standardized test; Wechsler Intelligence Scale for Children; Wechsler Adult Intelligence Scale; Clinical psychology; Cognition; Wechsler Preschool and Primary Scale of Intelligence; Intelligence quotient; Medical education; Applied psychology; Mathematics education; Psychiatry; Medicine","score_opus":0.10395269919433764,"score_gpt":0.4554083521238081,"score_spread":0.35145565292947045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797014392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8712488,0.00030272617,0.002323115,0.04876441,0.0026949379,0.00036317066,0.000010395866,0.000010078946,0.07428236],"genre_scores_gemma":[0.9935599,0.00010651317,0.0024928618,0.0024671436,0.00086874136,0.0000060031794,9.2747683e-7,0.0000126420855,0.00048524115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979848,0.00028437917,0.00039680075,0.0002411855,0.0004174306,0.00067538326],"domain_scores_gemma":[0.9981021,0.00010523251,0.00029116072,0.000115105875,0.0007422212,0.0006441532],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018640785,0.00013888853,0.00030474344,0.0006043536,0.00048398657,0.0001972229,0.00050018524,0.00015508659,0.0012820741],"category_scores_gemma":[0.00060144527,0.0001372798,0.000079127094,0.00072174997,0.0005704838,0.0003962816,0.00001631583,0.00045209125,0.00004860055],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006624753,0.000040757837,0.9458689,0.000005733625,0.00008109767,0.00021266907,0.015140742,8.400416e-8,0.00012305565,0.009976985,0.022484832,0.005998885],"study_design_scores_gemma":[0.0027568233,0.00051589106,0.8538849,0.00024309382,0.00003377582,0.000024622424,0.04668323,0.0000018050441,0.00010150815,0.0043477127,0.09106576,0.0003409179],"about_ca_topic_score_codex":0.002296444,"about_ca_topic_score_gemma":0.060946442,"teacher_disagreement_score":0.12231112,"about_ca_system_score_codex":0.0007896223,"about_ca_system_score_gemma":0.006400033,"threshold_uncertainty_score":0.99963087},"labels":[],"label_agreement":null},{"id":"W2801829489","doi":"10.1007/s10758-018-9363-2","title":"Online Project-Based Learning and Formative Assessment","year":2018,"lang":"en","type":"article","venue":"Technology Knowledge and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Formative assessment; Context (archaeology); Psychology; Mathematics education; Computer science; Knowledge management; Medical education; Pedagogy; Medicine","score_opus":0.02415889938500342,"score_gpt":0.3958033213554171,"score_spread":0.3716444219704137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801829489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9164154,0.00080567895,0.00074625644,0.0012521662,0.00013287691,0.0002720148,5.9598796e-7,0.00055601285,0.07981903],"genre_scores_gemma":[0.99231523,0.00020355667,0.0030875502,0.000032898362,0.00019336976,0.000020041804,0.0000059981667,0.000011753875,0.004129621],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989347,0.0002055754,0.00014911513,0.00024522698,0.00012738156,0.00033800077],"domain_scores_gemma":[0.99949306,0.00015150703,0.00009811699,0.00006371843,0.00014528475,0.00004832013],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00068729086,0.00012701457,0.00018361921,0.0003093557,0.0015527091,0.00006528137,0.00012774704,0.00020338428,0.000080145575],"category_scores_gemma":[0.00023595999,0.00011943836,0.000022295011,0.00052143633,0.00087760465,0.00014041115,0.00013864427,0.0006810721,0.000028645376],"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":[0.000023574454,0.00024771437,0.67488915,0.00003951474,0.00006946654,0.0000055446985,0.0551163,8.225063e-7,0.00069053966,0.021310164,0.0011844562,0.24642274],"study_design_scores_gemma":[0.001096663,0.0008896855,0.03006244,0.00009614034,0.000047054782,0.0000028115442,0.09616062,0.0027060024,0.00014044943,0.00045560597,0.8679905,0.0003520221],"about_ca_topic_score_codex":0.000066189474,"about_ca_topic_score_gemma":0.00043040697,"teacher_disagreement_score":0.86680603,"about_ca_system_score_codex":0.00005181524,"about_ca_system_score_gemma":0.00015230171,"threshold_uncertainty_score":0.99974716},"labels":[],"label_agreement":null},{"id":"W2802895273","doi":"10.3968/10161","title":"Alternative Assessment in the Moroccan EFL Classrooms Teachers’ Conceptions and Practices","year":2018,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Class (philosophy); Curriculum; Face (sociological concept); Alternative assessment; Mathematics education; Psychology; Focus group; Pedagogy; Medical education; Sociology; Computer science; Medicine; Social science","score_opus":0.0664318506703283,"score_gpt":0.4809214078683849,"score_spread":0.4144895571980566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802895273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5609201,0.000028041683,0.000010742358,0.0071080937,0.00070010294,0.00021123256,9.782731e-7,0.000009670502,0.43101102],"genre_scores_gemma":[0.99431217,0.000027000204,0.00036951067,0.00036401025,0.0008259715,0.000032788415,9.58493e-7,0.0000024941583,0.004065095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99856716,0.00020814827,0.00014496474,0.00019943553,0.00067346205,0.00020680932],"domain_scores_gemma":[0.99918455,0.00014627665,0.00031076843,0.0000841466,0.00022538583,0.0000488758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016303501,0.00006157402,0.00008076659,0.00008264319,0.00094438216,0.00017236827,0.00047486558,0.00003800028,0.0004654134],"category_scores_gemma":[0.000096871336,0.000049236856,0.000019254841,0.0008388708,0.002342306,0.0006191147,0.000046018497,0.00011878434,0.0000086791915],"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":[0.0000020722553,0.00018587011,0.10108657,0.0000015104272,0.000003830995,7.0932025e-8,0.20222369,8.15589e-8,0.0005542353,0.6923004,0.0012738239,0.0023678353],"study_design_scores_gemma":[0.00009870418,0.000035795176,0.8252603,0.0000068227755,0.000008131837,9.5539e-8,0.103687584,0.0000038053176,0.000013327624,0.0028868977,0.067936175,0.000062408464],"about_ca_topic_score_codex":0.0032934486,"about_ca_topic_score_gemma":0.00032256776,"teacher_disagreement_score":0.72417367,"about_ca_system_score_codex":0.00023477529,"about_ca_system_score_gemma":0.0009227616,"threshold_uncertainty_score":0.8630324},"labels":[],"label_agreement":null},{"id":"W2804173549","doi":"10.3138/jvme.0117-015r","title":"Teaching Tip: A Method for Evaluating Learning Evidence when Using Cumulative Final Examinations","year":2018,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Microsoft excel; Computer science; Medical education; Psychology; Mathematics education; Medicine","score_opus":0.4702388782930537,"score_gpt":0.6169445040889544,"score_spread":0.14670562579590068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804173549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85998017,0.0002114317,0.13153343,0.004832127,0.0016605966,0.00023109911,2.4902778e-7,0.000013811304,0.0015370868],"genre_scores_gemma":[0.792205,0.000027763777,0.20358992,0.00023034641,0.0030314822,0.000009271907,0.0000010859003,0.000009247093,0.0008958985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99716675,0.0010731848,0.00042244763,0.0001299618,0.0010096731,0.0001980063],"domain_scores_gemma":[0.9970118,0.0015038066,0.00052747864,0.000060487997,0.0007177674,0.00017865264],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009222986,0.00008101979,0.00016498806,0.00015220855,0.0008621474,0.000079325924,0.00027828378,0.00008749025,0.0004903349],"category_scores_gemma":[0.016053597,0.00007413837,0.0000870588,0.00013906026,0.00014122261,0.0006909993,0.0000453796,0.00034948543,0.0000033738459],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029019066,0.00048726294,0.0062224595,0.00006435514,0.00009146432,0.0000058319565,0.18001147,0.000038981532,0.005989363,0.003117243,0.00217229,0.8015091],"study_design_scores_gemma":[0.004573631,0.020125773,0.05912802,0.00980132,0.0010372098,0.00068622676,0.24709198,0.31041062,0.00017612817,0.023574999,0.32206225,0.0013318369],"about_ca_topic_score_codex":0.00037533068,"about_ca_topic_score_gemma":0.00002583527,"teacher_disagreement_score":0.8001773,"about_ca_system_score_codex":0.0002864305,"about_ca_system_score_gemma":0.002274144,"threshold_uncertainty_score":0.9922346},"labels":[],"label_agreement":null},{"id":"W2807722510","doi":"10.3138/jvme.0117-014r1","title":"Think Subscores Are a Helpful Form of Feedback? Think Again","year":2018,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Medical education; Engineering ethics; Medicine; Engineering","score_opus":0.06954159974503704,"score_gpt":0.41994441087406226,"score_spread":0.3504028111290252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807722510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805612,0.0003661608,0.00009082016,0.008223877,0.003055521,0.000116377494,8.5261337e-7,0.000012308683,0.007572914],"genre_scores_gemma":[0.9943715,0.00043207261,0.000982962,0.00057991425,0.003004918,0.000001653426,0.0000016022964,0.000008528837,0.00061685184],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.997668,0.00020190362,0.00051804713,0.000106729574,0.0012895383,0.00021577213],"domain_scores_gemma":[0.9981684,0.00015929868,0.0006692724,0.00012800844,0.00058378046,0.00029120274],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018628498,0.00009763989,0.00024850338,0.00014933797,0.0002062038,0.000042436277,0.00051277573,0.00014673261,0.0015692004],"category_scores_gemma":[0.0014993125,0.000078276775,0.0001283277,0.0002783591,0.00044621213,0.00042292484,0.000056483637,0.00024305732,0.000024052259],"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":[0.001407454,0.0046477113,0.09121595,0.0002586935,0.00037750785,0.00012682432,0.50882363,4.4964418e-7,0.0034097147,0.010989265,0.17266044,0.20608234],"study_design_scores_gemma":[0.0023269542,0.005595979,0.5988251,0.0020406547,0.000166892,0.0002771754,0.22538048,0.00007379297,0.00032552588,0.01524735,0.1492141,0.00052598113],"about_ca_topic_score_codex":0.00014204517,"about_ca_topic_score_gemma":0.00011925723,"teacher_disagreement_score":0.5076091,"about_ca_system_score_codex":0.00013076841,"about_ca_system_score_gemma":0.0017114038,"threshold_uncertainty_score":0.9993435},"labels":[],"label_agreement":null},{"id":"W2808382347","doi":"10.18162/fp.2018.458","title":"L’autoévaluation et l’évaluationpar les pairs en enseignementsupérieur : promesses et défis","year":2018,"lang":"fr","type":"article","venue":"Formation et profession","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Political science","score_opus":0.07013561867856578,"score_gpt":0.4178736721217637,"score_spread":0.3477380534431979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808382347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71832037,0.0007364138,0.022345174,0.12658939,0.00673355,0.0029539138,0.000049322316,0.00037790145,0.12189397],"genre_scores_gemma":[0.9713214,0.0012686265,0.0026112392,0.001831043,0.00063920434,0.00019871256,0.00043963722,0.00003484867,0.021655306],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907002,0.0060783005,0.0007686509,0.00037805457,0.0015567262,0.0005180686],"domain_scores_gemma":[0.9977892,0.0005477555,0.0006719441,0.0002776793,0.0005869256,0.0001265053],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010554352,0.00031793842,0.00028267544,0.00021147473,0.0015709935,0.0002731248,0.0003443702,0.00038616123,0.004259525],"category_scores_gemma":[0.000620799,0.0002971467,0.00012229958,0.00075731665,0.00030045427,0.004469373,0.00020586161,0.00047074215,0.0012781139],"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":[0.000087090666,0.0006140022,0.0067024613,0.00025688484,0.00007821726,0.0000010186867,0.712264,0.000050902323,0.0009561406,0.16394885,0.071162805,0.043877617],"study_design_scores_gemma":[0.0032426636,0.0011040897,0.16444881,0.0019741287,0.000304559,0.000004973195,0.27978104,0.015449385,0.0022436322,0.026883196,0.50333893,0.0012245927],"about_ca_topic_score_codex":0.00033068706,"about_ca_topic_score_gemma":0.0007980966,"teacher_disagreement_score":0.43248296,"about_ca_system_score_codex":0.00039647092,"about_ca_system_score_gemma":0.00059773587,"threshold_uncertainty_score":0.9999481},"labels":[],"label_agreement":null},{"id":"W2809613764","doi":"10.15760/nwjte.2011.9.1.1","title":"Using Exploratory Interviews to Re-frame Planned Research on Classroom Issues","year":2011,"lang":"en","type":"article","venue":"Northwest Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Interview; Exploratory research; Framing (construction); Grading (engineering); Psychology; Pedagogy; Medical education; Mathematics education; Sociology; Medicine; Social science","score_opus":0.38259458490481973,"score_gpt":0.5143041322206915,"score_spread":0.13170954731587176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809613764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9705613,0.00038775455,0.000049838964,0.0022184968,0.0016377465,0.00021640307,7.129443e-7,0.000013489993,0.024914213],"genre_scores_gemma":[0.9931676,0.00011699388,0.002861198,0.00021688017,0.0017387108,0.000009121758,0.000001844832,0.000015514795,0.0018721655],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99766606,0.0007094127,0.00038581822,0.0001529487,0.00079857686,0.00028717727],"domain_scores_gemma":[0.9986578,0.00007509041,0.00025329107,0.00018490908,0.00060295954,0.00022595254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033018827,0.00010185909,0.00017996936,0.00042813952,0.0003076159,0.00010678026,0.00048808777,0.00009557999,0.0006383798],"category_scores_gemma":[0.00024016252,0.00009002723,0.00008268396,0.00047302502,0.00009014017,0.0004621222,0.000043424145,0.00046036104,0.00012764387],"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":[0.00024333913,0.0019266,0.49778414,0.000013193315,0.000053459902,0.0000065151016,0.4357802,0.000005431517,0.00039696824,0.0027972185,0.04084196,0.020150986],"study_design_scores_gemma":[0.00033988873,0.0010239616,0.25688937,0.0004226771,0.00004730674,0.0000036054157,0.4732021,0.000003132408,0.0003356982,0.0022224505,0.2652237,0.0002860721],"about_ca_topic_score_codex":0.0023478556,"about_ca_topic_score_gemma":0.00438375,"teacher_disagreement_score":0.24089476,"about_ca_system_score_codex":0.0004119351,"about_ca_system_score_gemma":0.0007676275,"threshold_uncertainty_score":0.69898105},"labels":[],"label_agreement":null},{"id":"W2853632348","doi":"10.1007/s10459-018-9841-2","title":"Comparatively salient: examining the influence of preceding performances on assessors’ focus and interpretations in written assessment comments","year":2018,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"National Institute for Health and Care Research","keywords":"Optimal distinctiveness theory; Salience (neuroscience); Competence (human resources); Psychology; Cognitive psychology; Contrast (vision); Salient; Social psychology; Cognition; Benchmarking; Computer science; Artificial intelligence","score_opus":0.05070227454645189,"score_gpt":0.47750808015242924,"score_spread":0.42680580560597736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2853632348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97508526,0.0006935596,0.00008179336,0.0029378883,0.00052965735,0.00052309455,0.0000014007572,0.000010259004,0.0201371],"genre_scores_gemma":[0.99599826,0.0017103035,0.0016003402,0.00047919658,0.00008136612,0.000087095344,0.0000013895125,0.0000029470239,0.000039116007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980967,0.0003714285,0.000452229,0.0002745097,0.0004908688,0.00031426505],"domain_scores_gemma":[0.9986406,0.0007242861,0.00037056612,0.000101398975,0.000104619976,0.000058536225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029069905,0.000097059856,0.00017154198,0.00021763229,0.0012240859,0.00014507753,0.0003859343,0.000028029894,0.000012540983],"category_scores_gemma":[0.00017467135,0.00007547544,0.000011121648,0.0010262124,0.0011149185,0.0012559377,0.00005272424,0.00014588879,0.0000020060374],"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":[0.000008465502,0.00012393334,0.90083295,0.000026270705,0.0000016389664,2.8434583e-8,0.051313475,0.0005655983,0.000015011427,0.025545403,0.00003108674,0.021536116],"study_design_scores_gemma":[0.00017555969,0.000411396,0.92365503,0.0005305773,0.000001898408,1.6505601e-7,0.068840034,0.0011536442,0.000021359987,0.0032437986,0.0018694698,0.000097091535],"about_ca_topic_score_codex":0.002747576,"about_ca_topic_score_gemma":0.010185624,"teacher_disagreement_score":0.022822032,"about_ca_system_score_codex":0.0002313531,"about_ca_system_score_gemma":0.0006938441,"threshold_uncertainty_score":0.9414803},"labels":[],"label_agreement":null},{"id":"W2884360845","doi":"10.1002/tl.20302","title":"Creating a Culture of Continuous Assessment to Improve Student Learning Through Curriculum Review","year":2018,"lang":"en","type":"article","venue":"New Directions for Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Curriculum; Curriculum development; Mathematics education; Pedagogy; Active learning (machine learning); Action (physics); Psychology; Computer science; Artificial intelligence","score_opus":0.016468156458477337,"score_gpt":0.39776346616416125,"score_spread":0.3812953097056839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884360845","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43593886,0.0074166507,0.028445438,0.002642794,0.0018144959,0.0027818875,0.000004038791,0.00070841215,0.5202474],"genre_scores_gemma":[0.9112204,0.001803223,0.03440404,0.0002763399,0.0014404642,0.000103940656,0.000009390058,0.000030327708,0.050711896],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.998147,0.0005857623,0.00029482198,0.00032122948,0.00033267945,0.00031852032],"domain_scores_gemma":[0.99909246,0.00028668222,0.00022923463,0.00009413791,0.0001773366,0.00012016341],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021966423,0.00014756995,0.0003223335,0.000060740007,0.0033177105,0.00013624936,0.00014937918,0.00007081714,0.0000638385],"category_scores_gemma":[0.001658064,0.00013418336,0.000113247814,0.00025346447,0.00009698896,0.00021329682,0.000074470525,0.0006993917,0.000005514524],"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":[0.00001934793,0.00032577713,0.15573257,0.00031300032,0.00025842406,0.0000010240811,0.4929134,0.00006314493,0.0024053848,0.011458596,0.0129575655,0.32355174],"study_design_scores_gemma":[0.00045674783,0.0007444895,0.0048127924,0.00108744,0.00016043885,0.0000012167811,0.14223999,0.00011384414,0.000018624673,0.00006601874,0.85005414,0.00024427124],"about_ca_topic_score_codex":0.005802033,"about_ca_topic_score_gemma":0.00028911268,"teacher_disagreement_score":0.8370966,"about_ca_system_score_codex":0.00009525006,"about_ca_system_score_gemma":0.00008447906,"threshold_uncertainty_score":0.9979798},"labels":[],"label_agreement":null},{"id":"W2885480655","doi":"10.1111/medu.13645","title":"Assessment, feedback and the alchemy of learning","year":2018,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":416,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Western University","funders":"","keywords":"Formative assessment; Summative assessment; Competence (human resources); CLARITY; Assessment for learning; Judgement; Psychology; Peer feedback; Pedagogy; Medical education; Social psychology; Medicine; Political science","score_opus":0.014690897748753037,"score_gpt":0.39760354015591914,"score_spread":0.3829126424071661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885480655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5962722,0.00017329483,0.00032436542,0.02839682,0.00094431586,0.00021231564,1.16238134e-7,0.000026601401,0.37364998],"genre_scores_gemma":[0.9947814,0.00018342205,0.00026272773,0.0006316566,0.00070191233,0.000011756209,0.0000020167975,0.0000028553484,0.003422265],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990102,0.00019397582,0.00011643857,0.00008603642,0.00048689038,0.00010643957],"domain_scores_gemma":[0.99951255,0.00020085713,0.00007165873,0.000059627397,0.000097916454,0.000057369445],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014733566,0.000037493042,0.0000799803,0.000022397075,0.0002969926,0.000030429523,0.00014750603,0.000052875283,0.0013496301],"category_scores_gemma":[0.0010702332,0.000025222309,0.000020997333,0.00015748828,0.0010918486,0.000067625566,0.0000345936,0.00011236486,0.000016897466],"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":[0.000035467307,0.0003212567,0.38685486,0.000021102782,0.000045795205,1.5401996e-7,0.06734312,7.316738e-8,0.00008167806,0.35502237,0.03715706,0.15311706],"study_design_scores_gemma":[0.0016331138,0.00009435846,0.41288817,0.00009226897,0.000053823194,0.0000010007641,0.07357973,0.00035316567,0.000049684677,0.0052031903,0.5058989,0.00015259716],"about_ca_topic_score_codex":0.0006289145,"about_ca_topic_score_gemma":0.00016854281,"teacher_disagreement_score":0.46874183,"about_ca_system_score_codex":0.000023822533,"about_ca_system_score_gemma":0.0007435432,"threshold_uncertainty_score":0.9995633},"labels":[],"label_agreement":null},{"id":"W2885719062","doi":"","title":"Collaboration Between Content Experts and Assessment Specialists: Using a Validity Argument Framework to Develop a College Mathematics Assessment","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University; Institute for Christian Studies; University of Toronto","funders":"","keywords":"Argument (complex analysis); Content validity; Psychology; Educational assessment; Content (measure theory); Mathematics education; Psychometrics; Medicine; Mathematics","score_opus":0.1838400374076336,"score_gpt":0.41436563256571973,"score_spread":0.23052559515808613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885719062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97435206,0.000059048514,0.004402256,0.012060922,0.0048325476,0.0006588269,0.000036577036,0.000007778872,0.0035899903],"genre_scores_gemma":[0.92286813,0.000025903808,0.072218515,0.0005677348,0.003668413,0.00003353296,0.000017822007,0.000021171963,0.00057877006],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9979648,0.00029824756,0.00065857754,0.00024204521,0.0002575489,0.0005787774],"domain_scores_gemma":[0.99461305,0.0002124554,0.00057568046,0.00021383604,0.0027369338,0.0016480564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023320396,0.00017909336,0.00031406482,0.00055532623,0.00090801355,0.00039280043,0.00030909778,0.00014912676,0.00025334934],"category_scores_gemma":[0.001602298,0.0002053758,0.000044656823,0.0011917164,0.00016671546,0.000448239,0.000016800272,0.00019336124,0.00000395254],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000011494015,0.0002352699,0.2396412,0.00008076155,0.00015155197,0.000013592133,0.57774234,0.000010503262,0.00042238043,0.15045692,0.025185784,0.0060481997],"study_design_scores_gemma":[0.00032710997,0.00029661445,0.28841686,0.00063607143,0.0001818791,0.000038442977,0.52379185,0.00006898435,0.00006897067,0.008874141,0.1768268,0.0004722934],"about_ca_topic_score_codex":0.029509999,"about_ca_topic_score_gemma":0.5542275,"teacher_disagreement_score":0.5247175,"about_ca_system_score_codex":0.012165927,"about_ca_system_score_gemma":0.03200822,"threshold_uncertainty_score":0.9916262},"labels":[],"label_agreement":null},{"id":"W2889059640","doi":"10.5206/cie-eci.v47i1.9324","title":"Grading Policies in Canada and China: A Comparative Study","year":2018,"lang":"en","type":"article","venue":"Comparative and International Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); China; Internationalization; Christian ministry; Immigration; Political science; Globalization; Comparative education; Academic achievement; Promotion (chess); Mathematics education; Pedagogy; Higher education; Psychology; Business","score_opus":0.1087710950017053,"score_gpt":0.46185380432581685,"score_spread":0.35308270932411157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889059640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95893735,0.00013049797,0.000007919698,0.0008432623,0.0006665546,0.00021399767,0.0000017563174,0.000005083757,0.03919358],"genre_scores_gemma":[0.9976528,0.000029699127,0.000055639226,0.00010201583,0.00024119484,0.000023888997,0.000005024231,0.0000016012729,0.0018881285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993923,0.000083043735,0.00012133485,0.00013664205,0.00016918479,0.00009749786],"domain_scores_gemma":[0.9996587,0.000058509482,0.000056698012,0.00003493367,0.00014453182,0.0000466428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013267227,0.00006539487,0.00010743823,0.00008478065,0.00021314085,0.00008377191,0.000098177035,0.0000112279795,0.000085111984],"category_scores_gemma":[0.000022229526,0.000063118714,0.000006337329,0.00013657492,0.00013797107,0.00022991076,0.00003277242,0.000054711676,0.0000037995846],"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":[0.000012240111,0.00012398037,0.79417515,6.774151e-7,0.000020493877,1.2394325e-7,0.19173858,4.6698165e-7,0.00001613203,0.009292021,0.003998209,0.00062192825],"study_design_scores_gemma":[0.00016013684,0.000039989252,0.80818236,0.000009994046,0.0000033875497,2.6343403e-7,0.18579605,0.00011833596,0.000012761508,0.0006458804,0.0049702264,0.000060585076],"about_ca_topic_score_codex":0.8423057,"about_ca_topic_score_gemma":0.97014743,"teacher_disagreement_score":0.1278417,"about_ca_system_score_codex":0.00026755538,"about_ca_system_score_gemma":0.0006398189,"threshold_uncertainty_score":0.25739065},"labels":[],"label_agreement":null},{"id":"W2889522036","doi":"10.5539/ies.v11n9p12","title":"Interrater Scoring of Public Speaking Performances in English Language Teacher Education Program","year":2018,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; Inter-rater reliability; Mathematics education; Curriculum; Rating scale; Qualitative research; Qualitative property; Empowerment; Pedagogy; Teacher education; Computer science","score_opus":0.08813912167534482,"score_gpt":0.47629297147951877,"score_spread":0.38815384980417394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889522036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8529606,0.00060269196,0.0000074955487,0.0010416929,0.0070950435,0.00022965661,5.4284425e-7,0.000045713314,0.13801658],"genre_scores_gemma":[0.9906074,0.00019699566,0.00085531216,0.0000815655,0.002142695,0.00018864401,0.000008820151,0.0000061149044,0.005912444],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9990399,0.00006773672,0.0002509726,0.00015835513,0.00032812968,0.00015493222],"domain_scores_gemma":[0.9982087,0.000044646655,0.00015034118,0.000080238366,0.0014859634,0.000030105948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054984866,0.00007889622,0.00010928706,0.00027007738,0.00013045964,0.00009531466,0.00026319936,0.00003259757,0.00035152753],"category_scores_gemma":[0.0007476577,0.00007369325,0.00003387368,0.00028411194,0.00025929557,0.0006005514,0.00007195206,0.00007701695,0.000023223085],"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":[0.0000067659025,0.0007322814,0.5499142,0.000013190473,0.000056937817,7.729913e-8,0.25236726,1.9826359e-7,0.000046529512,0.004385395,0.0025137537,0.1899634],"study_design_scores_gemma":[0.00016608823,0.000048579353,0.17438994,0.00017573684,0.000010055159,2.686452e-7,0.6507661,0.000019457937,0.00018788908,0.00034696655,0.17375189,0.00013704134],"about_ca_topic_score_codex":0.0006688636,"about_ca_topic_score_gemma":0.0023996911,"teacher_disagreement_score":0.39839882,"about_ca_system_score_codex":0.0002404816,"about_ca_system_score_gemma":0.00042335494,"threshold_uncertainty_score":0.38489798},"labels":[],"label_agreement":null},{"id":"W2890137837","doi":"10.4018/978-1-5225-3940-7.ch005","title":"Using Computerized Formative Testing to Support Personalized Learning in Higher Education","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Test (biology); Computer science; Psychology; Mathematics education","score_opus":0.0862099370797399,"score_gpt":0.36275300424261275,"score_spread":0.27654306716287286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890137837","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01099934,0.013657976,0.0010192476,0.012053247,0.0067697316,0.0030000682,0.000039904302,0.0007815666,0.95167893],"genre_scores_gemma":[0.015672386,0.015561223,0.4144564,0.00058948866,0.0016654849,0.00042116543,0.0001321953,0.00009660008,0.5514051],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838513,0.00005246848,0.0004297238,0.00043091504,0.00040155172,0.00030018593],"domain_scores_gemma":[0.99898756,0.00029701306,0.00029304926,0.00010814295,0.00026528642,0.00004894374],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029990764,0.00028402894,0.0003395385,0.0005647011,0.0004714515,0.00010745862,0.00027755313,0.00028855886,0.0009815388],"category_scores_gemma":[0.00018910422,0.00030786893,0.000042035655,0.00025859807,0.0010080793,0.0017685593,0.00014043266,0.00036891596,0.000017137954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009959471,0.0000442654,0.0024104393,0.000044327586,0.000022690087,0.0000012995068,0.0026229403,0.00011482385,0.000044714427,0.9422034,0.0006464701,0.051745053],"study_design_scores_gemma":[0.0002472082,0.00018657817,0.0018470808,0.000411841,0.0000127092635,0.000014863142,0.0083898585,0.000019479556,0.000009504196,0.264131,0.72430664,0.00042323334],"about_ca_topic_score_codex":0.0000419608,"about_ca_topic_score_gemma":0.00008389217,"teacher_disagreement_score":0.7236602,"about_ca_system_score_codex":0.0005592748,"about_ca_system_score_gemma":0.0010783366,"threshold_uncertainty_score":0.99993736},"labels":[],"label_agreement":null},{"id":"W2893953242","doi":"10.1177/1541931218621082","title":"Usability Analysis of Freeform Marking on Engineering Problem Solving","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Usability; Formative assessment; Consistency (knowledge bases); Computer science; Test (biology); Perspective (graphical); Group (periodic table); Sample (material); Mathematics education; Human–computer interaction; Psychology; Artificial intelligence","score_opus":0.018590048526772915,"score_gpt":0.27364103322569827,"score_spread":0.25505098469892534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893953242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933854,0.000018056115,0.0000033897759,0.000055050543,0.00010018489,0.00015768217,0.000010055504,0.000027909304,0.0062423227],"genre_scores_gemma":[0.99878323,0.000028870663,0.00091572944,0.00001670824,0.00016810214,0.0000024539888,9.704839e-7,0.000010393482,0.00007353313],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99884605,0.000008077154,0.00035447598,0.00023643467,0.0002685649,0.00028637177],"domain_scores_gemma":[0.9991111,0.0001309939,0.00038622352,0.000073250216,0.00024106391,0.000057324683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012202184,0.00014431254,0.00031485845,0.00006669594,0.0007894969,0.00007870943,0.0003643167,0.0001001348,0.000015835387],"category_scores_gemma":[0.00014007685,0.00011183176,0.00032413474,0.00047586093,0.00040133792,0.00026179376,0.00022042413,0.00014665969,1.8201601e-7],"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":[0.000012774948,0.00004399237,0.87668896,0.00006767343,0.00041332725,4.6627373e-9,0.111205265,0.00003540207,0.0049204207,0.006330433,0.000154841,0.00012688342],"study_design_scores_gemma":[0.00024225729,0.00012105605,0.87742835,0.00021030282,0.0005060349,4.3080096e-8,0.1137529,0.0014182683,0.0048554875,0.00045154852,0.00068593887,0.0003278021],"about_ca_topic_score_codex":0.00071943516,"about_ca_topic_score_gemma":0.00014616377,"teacher_disagreement_score":0.0061687897,"about_ca_system_score_codex":0.00012594972,"about_ca_system_score_gemma":0.000022908316,"threshold_uncertainty_score":0.6072251},"labels":[],"label_agreement":null},{"id":"W2897106912","doi":"10.1111/medu.13746","title":"When I say … feedback","year":2018,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Constructive; Process (computing); Term (time); Space (punctuation); Series (stratigraphy); Psychology; Computer science; Social psychology; Sociology; Physics; Programming language","score_opus":0.019267145783885532,"score_gpt":0.3851389734389596,"score_spread":0.36587182765507403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897106912","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1541451,0.00010462311,0.00026501727,0.105422325,0.0049544238,0.00019571006,2.9274884e-7,0.00010174003,0.73481077],"genre_scores_gemma":[0.9394937,0.00006388929,0.0008579573,0.012501295,0.005763225,0.000022903347,0.0000092101545,0.000007366567,0.041280434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988129,0.000085769105,0.00010732123,0.0001263497,0.0006830176,0.00018460407],"domain_scores_gemma":[0.9995804,0.000050301245,0.000034196233,0.000097549324,0.00011633215,0.00012125433],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00064122677,0.000047033307,0.000060465965,0.00003524098,0.00028950712,0.000051058465,0.00024587303,0.00009071287,0.017976196],"category_scores_gemma":[0.00091635465,0.00004242638,0.000024622881,0.00015440435,0.0003491032,0.000115869414,0.000025896852,0.0000773038,0.0013533317],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000376658,0.00017607775,0.02589721,0.0000022827926,0.000005815975,2.0291527e-7,0.024025949,2.1033346e-9,0.00000773045,0.017288228,0.84062755,0.0919652],"study_design_scores_gemma":[0.00010289663,0.000022950313,0.02537014,0.000018989052,0.0000058973437,2.4412472e-7,0.0050345045,0.000006852243,0.000013899606,0.0030582899,0.9662996,0.00006575257],"about_ca_topic_score_codex":0.001040115,"about_ca_topic_score_gemma":0.0011231257,"teacher_disagreement_score":0.7853486,"about_ca_system_score_codex":0.00007561449,"about_ca_system_score_gemma":0.0014108376,"threshold_uncertainty_score":0.9994242},"labels":[],"label_agreement":null},{"id":"W2898183750","doi":"10.1007/978-3-319-92390-1_44","title":"Enhancing Mathematics Teaching and Learning Through Sound Assessment Practices","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in mathematics education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Variety (cybernetics); Mathematics education; Plan (archaeology); Process (computing); Assessment for learning; Computer science; Psychology; Formative assessment; Artificial intelligence","score_opus":0.04105032535141184,"score_gpt":0.4358463200985673,"score_spread":0.39479599474715543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898183750","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038794086,0.00232249,0.0043397523,0.00028373845,0.0009063339,0.0007059616,0.0000013346036,0.00008158666,0.9874794],"genre_scores_gemma":[0.011975974,0.009211741,0.45406738,0.000112918664,0.0016128396,0.000100010744,0.000036476897,0.00011143841,0.52277124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774104,0.0001539817,0.00064596196,0.00041605456,0.0007185626,0.0003244214],"domain_scores_gemma":[0.9959915,0.0016792543,0.0018329653,0.00027042493,0.00015668487,0.00006911347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027243833,0.0003279139,0.00044249007,0.00016238162,0.00089973985,0.00032804336,0.0003172544,0.00026077425,0.00049436913],"category_scores_gemma":[0.0013362046,0.00033642392,0.000066125955,0.00006105175,0.00029136418,0.0012726407,0.00011283825,0.0010320209,0.00007383642],"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":[0.0000015581226,0.00022020431,0.00044753862,0.00057623157,0.000036892936,9.765147e-7,0.16200675,0.0000030511212,0.000014900649,0.83167976,0.00021454059,0.0047976193],"study_design_scores_gemma":[0.00010597579,0.000044537534,0.00003336316,0.0012423355,0.000101426136,0.0000030376905,0.10812485,0.00006631547,0.0000026508112,0.70159334,0.18829395,0.00038819807],"about_ca_topic_score_codex":0.00009612922,"about_ca_topic_score_gemma":0.0011291584,"teacher_disagreement_score":0.46470818,"about_ca_system_score_codex":0.00038404978,"about_ca_system_score_gemma":0.00046939068,"threshold_uncertainty_score":0.9999088},"labels":[],"label_agreement":null},{"id":"W2898388844","doi":"10.1007/978-3-319-92390-1_43","title":"Re-Framing Testing to Better Fit Within Problem-solving Classrooms: Ways to Create and Review Tests","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in mathematics education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; York University","funders":"","keywords":"Mathematics education; Framing (construction); Underpinning; Pencil (optics); Test (biology); Psychology; Pedagogy; Engineering","score_opus":0.05781820994205484,"score_gpt":0.3800965022162223,"score_spread":0.3222782922741675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898388844","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011203188,0.010258823,0.0010184948,0.002132371,0.00072782475,0.002672025,0.0000044317276,0.00009074828,0.98197496],"genre_scores_gemma":[0.0015847477,0.012947593,0.7595005,0.0038699082,0.0018771974,0.00047049337,0.000024243014,0.00015934792,0.21956596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99802744,0.000028744831,0.0006669444,0.00045709524,0.0005013685,0.00031841174],"domain_scores_gemma":[0.99815696,0.00060912897,0.0004900398,0.0003151247,0.00028129123,0.00014745092],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013061723,0.0002937514,0.000440672,0.00020590606,0.00027383966,0.00014643985,0.0003571362,0.00014533348,0.0002999687],"category_scores_gemma":[0.001333075,0.00028672424,0.000041559677,0.00022151142,0.00011570129,0.00038425086,0.00013293413,0.00023065298,0.00015983793],"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":[0.000012140494,0.00048613155,0.011893006,0.015631266,0.000103156264,0.00000793668,0.3193472,0.0000294801,0.000078929996,0.36856458,0.03521763,0.24862854],"study_design_scores_gemma":[0.00013541685,0.00015284387,0.00037539832,0.058078513,0.00017548921,0.0000027045198,0.010483936,0.000030679104,0.000005923953,0.52798176,0.40152907,0.0010482903],"about_ca_topic_score_codex":0.000047484114,"about_ca_topic_score_gemma":0.0015028781,"teacher_disagreement_score":0.76240903,"about_ca_system_score_codex":0.00029402907,"about_ca_system_score_gemma":0.00027622617,"threshold_uncertainty_score":0.9999585},"labels":[],"label_agreement":null},{"id":"W2902865842","doi":"10.3390/educsci8040211","title":"Assessing English: A Comparison between Canada and England’s Assessment Procedures","year":2018,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Portfolio; Subject (documents); Mathematics education; Psychology; Pedagogy; Medical education; Computer science; Library science; Medicine; Business","score_opus":0.0673436257260798,"score_gpt":0.4531102707697182,"score_spread":0.38576664504363845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902865842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89878744,0.00010829657,0.000048553527,0.0019588384,0.0016995756,0.00016468142,0.000001030699,0.000037321035,0.09719428],"genre_scores_gemma":[0.9952469,0.000017169072,0.001981785,0.00017736357,0.0019158031,0.000016705078,0.0000031654029,0.00000344939,0.00063768524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983697,0.00013787957,0.00019022918,0.00027978874,0.00074164505,0.0002807703],"domain_scores_gemma":[0.9991071,0.00026304083,0.00013271353,0.000080201455,0.0002772678,0.0001396706],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0010239515,0.000088345645,0.00012788562,0.00007876284,0.0016661988,0.00083249,0.00030636266,0.00003838093,0.00011432614],"category_scores_gemma":[0.00040653802,0.00007701532,0.000013326395,0.00051317504,0.00072806265,0.00072106277,0.000045101482,0.000080024955,0.0000034484378],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[3.878733e-7,0.00003169852,0.95214146,0.000004551591,0.000004874883,5.8589556e-8,0.021992672,1.8311073e-7,0.000013764789,0.00571809,0.0040036286,0.016088635],"study_design_scores_gemma":[0.0000921497,0.000039057915,0.8074344,0.00003740091,0.000012091383,1.3497967e-7,0.10238497,0.000021188538,0.000039522674,0.00041243384,0.08938855,0.00013811138],"about_ca_topic_score_codex":0.31022263,"about_ca_topic_score_gemma":0.70629203,"teacher_disagreement_score":0.3960694,"about_ca_system_score_codex":0.00016864568,"about_ca_system_score_gemma":0.008378939,"threshold_uncertainty_score":0.9996335},"labels":[],"label_agreement":null},{"id":"W2906729407","doi":"10.5539/ies.v12n1p61","title":"Application of Rubrics in the Classroom: A Vital Tool for Improvement in Assessment, Feedback and Learning","year":2018,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; Grading (engineering); Strengths and weaknesses; Mathematics education; Computer science; Peer assessment; Standards-based assessment; Teaching method; Psychology; Educational assessment; Engineering","score_opus":0.046335732846251504,"score_gpt":0.44900247867417203,"score_spread":0.4026667458279205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906729407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98253983,0.00015485266,0.0013036672,0.004550615,0.0007182398,0.00055328297,0.0000026983926,0.000007997497,0.0101688085],"genre_scores_gemma":[0.9966707,0.0002095071,0.0014236306,0.00019300207,0.00030223254,0.0003461052,0.000008965236,0.0000034312145,0.0008424304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991999,0.00006647657,0.00022230482,0.00013883077,0.00026998128,0.00010247924],"domain_scores_gemma":[0.9988834,0.00036741697,0.00013512438,0.00005269059,0.0005517465,0.000009574587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010033663,0.000057756148,0.000090459806,0.00011052264,0.00015940369,0.00004471074,0.00016516505,0.00002625989,0.000010474073],"category_scores_gemma":[0.00043328357,0.000048370843,0.000022059507,0.00019160456,0.00016554665,0.00015952848,0.000041817217,0.00007621019,0.0000021917367],"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":[0.000024246052,0.00040958176,0.8380501,0.00002031424,0.000057290694,5.6820806e-8,0.042446926,0.0000041663684,0.0005279401,0.0649056,0.001497761,0.052055985],"study_design_scores_gemma":[0.00067063957,0.00014394856,0.7112288,0.00004576656,0.000014060922,2.5550676e-7,0.20362885,0.00032647184,0.000046118974,0.009037979,0.07473084,0.00012627189],"about_ca_topic_score_codex":0.00040676724,"about_ca_topic_score_gemma":0.00085080886,"teacher_disagreement_score":0.16118193,"about_ca_system_score_codex":0.00016249368,"about_ca_system_score_gemma":0.00013099198,"threshold_uncertainty_score":0.19725057},"labels":[],"label_agreement":null},{"id":"W2907726877","doi":"10.5539/jel.v8n1p74","title":"Teachers’ Perceptions on Factors Influence Adoption of Formative Assessment","year":2018,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Stratified sampling; Psychology; Perception; Medical education; School teachers; Sample (material); Mathematics education; Pedagogy; Medicine","score_opus":0.029315647635401475,"score_gpt":0.4112247397543618,"score_spread":0.38190909211896035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907726877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98516566,0.000014656852,0.00018279246,0.00037514893,0.00030516184,0.000041625262,1.2120607e-7,0.0000038943926,0.01391094],"genre_scores_gemma":[0.99802715,0.00007356869,0.0007800322,0.00004721381,0.00024774068,6.9146296e-7,8.9102355e-7,0.0000022637737,0.00082047936],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992987,0.00017305774,0.00017795702,0.00004076318,0.00023965897,0.00006988223],"domain_scores_gemma":[0.9991913,0.00010066759,0.00032961127,0.00002625136,0.00029675808,0.00005540826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063782086,0.00004105365,0.00007952491,0.0001148507,0.00034825885,0.000042601052,0.0000635347,0.00003209607,0.00021667419],"category_scores_gemma":[0.00020035528,0.000033759286,0.000033314343,0.00011700566,0.000110975474,0.00034663753,0.0000071965137,0.00021157225,0.000004885662],"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":[0.0000073601627,0.00014819122,0.6492012,0.000003384692,0.000016956586,3.921353e-8,0.33756632,0.000025446203,0.0008299193,0.002160044,0.00043377202,0.009607371],"study_design_scores_gemma":[0.000079907484,0.00021656769,0.709017,0.000042861615,0.000010468781,3.909651e-7,0.28446102,0.0000065438735,0.000012474792,0.000057126625,0.0060669114,0.000028732387],"about_ca_topic_score_codex":0.000065102555,"about_ca_topic_score_gemma":0.000017762515,"teacher_disagreement_score":0.059815805,"about_ca_system_score_codex":0.000084112726,"about_ca_system_score_gemma":0.00024429723,"threshold_uncertainty_score":0.2678561},"labels":[],"label_agreement":null},{"id":"W2907966827","doi":"10.5430/wje.v8n6p130","title":"Student Self-Assessment in Higher Education: The International Experience and the Greek Example","year":2018,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Self-assessment; Psychology; Higher education; Dialogical self; Self-efficacy; Affect (linguistics); Critical thinking; Formative assessment; Mathematics education; Self-regulated learning; Medical education; Pedagogy; Social psychology","score_opus":0.04237049182951008,"score_gpt":0.40659561016836215,"score_spread":0.36422511833885207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907966827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83113396,0.0005319023,0.000009808471,0.0675926,0.008641349,0.00026792593,1.2505595e-7,0.0000061155465,0.09181619],"genre_scores_gemma":[0.9888223,0.00024368084,0.00048604776,0.0011884932,0.0027682204,0.000031973857,4.5414112e-7,0.000003692234,0.006455161],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988205,0.00018550063,0.00027521746,0.00009025,0.00051725894,0.000111311456],"domain_scores_gemma":[0.9990838,0.00019415427,0.00027107983,0.00010551167,0.0002978224,0.000047636935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013129937,0.000061760504,0.000088577486,0.00011544998,0.00032906537,0.00022829555,0.0004963864,0.000016799911,0.00077741663],"category_scores_gemma":[0.000020103042,0.00003634028,0.00003501243,0.00031796194,0.0002717571,0.00029637173,0.00005067324,0.00015128942,0.0000055144033],"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":[0.0000404458,0.0005994651,0.60119057,0.000001935754,0.000043993703,4.5218232e-7,0.16474049,6.026823e-7,0.000023120647,0.19997883,0.020890355,0.012489742],"study_design_scores_gemma":[0.00035218353,0.000018626157,0.69971615,0.000026739921,0.000015176121,0.0000029426262,0.049750477,0.0000026657221,0.0000024552726,0.0025557403,0.2475122,0.000044603137],"about_ca_topic_score_codex":0.00055932644,"about_ca_topic_score_gemma":0.0011717037,"teacher_disagreement_score":0.22662185,"about_ca_system_score_codex":0.0002844296,"about_ca_system_score_gemma":0.0010140466,"threshold_uncertainty_score":0.8512167},"labels":[],"label_agreement":null},{"id":"W2910055723","doi":"","title":"Assessment for learning in the teaching of traditional Newfoundland craft","year":2018,"lang":"en","type":"article","venue":"2018 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Formative assessment; Context (archaeology); Craft; Government (linguistics); Assessment for learning; Pedagogy; Psychology; Work (physics); Mathematics education; Engineering; Geography","score_opus":0.0833379041947642,"score_gpt":0.37507077196851163,"score_spread":0.2917328677737474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910055723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971717,0.000027754957,0.0002952804,0.011052722,0.00094379723,0.0022481934,0.00002561553,0.0000036894344,0.013685924],"genre_scores_gemma":[0.9977494,0.0000060305056,0.00057475746,0.0001221477,0.0003228379,0.00012747152,0.000006782199,0.000004673283,0.0010859407],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99904704,0.00014862599,0.00020742539,0.00010685509,0.00031794544,0.00017212695],"domain_scores_gemma":[0.9986714,0.0006004122,0.00023943771,0.00016785928,0.00028766174,0.0000331907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019472113,0.000066902525,0.00012085678,0.000029617777,0.0012176431,0.000050826337,0.0006215813,0.000045072888,0.000036307614],"category_scores_gemma":[0.0002041655,0.00004148114,0.00015282625,0.0001490486,0.00040745645,0.00008896095,0.000015921514,0.00012567948,2.3672276e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020353455,0.0008509039,0.3090826,0.000044491415,0.00024315596,7.468837e-9,0.5230769,0.000022473321,0.00016129458,0.13091381,0.027855307,0.0077287205],"study_design_scores_gemma":[0.00044865606,0.00034332916,0.54529756,0.000041949093,0.00009878331,7.78519e-8,0.4324985,0.00028862956,0.000005171143,0.005292732,0.015612023,0.00007259574],"about_ca_topic_score_codex":0.19653884,"about_ca_topic_score_gemma":0.6491056,"teacher_disagreement_score":0.45256674,"about_ca_system_score_codex":0.00021998059,"about_ca_system_score_gemma":0.0023582708,"threshold_uncertainty_score":0.9365249},"labels":[],"label_agreement":null},{"id":"W2910202428","doi":"10.1007/s40037-018-0492-z","title":"Giving feedback on others’ writing","year":2019,"lang":"en","type":"editorial","venue":"Perspectives on Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Medical education; Psychology; Data science; Medicine","score_opus":0.01407736540808381,"score_gpt":0.3876558373560515,"score_spread":0.3735784719479677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910202428","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017508866,0.0003900663,0.000013971329,0.0063150614,0.68759006,0.00046325955,0.000010007699,0.00011540627,0.30335128],"genre_scores_gemma":[0.020908644,0.0016256529,0.00008942376,0.0005199937,0.9379394,0.00007298493,0.00008251697,0.0000641324,0.038697228],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99403065,0.00041746316,0.00033061416,0.0007906764,0.0039254213,0.0005051577],"domain_scores_gemma":[0.99614596,0.0024447264,0.00028751267,0.00035638973,0.0004184369,0.00034696556],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018123232,0.0003152833,0.00039338632,0.00025595547,0.00051914825,0.00027050322,0.00077607844,0.0010396149,0.0052325814],"category_scores_gemma":[0.0143628055,0.00030666127,0.00018245894,0.0003378459,0.00033814,0.00016314996,0.000057071808,0.0015441308,0.0012710745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003247131,0.0006039408,0.00018862606,0.000032066964,0.000045204797,0.0000010094956,0.06984995,4.365557e-7,9.397235e-7,0.011293869,0.91093075,0.00702071],"study_design_scores_gemma":[0.00030528885,0.00012663368,0.0004535677,0.00063786225,0.000024193658,6.9552385e-8,0.20727202,0.000005288866,5.961821e-7,0.00024175447,0.79063505,0.0002976634],"about_ca_topic_score_codex":0.0010904896,"about_ca_topic_score_gemma":0.00021859827,"teacher_disagreement_score":0.26465407,"about_ca_system_score_codex":0.0015476977,"about_ca_system_score_gemma":0.0061690933,"threshold_uncertainty_score":0.99993855},"labels":[],"label_agreement":null},{"id":"W2910283173","doi":"10.53841/bpsptr.2018.24.2.64","title":"Using the Immediate Feedback Assessment Technique (IFAT) for non-assessments: Student perceptions and performance","year":2018,"lang":"en","type":"article","venue":"Psychology Teaching Review","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Durham College","funders":"","keywords":"Psychology; Lottery; Class (philosophy); Mathematics education; Perception; Reading (process); Medical education; Computer science; Statistics; Mathematics; Medicine; Linguistics","score_opus":0.0840307749180396,"score_gpt":0.5186797314255001,"score_spread":0.43464895650746044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910283173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63204426,0.013437706,0.13152406,0.035672646,0.0052314894,0.016510926,0.000028685745,0.00045065547,0.16509958],"genre_scores_gemma":[0.9012023,0.05021112,0.038298573,0.0072021745,0.0012783397,0.001032309,0.000013440058,0.000044461503,0.0007172657],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976312,0.0005881669,0.0004445904,0.0004619938,0.00036889472,0.0005051508],"domain_scores_gemma":[0.99886745,0.00020882626,0.00025387487,0.00042527402,0.00014043607,0.00010414985],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00514765,0.00022531625,0.00038239558,0.000072445,0.0021935925,0.000118572265,0.0006337429,0.00012020787,0.00021735397],"category_scores_gemma":[0.00007584119,0.000164586,0.0001227507,0.00021965003,0.0005988568,0.00027036935,0.0001415991,0.00045777007,0.00002700346],"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":[0.00006528743,0.0012111203,0.67197,0.0014475683,0.0005070727,0.0000035453054,0.022878228,7.5923845e-7,0.004573908,0.014575844,0.05647258,0.2262941],"study_design_scores_gemma":[0.0014453973,0.0009826766,0.5940252,0.0030439831,0.00064883364,0.000027123126,0.0064903004,0.00024571767,0.000007755741,0.00083066185,0.39142704,0.00082529866],"about_ca_topic_score_codex":0.00006335712,"about_ca_topic_score_gemma":0.000052790227,"teacher_disagreement_score":0.33495447,"about_ca_system_score_codex":0.00016002422,"about_ca_system_score_gemma":0.00011122683,"threshold_uncertainty_score":0.9991054},"labels":[],"label_agreement":null},{"id":"W2910439838","doi":"10.20381/ruor-22955","title":"Large-scale Assessment and Mathematics Teacher Practice: A Case Study with Ontario Grade 9 Applied Teachers","year":2019,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Scale (ratio); Pedagogy; Mathematics; Psychology; Geography; Cartography","score_opus":0.05698183760826345,"score_gpt":0.410490315276935,"score_spread":0.35350847766867155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910439838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7095697,0.000010070118,0.000030586954,0.0002201127,0.000056775665,0.0016139939,0.000005656386,0.00002574322,0.28846735],"genre_scores_gemma":[0.83458054,0.000049363593,0.004511689,0.0000051023253,0.000043281194,0.0000067657907,0.00006745654,0.000029878442,0.16070592],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9961082,0.00050324795,0.00017120467,0.0005174816,0.002149421,0.00055049773],"domain_scores_gemma":[0.9982685,0.00041406052,0.00030252192,0.00037135222,0.0004377722,0.0002057994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036803558,0.00021845239,0.00044752253,0.00039562373,0.0012721815,0.00015654333,0.00053969375,0.00028128072,0.0006313177],"category_scores_gemma":[0.00004552966,0.00023157141,0.00007129267,0.00049002515,0.00029230447,0.0003938727,0.00015222943,0.0012364851,0.000027016966],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042581993,0.0028602309,0.20306642,0.00012321767,0.00047350462,0.00081493804,0.7845677,9.90385e-7,0.000019714571,0.0054525896,0.0020438943,0.0005341877],"study_design_scores_gemma":[0.0014336085,0.00042759278,0.056630965,0.000046240948,0.00023877299,0.000008279171,0.9145292,0.000019539744,6.808821e-7,0.00004388929,0.026386742,0.00023449375],"about_ca_topic_score_codex":0.053549476,"about_ca_topic_score_gemma":0.7755955,"teacher_disagreement_score":0.72204596,"about_ca_system_score_codex":0.0007900728,"about_ca_system_score_gemma":0.0015214867,"threshold_uncertainty_score":0.978472},"labels":[],"label_agreement":null},{"id":"W2914965366","doi":"10.1002/9780470690048.ch10","title":"The Role of Assessment in a Learning Culture","year":2002,"lang":"en","type":"other","venue":"Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Reading (process); Section (typography); Mathematics education; Psychology; Process (computing); Pedagogy; Computer science; Political science","score_opus":0.012356049490881798,"score_gpt":0.32887429515767197,"score_spread":0.31651824566679015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914965366","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024241514,0.004109236,0.000016205853,0.00013304486,0.00009335364,0.00013593718,2.7857675e-7,0.000107060136,0.9929807],"genre_scores_gemma":[0.24807225,0.001741455,0.00041749523,0.0000062562503,0.00025922194,0.0000071673626,0.0000032067167,0.000063463085,0.74942946],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99769884,0.001350632,0.0001555016,0.00018784164,0.00034476107,0.00026242953],"domain_scores_gemma":[0.9993652,0.00027884223,0.00022863309,0.00007613073,0.0000105784575,0.000040576713],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0021162224,0.00013439488,0.00021557549,0.000098340155,0.0010414291,0.000116573996,0.00019108264,0.00018051118,0.0003046953],"category_scores_gemma":[0.00030247236,0.00009985391,0.000049334893,0.0000948144,0.00012517866,0.000038653376,0.000060728526,0.0023835294,0.000009211103],"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":[0.000008629907,0.000110069384,0.33108497,0.0000541666,0.00012902082,0.0000064267188,0.2751297,0.00013207254,0.00010350593,0.027488127,0.028706532,0.33704677],"study_design_scores_gemma":[0.00013224449,0.000030698473,0.001270091,0.0001699681,0.000013159716,1.8997224e-7,0.07937921,0.00021723902,1.5937545e-7,0.00005850143,0.91861266,0.00011586045],"about_ca_topic_score_codex":0.004928202,"about_ca_topic_score_gemma":0.0009161459,"teacher_disagreement_score":0.88990617,"about_ca_system_score_codex":0.00004572513,"about_ca_system_score_gemma":0.000035093013,"threshold_uncertainty_score":0.999918},"labels":[],"label_agreement":null},{"id":"W2919446416","doi":"10.18162/ritpu.2009.159","title":"10.18162/ritpu.2009.159","year":2016,"lang":"fr","type":"dataset","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Pencil (optics); Multiple choice; Test (biology); Significant difference; Psychology; Cognition; Mathematics education; Computer science; Statistics; Mathematics; Engineering","score_opus":0.03289347138127198,"score_gpt":0.34694202684143716,"score_spread":0.3140485554601652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919446416","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003650552,0.0009523214,0.000022701344,0.0055060843,0.003012403,0.00041338798,0.5380069,0.000086146734,0.45196354],"genre_scores_gemma":[0.000045902176,0.0027277642,0.00013287447,0.00057802576,0.0040879627,0.0000347414,0.24715789,0.000028369184,0.7452065],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99571514,0.0003626527,0.00060364266,0.00082475523,0.0013549348,0.0011388508],"domain_scores_gemma":[0.99783236,0.00051267433,0.00034621524,0.0007213667,0.00018372702,0.00040364658],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008474849,0.00058946834,0.0006712819,0.000153541,0.0007640643,0.0003008328,0.0017004865,0.0008330147,0.510806],"category_scores_gemma":[0.00015530281,0.0004495639,0.00037612978,0.00055536715,0.0009814163,0.00046924473,0.00044186524,0.00038939825,0.23860373],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000208665,0.00021810435,0.00021884308,0.000034274384,0.00013888041,0.000020204436,0.00023936055,6.651846e-8,0.0000036955357,0.00756563,0.9837248,0.00781528],"study_design_scores_gemma":[0.00052607,0.00016622603,0.0003174645,0.00014721758,0.0001648447,0.0000013167498,0.00087534764,0.0000011309256,0.0000037264901,0.00076053437,0.99631363,0.00072246284],"about_ca_topic_score_codex":0.0024393313,"about_ca_topic_score_gemma":0.0027334562,"teacher_disagreement_score":0.29324296,"about_ca_system_score_codex":0.00030968414,"about_ca_system_score_gemma":0.00035260143,"threshold_uncertainty_score":0.9997956},"labels":[],"label_agreement":null},{"id":"W2923578044","doi":"10.1186/s40468-019-0078-7","title":"The language assessment literacy needs of Iranian EFL teachers with a focus on reformed assessment policies","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Rubric; Psychology; Literacy; Curriculum; Pedagogy; Active listening; Mathematics education; Language assessment; Alternative assessment; Perception; Focus group; Sociology","score_opus":0.016486939779852855,"score_gpt":0.3597537479867195,"score_spread":0.3432668082068666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923578044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73854375,0.000086236636,0.000011115717,0.0008582077,0.00010694401,0.00047829407,0.0000032763596,0.00008218337,0.25983],"genre_scores_gemma":[0.9922814,0.000008688894,0.00398759,0.00010257393,0.00012386173,0.000039190592,0.0000059089452,0.00002603912,0.0034247441],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99787766,0.00027869164,0.00033678685,0.0002079076,0.0007577382,0.00054124225],"domain_scores_gemma":[0.99822253,0.00095411635,0.00026533718,0.000401505,0.00007523277,0.00008127846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012979126,0.00020248181,0.0002800356,0.00018488336,0.00027335342,0.00020277839,0.0005256163,0.00008174123,0.000090272304],"category_scores_gemma":[0.00021551726,0.00013157044,0.00006249021,0.00095696683,0.00017420146,0.00020029148,0.00008140898,0.0003746251,0.000018236964],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002767608,0.00015224538,0.7561647,0.000022006652,0.000041083946,0.000022920834,0.20572098,0.000023045031,0.0023872466,0.0082842,0.000059402446,0.027094468],"study_design_scores_gemma":[0.001109891,0.0003988157,0.66257334,0.00031725364,0.000024641091,0.000002201009,0.33428672,0.00016493916,0.00014020417,0.00011619222,0.0006004857,0.00026531573],"about_ca_topic_score_codex":0.008235031,"about_ca_topic_score_gemma":0.0026889099,"teacher_disagreement_score":0.25640526,"about_ca_system_score_codex":0.00034717194,"about_ca_system_score_gemma":0.0002686807,"threshold_uncertainty_score":0.9983692},"labels":[],"label_agreement":null},{"id":"W2923740196","doi":"10.1080/0969594x.2019.1593105","title":"Conceptualising fairness in classroom assessment: exploring the value of organisational justice theory","year":2019,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Foundation (evidence); Economic Justice; Scholarship; Value (mathematics); Core (optical fiber); Sociology; Psychology; Social psychology; Epistemology; Political science; Computer science; Law","score_opus":0.07905727411628827,"score_gpt":0.4421515498552321,"score_spread":0.3630942757389438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923740196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76570654,0.00013080242,0.00032807325,0.013752635,0.0010582444,0.0006923455,0.0000037942968,0.000020871556,0.21830669],"genre_scores_gemma":[0.992701,0.0008593524,0.0037466786,0.0010143329,0.00039764206,0.00010815565,0.000013913601,0.0000148620375,0.0011440843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.996267,0.0019421374,0.0005124431,0.00030239008,0.00064990047,0.00032610804],"domain_scores_gemma":[0.99162704,0.007442335,0.00041942517,0.00025899382,0.00018276172,0.000069440895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005509842,0.00015313391,0.00021529787,0.00026529544,0.00030250798,0.00017681715,0.00035393855,0.00008157531,0.00018143698],"category_scores_gemma":[0.0019450791,0.00013766268,0.000035910634,0.0008488765,0.00022386565,0.0017424127,0.00013192664,0.00040146185,0.000010186719],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028650853,0.00032297347,0.10661192,0.0000401553,0.000020596719,4.1832726e-7,0.037772484,0.00018406726,0.00012307975,0.8522458,0.000021723175,0.002628144],"study_design_scores_gemma":[0.0005097623,0.000038422342,0.56339604,0.00009847654,0.000060778664,0.0000028898432,0.37739146,0.00014479014,0.000019613757,0.014906913,0.043244857,0.0001859801],"about_ca_topic_score_codex":0.0034723678,"about_ca_topic_score_gemma":0.00035615792,"teacher_disagreement_score":0.83733886,"about_ca_system_score_codex":0.0005734127,"about_ca_system_score_gemma":0.0037322294,"threshold_uncertainty_score":0.6620815},"labels":[],"label_agreement":null},{"id":"W2929902524","doi":"10.1021/acs.jchemed.9b00072","title":"Writing as a Mode of Learning: Staged Approaches to Chromatography and Writing in the Undergraduate Organic Lab","year":2019,"lang":"en","type":"article","venue":"Journal of Chemical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Waterloo","funders":"Korea Electrotechnology Research Institute; University of Winnipeg","keywords":"TUTOR; Craft; Scientific writing; Mathematics education; Reflection (computer programming); Process (computing); Professional writing; Computer science; Peer tutor; Report writing; Chemistry; Psychology; Visual arts; Literature; Art; Library science","score_opus":0.03764289474911719,"score_gpt":0.3391362368971839,"score_spread":0.3014933421480667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2929902524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99026775,0.00009746664,0.000010647089,0.005176948,0.000061031566,0.000118146774,9.2945555e-8,0.0000031533841,0.0042647407],"genre_scores_gemma":[0.999224,0.000039778824,0.00043639462,0.00008505709,0.00015352257,0.0000020497253,7.5309583e-7,0.000004445815,0.00005399557],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9990958,0.000121987716,0.00026806252,0.000071516704,0.0003290616,0.00011356819],"domain_scores_gemma":[0.99939984,0.00021135887,0.0002219933,0.000044847337,0.00007301813,0.00004895947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088603265,0.000049913928,0.00012515287,0.00009213113,0.000053038217,0.000064553875,0.00016106178,0.00003975849,0.00002387215],"category_scores_gemma":[0.00017170314,0.00003912561,0.000040884348,0.0003611013,0.00004289072,0.00015534188,0.000019480685,0.00021016371,0.0000022383224],"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":[0.000047365436,0.00043190396,0.7237233,0.00007869735,0.000040892075,6.8939016e-7,0.10946088,0.000015801641,0.14705986,0.014158569,0.0003421241,0.004639914],"study_design_scores_gemma":[0.0016202962,0.0003625967,0.12008524,0.00076123554,0.00010696156,0.000028161134,0.83707213,0.00016148042,0.020484464,0.01717205,0.0017135909,0.0004317814],"about_ca_topic_score_codex":0.00006748009,"about_ca_topic_score_gemma":0.00000817703,"teacher_disagreement_score":0.72761124,"about_ca_system_score_codex":0.000044039396,"about_ca_system_score_gemma":0.00021335327,"threshold_uncertainty_score":0.15954961},"labels":[],"label_agreement":null},{"id":"W2930362096","doi":"10.5539/hes.v9n2p117","title":"Using Digital Tools to Assess and Improve College Student Writing","year":2019,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Grading (engineering); Higher education; Computer science; Learning analytics; Workload; Sophistication; Curriculum; Mathematics education; Medical education; Pedagogy; Psychology; Data science; Engineering; Sociology","score_opus":0.1686309663595367,"score_gpt":0.47804219324124064,"score_spread":0.30941122688170397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930362096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94783866,0.00071794476,0.0000037869875,0.0014523269,0.0026714972,0.00045442913,0.000007432987,0.00003821141,0.046815686],"genre_scores_gemma":[0.9731615,0.00006461137,0.00051375607,0.00034589396,0.00057043275,0.00004371759,0.0000016959705,0.000009266053,0.025289094],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99896944,0.000041027724,0.00017673115,0.00024150005,0.00034757346,0.00022373203],"domain_scores_gemma":[0.9992625,0.00020370122,0.000072636794,0.000104058345,0.00027748419,0.00007959417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002574325,0.00010568253,0.00018052298,0.00006583344,0.00037816,0.00034139823,0.00012161919,0.000034405643,0.00011222583],"category_scores_gemma":[0.000028703216,0.000100359626,0.00002880379,0.00024777834,0.00007219038,0.00052217144,0.00014680102,0.000052572082,0.000080033424],"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":[0.000008391849,0.00025894208,0.8964426,0.000035941808,0.00015410448,6.5122833e-7,0.020204555,0.0000019027415,0.000629685,0.07480162,0.00566604,0.0017955487],"study_design_scores_gemma":[0.0002511629,0.00004659209,0.5569219,0.0000680469,0.000030380936,2.7340943e-7,0.3267257,8.4070285e-7,0.000021760196,0.00033938483,0.11534734,0.00024662155],"about_ca_topic_score_codex":0.000050189854,"about_ca_topic_score_gemma":0.000014972604,"teacher_disagreement_score":0.33952072,"about_ca_system_score_codex":0.00018384305,"about_ca_system_score_gemma":0.00015201021,"threshold_uncertainty_score":0.40925467},"labels":[],"label_agreement":null},{"id":"W2930367903","doi":"","title":"Preparing for the exam vs. developing the language proficiency: A washback study on the learners","year":2018,"lang":"en","type":"article","venue":"2019 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics education; Certificate; Psychology; Test (biology); School Certificate; Pedagogy; Focus group; Argument (complex analysis); English language; Medical education; Sociology; Medicine; Mathematics","score_opus":0.06936604890178882,"score_gpt":0.37074523631046336,"score_spread":0.30137918740867453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930367903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9629652,0.000079702426,0.000058258975,0.023515949,0.00123195,0.0074809794,0.000011815593,0.000010356766,0.004645817],"genre_scores_gemma":[0.9945542,0.000014941161,0.000047419173,0.00055004534,0.0003329263,0.0005348663,0.0000015431118,0.000011906831,0.0039521204],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9985469,0.00019544968,0.00023614313,0.00021557057,0.0004682344,0.00033772716],"domain_scores_gemma":[0.99753535,0.001114191,0.00029062337,0.0005994909,0.00041602607,0.000044345255],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0027666516,0.00013292294,0.000146898,0.000021544247,0.0037053952,0.00017347117,0.0017442161,0.000051321058,0.000028988492],"category_scores_gemma":[0.00047604763,0.00005724876,0.00019477821,0.00037099468,0.0006792305,0.00008119736,0.000091001384,0.00015405465,0.0000038468374],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002826117,0.0002795929,0.022700112,0.000012602359,0.00035764676,7.519113e-9,0.9189576,0.000011290445,0.0000456737,0.022382226,0.030372001,0.004853019],"study_design_scores_gemma":[0.00026459066,0.0002654421,0.09733152,0.000031206844,0.00017209836,6.402987e-8,0.89365673,0.00015721744,0.000050303464,0.0003942433,0.0075801387,0.00009643568],"about_ca_topic_score_codex":0.12315107,"about_ca_topic_score_gemma":0.46985942,"teacher_disagreement_score":0.34670836,"about_ca_system_score_codex":0.0002560823,"about_ca_system_score_gemma":0.0026888219,"threshold_uncertainty_score":0.9975917},"labels":[],"label_agreement":null},{"id":"W2935437723","doi":"","title":"Teacher candidates' approaches to assessment: A latent class analysis","year":2019,"lang":"en","type":"article","venue":"2019 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Class (philosophy); Context (archaeology); Certification; Psychology; Teacher education; Relevance (law); Pedagogy; Mathematics education; Latent class model; Computer science; Political science","score_opus":0.08837553336067248,"score_gpt":0.3379940463399017,"score_spread":0.2496185129792292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935437723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97231585,0.000038586393,0.00004626578,0.009658199,0.0006255925,0.0025991523,0.00003082577,0.0000061237706,0.014679382],"genre_scores_gemma":[0.98499626,0.000008177212,0.00018681586,0.00016148276,0.000079742575,0.00011502809,0.000012262882,0.0000072204716,0.014433011],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99882495,0.00009987547,0.0002141889,0.00020165724,0.00040416184,0.00025519173],"domain_scores_gemma":[0.9988857,0.0001321787,0.00021053158,0.000425569,0.00022863537,0.000117406445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092912535,0.00010304416,0.00022260488,0.00007459469,0.0005514094,0.00008714957,0.0007975201,0.000068893285,0.00021521418],"category_scores_gemma":[0.000045313405,0.00006991656,0.00033557514,0.0007387598,0.00012494718,0.0000891565,0.00005246944,0.00010766578,0.000006506297],"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":[0.000010237567,0.00041944993,0.80329585,0.000017433375,0.0015672646,6.5851653e-9,0.15550348,0.0001908054,0.000037432397,0.019868292,0.016999148,0.0020906029],"study_design_scores_gemma":[0.00034345675,0.000118980286,0.7023445,0.000018047931,0.0009911862,2.6566195e-8,0.28313783,0.0010254586,0.00001020854,0.00035327574,0.011495102,0.00016196656],"about_ca_topic_score_codex":0.3740175,"about_ca_topic_score_gemma":0.6966798,"teacher_disagreement_score":0.32266226,"about_ca_system_score_codex":0.00038238915,"about_ca_system_score_gemma":0.002533398,"threshold_uncertainty_score":0.630151},"labels":[],"label_agreement":null},{"id":"W2941199026","doi":"10.1187/cbe.17-07-0137","title":"Retention following Two-Stage Collaborative Exams Depends on Timing and Student Performance","year":2019,"lang":"en","type":"article","venue":"CBE—Life Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Knowledge retention; Retention rate; Retention time; Collaborative learning; Psychology; Content (measure theory); Computer science; Medical education; Mathematics education; Medicine; Chemistry; Mathematics; Chromatography","score_opus":0.042398828372233945,"score_gpt":0.403120116642093,"score_spread":0.36072128826985905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941199026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8978054,0.00017025133,0.000009341151,0.0005988266,0.0030734392,0.00046466666,0.000001019579,0.00003850191,0.09783856],"genre_scores_gemma":[0.9911311,0.00015622965,0.00033503005,0.00026018638,0.00024156095,0.00003304273,0.000005030572,0.0000063161697,0.007831486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980926,0.00015403185,0.00019167709,0.00041293434,0.00084214367,0.00030663304],"domain_scores_gemma":[0.9993678,0.00012625886,0.00015164255,0.00013624715,0.000092059374,0.00012601688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00166446,0.00012037328,0.00013710892,0.0001584734,0.0010891618,0.0003120414,0.0003126757,0.000050246897,0.00018250122],"category_scores_gemma":[0.00011154433,0.000110631125,0.000039410184,0.0008310085,0.00021084183,0.0009189893,0.000053567906,0.00009633972,0.00010278853],"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":[0.000013054952,0.00013620412,0.9449312,0.0000134137435,0.000016040822,2.6588177e-7,0.02962423,0.00008159082,0.0006590398,0.01152368,0.0004934229,0.012507864],"study_design_scores_gemma":[0.00075101474,0.0004254552,0.7237901,0.00017810173,0.00003704855,3.2207012e-7,0.2595634,0.00061517203,0.00032292842,0.0001844676,0.013691681,0.0004402873],"about_ca_topic_score_codex":0.00019106508,"about_ca_topic_score_gemma":0.00011974422,"teacher_disagreement_score":0.22993916,"about_ca_system_score_codex":0.00016085483,"about_ca_system_score_gemma":0.00077776145,"threshold_uncertainty_score":0.83770627},"labels":[],"label_agreement":null},{"id":"W2942832874","doi":"10.3138/cmlr.2018-0197","title":"Self-Assessment in the Primary L2 Writing Classroom","year":2019,"lang":"fr","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.013911688384095337,"score_gpt":0.27811199888622334,"score_spread":0.264200310502128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942832874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57360715,0.30039686,0.00001650399,0.010723016,0.00094435614,0.0018530634,0.00021170756,0.000067515844,0.112179816],"genre_scores_gemma":[0.88760644,0.08978949,0.0020847702,0.0076418687,0.0011359042,0.00016556167,0.0002731894,0.000119466,0.011183328],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948368,0.0012984213,0.0007753075,0.00075873523,0.0003715171,0.0019592398],"domain_scores_gemma":[0.9970948,0.0007991262,0.00028923995,0.00083458045,0.0001513898,0.000830877],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030845967,0.0005439355,0.0009360996,0.0002890659,0.00042713858,0.00027276351,0.0013995926,0.00030516548,0.0010256949],"category_scores_gemma":[0.00016210461,0.00049493695,0.00034029866,0.0012131955,0.00035646325,0.00046709052,0.00009478441,0.0009026945,0.00028899385],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013221479,0.0004153302,0.21089168,0.024680953,0.00052894163,0.0068594627,0.45461515,0.00002169955,0.00085962296,0.06407866,0.013021829,0.22401345],"study_design_scores_gemma":[0.0009839518,0.00016909819,0.22107063,0.016679537,0.00053581456,0.00031470598,0.08915239,0.0013882644,0.000002065722,0.0010974488,0.66696244,0.0016436535],"about_ca_topic_score_codex":0.34096295,"about_ca_topic_score_gemma":0.82772726,"teacher_disagreement_score":0.6539406,"about_ca_system_score_codex":0.003697982,"about_ca_system_score_gemma":0.0013657681,"threshold_uncertainty_score":0.9998875},"labels":[],"label_agreement":null},{"id":"W2943008257","doi":"10.55016/ojs/jet.v40i2.52563","title":"Standardized Testing and the Classroom","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardized test; Psychology; Mathematics education; Pedagogy","score_opus":0.04197803242966986,"score_gpt":0.3914393847025016,"score_spread":0.34946135227283176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943008257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67302656,0.0008508509,0.00016508918,0.066137984,0.0021326167,0.00017125241,0.0000018744284,0.000006422809,0.25750732],"genre_scores_gemma":[0.96932465,0.000114589755,0.017497297,0.00038265125,0.0068629663,0.0000020486352,1.9040266e-7,0.000004729501,0.005810888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990591,0.00015604796,0.00020203392,0.000050798048,0.00042313014,0.00010889722],"domain_scores_gemma":[0.99738353,0.001712522,0.00023893444,0.000046739176,0.0005571591,0.000061119186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017778681,0.000044193905,0.000106142215,0.000040358977,0.00051460357,0.0001137707,0.00017678314,0.000024390518,0.00038530497],"category_scores_gemma":[0.00201054,0.000026816837,0.000045230277,0.00021072311,0.0005504102,0.00017972273,0.000021024238,0.00009952439,0.000011251174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002562993,0.000098808334,0.14965567,0.000003814284,0.00010156245,7.661051e-7,0.014580953,7.0754226e-7,0.00013149224,0.7780228,0.051974975,0.00517214],"study_design_scores_gemma":[0.002833742,0.00014911933,0.25086868,0.00007974831,0.00009838322,0.00002766104,0.015006056,0.000018354938,0.000042069347,0.20887806,0.5218432,0.00015491422],"about_ca_topic_score_codex":0.00004518898,"about_ca_topic_score_gemma":0.000041529165,"teacher_disagreement_score":0.5691448,"about_ca_system_score_codex":0.00005323654,"about_ca_system_score_gemma":0.0005609334,"threshold_uncertainty_score":0.4218819},"labels":[],"label_agreement":null},{"id":"W2943955341","doi":"10.4300/jgme-d-18-01003.1","title":"Faculty and Resident Perspectives on Using Entrustment Anchors for Workplace-Based Assessment","year":2019,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Normative; Medical education; Data collection; Grounded theory; Psychology; Computer science; Medicine; Qualitative research; Sociology; Political science","score_opus":0.07086773104654848,"score_gpt":0.45126005979494244,"score_spread":0.38039232874839396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943955341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9771335,0.00020604474,0.00070875144,0.018353086,0.0015208607,0.0004197021,0.0000013288468,0.0000066632665,0.0016500686],"genre_scores_gemma":[0.9943474,0.00022311695,0.0035534294,0.00038747792,0.00074370793,0.000008513615,0.0000044766402,0.000007835664,0.00072407577],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9980214,0.00015007367,0.00029406082,0.00014078493,0.0012103036,0.00018338158],"domain_scores_gemma":[0.9988376,0.00021829609,0.0003217609,0.00006827796,0.0003104511,0.00024361591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016458741,0.00009038554,0.00018449912,0.00013401915,0.00019341859,0.000089846646,0.00015000213,0.0000705778,0.00030447126],"category_scores_gemma":[0.0005015207,0.00007118334,0.000088772875,0.00013778002,0.00009606457,0.00015908436,0.000012624702,0.00020295075,0.000003008446],"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":[0.0013841082,0.006475191,0.53252304,0.0003141819,0.00063929625,0.000015235865,0.1846894,0.00037354036,0.00046986557,0.095483296,0.10479485,0.072837986],"study_design_scores_gemma":[0.0067664846,0.0019956129,0.4168788,0.0016783241,0.00032804726,0.000011110394,0.502004,0.003454009,0.00012982542,0.005480466,0.060653158,0.0006201666],"about_ca_topic_score_codex":0.000101296086,"about_ca_topic_score_gemma":0.000020730075,"teacher_disagreement_score":0.31731462,"about_ca_system_score_codex":0.00055014977,"about_ca_system_score_gemma":0.0024729737,"threshold_uncertainty_score":0.4386949},"labels":[],"label_agreement":null},{"id":"W2945827673","doi":"10.31542/r.gm:1624","title":"Effects of feedback templates on student performance","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Template; Feedback control; Computer science; Control (management); Work (physics); Artificial intelligence; Engineering; Control engineering; Programming language","score_opus":0.014219661856784999,"score_gpt":0.3529219634070954,"score_spread":0.33870230155031045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945827673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63060963,0.00006978767,3.4362415e-7,0.000018762586,0.0013485696,0.00040339842,7.078518e-7,0.000039691215,0.3675091],"genre_scores_gemma":[0.8501877,0.00062042236,0.00008762433,0.00003764957,0.00047488816,0.000036517613,0.000051068742,0.000020932179,0.14848319],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99819005,0.000065960325,0.00026471296,0.0002706663,0.0009238997,0.00028474152],"domain_scores_gemma":[0.9991551,0.00020387462,0.00023789985,0.00015196596,0.00018228006,0.000068880276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003011452,0.00021043206,0.00032161016,0.00012877643,0.00030021148,0.0000634192,0.00047253122,0.00025600367,0.00078872073],"category_scores_gemma":[0.000047437803,0.00017885894,0.000114067494,0.00022388865,0.00010267729,0.00010817381,0.00002263067,0.00015121786,0.00044799535],"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":[0.0012934324,0.004573204,0.27263957,0.004070275,0.0017691319,0.000021708793,0.4627522,0.0000036059073,0.00439561,0.04997114,0.13328716,0.065222956],"study_design_scores_gemma":[0.00080122467,0.00076139823,0.9265992,0.00075415033,0.00016565916,5.3310227e-8,0.028204419,0.0000026382004,0.018027056,0.00013009748,0.024011524,0.0005425468],"about_ca_topic_score_codex":0.00029507824,"about_ca_topic_score_gemma":0.0010724348,"teacher_disagreement_score":0.6539597,"about_ca_system_score_codex":0.0000792544,"about_ca_system_score_gemma":0.00013392886,"threshold_uncertainty_score":0.8635939},"labels":[],"label_agreement":null},{"id":"W2946729216","doi":"10.55016/ojs/jet.v51i2.58451","title":"Alberta’s New Teaching Quality Standard and Its Implications for Teacher Education","year":2019,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Quality (philosophy); Teacher quality; Psychology; Mathematics education; Pedagogy; Epistemology; Economics; Operations management; Philosophy","score_opus":0.05178738373696707,"score_gpt":0.4593764704320529,"score_spread":0.4075890866950858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946729216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7390834,0.0012189621,0.0003293681,0.14518633,0.0022990897,0.00062163774,0.000009072996,0.0000067440888,0.1112454],"genre_scores_gemma":[0.84341824,0.000120529294,0.010877131,0.00039084646,0.0034407172,0.000014137904,0.000010726378,0.000012012308,0.14171563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989895,0.00012775508,0.00034236026,0.00011967104,0.00027268112,0.00014801488],"domain_scores_gemma":[0.9981592,0.00083576236,0.0003863336,0.000085027066,0.0003714714,0.00016215186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012324038,0.0000773529,0.000160834,0.00008877692,0.0003002527,0.00010910431,0.0002032147,0.000057204972,0.0005397604],"category_scores_gemma":[0.0009445365,0.00007020444,0.00008857354,0.00010258949,0.00002678776,0.00049167074,0.000016167378,0.00014872421,0.000016972368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000373308,0.00019815324,0.15871534,0.00001206924,0.00003247805,4.8056448e-9,0.0053153206,0.0000015325822,0.00034583852,0.76245666,0.06652387,0.006361423],"study_design_scores_gemma":[0.00038146466,0.000060892686,0.3583555,0.000037699592,0.000035540175,0.0000027650522,0.0046462473,0.0000014762165,0.000013666785,0.03659438,0.5997565,0.00011390515],"about_ca_topic_score_codex":0.000338982,"about_ca_topic_score_gemma":0.00027811696,"teacher_disagreement_score":0.72586226,"about_ca_system_score_codex":0.0001871309,"about_ca_system_score_gemma":0.0025960817,"threshold_uncertainty_score":0.5909998},"labels":[],"label_agreement":null},{"id":"W2948214676","doi":"10.1002/9781118784235.eelt0321","title":"Preparing Students to Take Tests","year":2018,"lang":"en","type":"other","venue":"The TESOL Encyclopedia of English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Test (biology); Context (archaeology); Mathematics education; Test preparation; Academic achievement; Student achievement; Psychology; Achievement test; Scale (ratio); Empirical research; Teacher preparation; Pedagogy; Medical education; Standardized test; Teacher education; Engineering; Medicine; Mathematics","score_opus":0.011415522042493593,"score_gpt":0.33989004920855964,"score_spread":0.32847452716606607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948214676","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01905332,0.0004363768,0.000026822438,0.00003836698,0.002181925,0.001015585,0.000017768716,0.0005580138,0.9766718],"genre_scores_gemma":[0.038024977,0.00023208058,0.0019279383,0.00014851938,0.010688556,0.0000683793,0.000018872784,0.0003499416,0.94854075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693084,0.00044289455,0.00036729526,0.00044799052,0.001226396,0.00058458187],"domain_scores_gemma":[0.9982677,0.0003856559,0.00035685571,0.00072178856,0.00009632983,0.00017166392],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020742998,0.00034659178,0.00046357652,0.00024195915,0.0003708308,0.00014602214,0.0020987883,0.0002561198,0.002295478],"category_scores_gemma":[0.003540588,0.00027187605,0.00014264818,0.0002774499,0.00022620767,0.00010967483,0.0005522883,0.00046765897,0.00028602954],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009026627,0.00013306757,0.013507759,0.000036222966,0.0001331397,0.0000050929375,0.42088372,7.179947e-7,0.000010852774,0.0006160467,0.5580385,0.0066259056],"study_design_scores_gemma":[0.00023367742,0.000055000983,0.0009228242,0.0003124951,0.00009685014,1.2417554e-7,0.046955828,6.947461e-7,0.0000028653403,0.000020809934,0.9510539,0.00034494366],"about_ca_topic_score_codex":0.0065800203,"about_ca_topic_score_gemma":0.00896974,"teacher_disagreement_score":0.39301544,"about_ca_system_score_codex":0.000103273436,"about_ca_system_score_gemma":0.000106752435,"threshold_uncertainty_score":0.99997336},"labels":[],"label_agreement":null},{"id":"W2948450036","doi":"10.11575/pplt.v3i1.53146","title":"Conversations and Perspectives on Peer Feedback for Problem Solving","year":2018,"lang":"en","type":"article","venue":"University of Calgary","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Conversation; Peer feedback; Session (web analytics); Leverage (statistics); Computer science; Context (archaeology); Peer review; Mathematics education; Psychology; Pedagogy; World Wide Web; Artificial intelligence; Political science","score_opus":0.028446742653643012,"score_gpt":0.2801169388451335,"score_spread":0.2516701961914905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948450036","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.402312,0.000049303613,0.0036433162,0.0051937983,0.00014849452,0.0005484409,0.0000076644565,0.00005779685,0.58803916],"genre_scores_gemma":[0.97599274,0.000054723623,0.006676655,0.000037524493,0.0000971698,1.6648902e-7,0.0000027077886,0.0000032205494,0.017135069],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9995563,0.000025490352,0.000033982953,0.000113333095,0.00016620627,0.00010466558],"domain_scores_gemma":[0.99955326,0.00009428357,0.0000363436,0.00004724433,0.00022690401,0.000041956595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018345073,0.000038932492,0.00006606896,0.000045903547,0.0004926104,0.000014595713,0.00009629563,0.000039889823,0.0002373008],"category_scores_gemma":[0.00003722549,0.000045280176,0.0000335214,0.00006830451,0.00048808148,0.000120852295,0.000030201121,0.000032223077,0.00001122486],"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":[0.00021439286,0.0001544838,0.025971271,0.000021881735,0.000101527185,0.0000018235871,0.51054066,4.885173e-7,0.00036841573,0.43204162,0.025308618,0.0052748267],"study_design_scores_gemma":[0.0019627386,0.00048354545,0.090009086,0.00004896197,0.000088313376,2.2569196e-7,0.67628837,0.0002734121,0.00009665888,0.002953249,0.22753887,0.0002565616],"about_ca_topic_score_codex":0.00055993634,"about_ca_topic_score_gemma":0.00054603827,"teacher_disagreement_score":0.57368076,"about_ca_system_score_codex":0.00004792617,"about_ca_system_score_gemma":0.00005896621,"threshold_uncertainty_score":0.37888104},"labels":[],"label_agreement":null},{"id":"W2952420433","doi":"10.21083/ajote.v7i3.4325","title":"FORMATIVE ASSESSMENT PRACTICES AMONG DISTANCE EDUCATION TUTORS IN GHANA","year":2018,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; TUTOR; Knowledge survey; Medical education; Data collection; Test (biology); Psychology; Mathematics education; Medicine; Summative assessment; Statistics; Mathematics","score_opus":0.028596621851778078,"score_gpt":0.41710532518256394,"score_spread":0.38850870333078585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952420433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8531324,0.00015606848,0.0002635054,0.0034195099,0.0017875603,0.00017912495,3.1490777e-7,0.000008093388,0.14105336],"genre_scores_gemma":[0.99329424,0.00003675141,0.0026417337,0.00008147029,0.0014743488,0.000015802181,0.0000020369216,0.0000074156205,0.0024461988],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984539,0.0003689482,0.00038925465,0.0001117806,0.00048317297,0.00019295096],"domain_scores_gemma":[0.99776,0.00010313333,0.0014482546,0.00010519429,0.00046902502,0.00011439205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016558537,0.0000898314,0.00014584835,0.00022924213,0.00021328642,0.00014175162,0.00030779414,0.000051607894,0.00024342566],"category_scores_gemma":[0.00040959855,0.000081847524,0.000052724386,0.0005135393,0.000216052,0.0015416318,0.000017153816,0.00024019933,0.000011029641],"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":[0.000023407494,0.0011722605,0.7922576,0.0000066218195,0.000025628127,3.755004e-7,0.15888044,3.764477e-7,0.000046523284,0.009084935,0.008943081,0.029558733],"study_design_scores_gemma":[0.00012689292,0.00010234268,0.5640744,0.00007102853,0.000027370248,0.0000010965495,0.4014626,0.000007815597,0.000015904841,0.00089084374,0.033126168,0.00009352871],"about_ca_topic_score_codex":0.0012228634,"about_ca_topic_score_gemma":0.001480729,"teacher_disagreement_score":0.24258217,"about_ca_system_score_codex":0.00072035956,"about_ca_system_score_gemma":0.0026818393,"threshold_uncertainty_score":0.47574678},"labels":[],"label_agreement":null},{"id":"W2954027589","doi":"10.7202/1071418ar","title":"Beyond the Competencies Agenda in Large-Scale International Assessments: A Confucian Alternative","year":2020,"lang":"en","type":"article","venue":"Philosophical Inquiry in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Judgement; Rationality; Sociology; Epistemology; Social psychology; Psychology; Pedagogy","score_opus":0.11006403246162254,"score_gpt":0.42963915418185183,"score_spread":0.3195751217202293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954027589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5308855,0.00012982346,0.00017404211,0.3858831,0.0035042833,0.0005738567,0.0000116672945,0.000042345833,0.078795396],"genre_scores_gemma":[0.98737365,0.000143965,0.00029681722,0.009162258,0.0027793539,0.00009572952,0.000044285436,0.000009358308,0.000094586314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982454,0.00029858894,0.00032205618,0.00029963048,0.00056191575,0.00027236989],"domain_scores_gemma":[0.99938315,0.00018698497,0.00011393544,0.000117921154,0.00011054562,0.00008743355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006123713,0.00012064,0.00015778013,0.000106666965,0.00018097986,0.00012864683,0.0006078343,0.00008484905,0.0003704174],"category_scores_gemma":[0.00021277284,0.000104942425,0.00005304721,0.0005270276,0.00031398746,0.00040571904,0.00011368763,0.00035163166,0.00007014832],"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":[0.0000666026,0.001146568,0.21700005,0.000011302435,0.0000412503,0.000006926087,0.319742,0.000037919326,0.00016477305,0.45568335,0.0027154842,0.0033837731],"study_design_scores_gemma":[0.0016314293,0.00013461453,0.28958026,0.00008560399,0.000027539241,0.0000010309454,0.3018492,0.0023931267,0.0000406322,0.34171292,0.06201932,0.0005243463],"about_ca_topic_score_codex":0.00039434587,"about_ca_topic_score_gemma":0.0011545107,"teacher_disagreement_score":0.45648816,"about_ca_system_score_codex":0.00027092724,"about_ca_system_score_gemma":0.0003387359,"threshold_uncertainty_score":0.42794278},"labels":[],"label_agreement":null},{"id":"W2954748270","doi":"10.1117/12.2523795","title":"Error detection tasks and peer feedback for engaging physics students","year":2019,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dawson College; John Abbott College; Vanier College","funders":"","keywords":"Peer instruction; Peer feedback; Asynchronous communication; Computer science; Class (philosophy); Peer-to-peer; Error detection and correction; Control (management); Peer assessment; Mathematics education; Multimedia; World Wide Web; Artificial intelligence; Algorithm; Psychology","score_opus":0.03869756151750285,"score_gpt":0.37844820519967604,"score_spread":0.33975064368217317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954748270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.954096,0.000015596414,0.0014831609,0.0004981295,0.00063273945,0.000648328,0.0000020785462,0.00007387748,0.042550072],"genre_scores_gemma":[0.96811604,0.000011936601,0.0004102994,0.00013428406,0.00028927036,0.000020742424,0.0000031902803,0.00000908362,0.031005144],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989739,0.000045132572,0.00009206511,0.00018611447,0.00047811767,0.00022465954],"domain_scores_gemma":[0.9996075,0.00012129009,0.000042194486,0.000079258854,0.00009488878,0.000054870765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063004345,0.00007795683,0.00010386604,0.000022784303,0.00039676606,0.00017802844,0.00015211849,0.000057536843,0.00017574424],"category_scores_gemma":[0.000038777816,0.00007186828,0.00003891084,0.000102237565,0.00004654264,0.00024808207,0.00005357005,0.00007995331,0.000093023904],"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":[0.000069255446,0.00020963454,0.8815922,0.000043626595,0.00012775828,4.924092e-7,0.04438057,0.000008447864,0.0040962845,0.01646507,0.003921703,0.049084965],"study_design_scores_gemma":[0.005728539,0.00040536837,0.494095,0.000046152174,0.0001526767,6.1559393e-7,0.18955529,0.0013938869,0.0023526773,0.005869951,0.29933873,0.0010611098],"about_ca_topic_score_codex":0.0003024302,"about_ca_topic_score_gemma":0.00041674843,"teacher_disagreement_score":0.3874972,"about_ca_system_score_codex":0.000044547036,"about_ca_system_score_gemma":0.000020798278,"threshold_uncertainty_score":0.30516437},"labels":[],"label_agreement":null},{"id":"W2956152746","doi":"10.1109/icse-companion.2019.00103","title":"Comparing the Popularity of Testing Careers Among Canadian, Chinese, and Indian Students","year":2019,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Popularity; Dimension (graph theory); Relevance (law); Vitality; Human Dimension; Software; Process (computing); Focus (optics)","score_opus":0.03566238364825517,"score_gpt":0.3338372350683909,"score_spread":0.2981748514201357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956152746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85216826,0.000017239237,3.6760147e-7,0.00014713837,0.00015485482,0.00021968894,7.8000494e-7,0.000012527013,0.14727916],"genre_scores_gemma":[0.9978193,0.000003216764,0.000057497826,0.000060960774,0.000040383005,0.0000021759695,0.0000011727199,0.000003598079,0.002011666],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991599,0.000053383726,0.000107993874,0.000108781955,0.0003543628,0.0002155887],"domain_scores_gemma":[0.9995896,0.00010158247,0.000050481714,0.000098114295,0.000050778424,0.00010944031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055532757,0.00006130908,0.00011713155,0.000050095852,0.00031148904,0.00010544751,0.00033423986,0.000039202525,0.00008724759],"category_scores_gemma":[0.000088897155,0.00004222789,0.000019914885,0.00027285924,0.00012520952,0.00012204986,0.00008029212,0.000089247245,0.000008983443],"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":[5.783709e-7,0.0000059560466,0.99053574,0.0000035526427,0.000012290284,6.5301396e-7,0.008272276,0.0000022865868,0.000007416181,0.0009992326,0.000060680515,0.00009934683],"study_design_scores_gemma":[0.00013313843,0.000009722326,0.9841462,0.000009993128,0.0000057796146,9.860194e-8,0.015348961,0.000037258025,9.408772e-7,0.000086276326,0.00016379479,0.000057833422],"about_ca_topic_score_codex":0.8081418,"about_ca_topic_score_gemma":0.90895796,"teacher_disagreement_score":0.14565109,"about_ca_system_score_codex":0.000056207213,"about_ca_system_score_gemma":0.00008810005,"threshold_uncertainty_score":0.23957533},"labels":[],"label_agreement":null},{"id":"W2967888896","doi":"10.1186/s40468-019-0089-4","title":"Critical review of validation models and practices in language testing: their limitations and future directions for validation research","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Empirical research; Construct (python library); Computer science; Test (biology); Construct validity; Language assessment; Management science; Psychology; Data science; Psychometrics; Statistics; Mathematics education; Mathematics; Engineering","score_opus":0.2871225134574545,"score_gpt":0.4973541369068704,"score_spread":0.21023162344941593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967888896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.950391,0.009614783,0.00003289545,0.002890097,0.00010103495,0.001037774,0.000009458484,0.000048318663,0.03587464],"genre_scores_gemma":[0.9844843,0.0015227272,0.013568017,0.000038328777,0.0001552732,0.000075397926,0.000017753071,0.000010020223,0.00012819465],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9987629,0.00036362562,0.00022249893,0.00020510083,0.00024614038,0.00019975062],"domain_scores_gemma":[0.99349976,0.005968047,0.00013593823,0.000104951585,0.00025460002,0.00003669989],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002735364,0.00006949196,0.00015020077,0.00015270262,0.00014998179,0.00008018706,0.00009263175,0.00006174558,0.000016054904],"category_scores_gemma":[0.014158816,0.00006526084,0.000014802052,0.0007933145,0.00008805448,0.000451443,0.00003817369,0.00016850777,0.0000014042854],"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":[0.000036281377,0.0004542522,0.53744376,0.004326604,0.000026933509,0.000010915036,0.2725309,0.000040472558,0.011377798,0.036784515,0.00024397805,0.13672356],"study_design_scores_gemma":[0.0019713482,0.00061807537,0.34270382,0.010848637,0.00012502685,0.0000138945525,0.61326945,0.012570039,0.0007303106,0.012769178,0.0035913961,0.0007888534],"about_ca_topic_score_codex":0.0011627866,"about_ca_topic_score_gemma":0.0006360557,"teacher_disagreement_score":0.3407385,"about_ca_system_score_codex":0.000042271826,"about_ca_system_score_gemma":0.00008187256,"threshold_uncertainty_score":0.99414533},"labels":[],"label_agreement":null},{"id":"W2969685073","doi":"10.3389/feduc.2019.00094","title":"Toward a Differential and Situated View of Assessment Literacy: Studying Teachers' Responses to Classroom Assessment Scenarios","year":2019,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Situated; Literacy; Mathematics education; Situated learning; Computer science; Pedagogy; Psychology; Artificial intelligence","score_opus":0.022140024713449183,"score_gpt":0.3697810083821209,"score_spread":0.34764098366867174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969685073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870349,0.0003215472,0.0021354316,0.0016629058,0.0029892689,0.0011672926,0.0000033068181,0.000028524759,0.004656816],"genre_scores_gemma":[0.9763545,0.00023341275,0.020731151,0.00012340903,0.00013140225,0.00008904002,0.00001695435,0.000013177546,0.002306975],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99802816,0.00045883126,0.00035828757,0.00034618544,0.00051626656,0.00029226168],"domain_scores_gemma":[0.9992854,0.000107862295,0.00015741003,0.00020235572,0.00012996198,0.0001169994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008456378,0.00015119385,0.00032298383,0.00033456503,0.00013330841,0.000155644,0.00025156527,0.00009429689,0.0001653117],"category_scores_gemma":[0.00007530934,0.00015391003,0.000049914353,0.00046681392,0.00006737048,0.00034728795,0.00008847609,0.00019005725,0.0000064502583],"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":[0.000041655247,0.0004596355,0.8788901,0.000035598947,0.000038088503,3.4531533e-7,0.060046297,0.0000032323956,0.0005084018,0.0007085612,0.0025160369,0.05675206],"study_design_scores_gemma":[0.00056821026,0.00012786714,0.9024902,0.0001778337,0.000037258236,1.7401537e-7,0.08337785,0.00017748585,0.000015195803,0.0003907402,0.012437935,0.00019927054],"about_ca_topic_score_codex":0.00063835864,"about_ca_topic_score_gemma":0.00009384073,"teacher_disagreement_score":0.05655279,"about_ca_system_score_codex":0.00057358237,"about_ca_system_score_gemma":0.00086318405,"threshold_uncertainty_score":0.6276269},"labels":[],"label_agreement":null},{"id":"W2969964033","doi":"10.1111/jedm.12237","title":"Students’ Interpretation of Formative Assessment Feedback: Three Claims for Why We Know So Little About Something So Important","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Formative assessment; Psychology; Interpretation (philosophy); Cognition; Process (computing); Mathematics education; Cognitive psychology; Computer science","score_opus":0.044221159940934986,"score_gpt":0.39151100053294274,"score_spread":0.34728984059200774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969964033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9360783,0.0067325425,0.014125541,0.027093908,0.008364882,0.0024449886,0.000024592106,0.000015847274,0.005119411],"genre_scores_gemma":[0.9927164,0.00072107575,0.0052983733,0.0002120163,0.0006573194,0.000039359304,0.000006514173,0.00001551615,0.00033344916],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995474,0.00018204474,0.0010955654,0.00017208298,0.0027525565,0.0003237982],"domain_scores_gemma":[0.9954891,0.00049658655,0.0015499049,0.00014562544,0.002182166,0.00013659838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006115943,0.00016812203,0.0003868715,0.0002487875,0.00035502797,0.00024666876,0.00058276416,0.000083225284,0.00047003577],"category_scores_gemma":[0.0003544473,0.00014496256,0.0002924267,0.00023925099,0.00012716316,0.00074226316,0.000051178788,0.00025173597,0.000012464458],"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":[0.00038483154,0.0024203812,0.8234078,0.00026763466,0.0013194875,4.4633467e-7,0.08745815,0.0001834305,0.0034496535,0.053318474,0.0107387435,0.017050952],"study_design_scores_gemma":[0.0039618216,0.0013857619,0.79987043,0.0021540083,0.00044136558,0.000004275848,0.069364354,0.00044309924,0.00046831495,0.057516523,0.06378975,0.00060032064],"about_ca_topic_score_codex":0.00010877219,"about_ca_topic_score_gemma":0.00047482378,"teacher_disagreement_score":0.056638088,"about_ca_system_score_codex":0.0010706723,"about_ca_system_score_gemma":0.0028485027,"threshold_uncertainty_score":0.59114015},"labels":[],"label_agreement":null},{"id":"W2970699927","doi":"10.5539/ells.v9n3p20","title":"Investigating Chinese EFL College Students’ Writing Through the Web-Automatic Writing Evaluation Program","year":2019,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Sichuan University","keywords":"Spelling; Punctuation; Grammar; Vocabulary; Mathematics education; Computer science; Psychology; Linguistics; Artificial intelligence","score_opus":0.019044630644175522,"score_gpt":0.38818521807161305,"score_spread":0.36914058742743755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970699927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9494536,0.019480975,2.5360038e-7,0.0006080245,0.000623303,0.0013932914,0.000010782147,0.00022108911,0.02820867],"genre_scores_gemma":[0.9960409,0.00040233298,0.00065404776,0.0002528377,0.0014911566,0.00018993893,0.000021579048,0.000016467196,0.0009307768],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9975653,0.00047664205,0.00031613954,0.00031812544,0.0009529597,0.0003708199],"domain_scores_gemma":[0.99855006,0.0006352394,0.00016045834,0.00018827905,0.00041618172,0.00004979109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002211988,0.00021660521,0.00029502975,0.000049030397,0.0010562349,0.0007207995,0.00029184698,0.00009140849,0.0000686118],"category_scores_gemma":[0.0015754781,0.0001403258,0.00007359928,0.00069738453,0.00022293067,0.0006024047,0.00020851704,0.00032013998,0.0000067577857],"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":[0.0000018380156,0.000051903622,0.13057448,0.000092702445,0.0001380564,0.000007151476,0.8619964,0.0000012075948,0.000038058053,0.0021482504,0.0007919107,0.0041580475],"study_design_scores_gemma":[0.0008176658,0.00006143534,0.02404552,0.0005662928,0.00007409414,0.0000012764327,0.9704884,0.00021935011,0.0000036877468,0.00043742958,0.0030544067,0.00023039088],"about_ca_topic_score_codex":0.00003489302,"about_ca_topic_score_gemma":0.00015329178,"teacher_disagreement_score":0.108492054,"about_ca_system_score_codex":0.00006268739,"about_ca_system_score_gemma":0.00005387596,"threshold_uncertainty_score":0.8123812},"labels":[],"label_agreement":null},{"id":"W2975545495","doi":"10.1080/10627197.2019.1670056","title":"Toward a Teacher Professional Learning Continuum in Assessment for Learning","year":2019,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Council of Ministers of Education; Queen's University","funders":"","keywords":"Mathematics education; Assessment for learning; Professional learning community; Psychology; Pedagogy; Professional development; Observational study; Empirical research; Epistemology; Mathematics; Formative assessment","score_opus":0.033801063854011035,"score_gpt":0.43057365010553394,"score_spread":0.3967725862515229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975545495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83547693,0.000058661895,0.00045763026,0.018468117,0.0028286995,0.0016423712,0.000002691561,0.00007515764,0.14098972],"genre_scores_gemma":[0.8476893,0.000019263365,0.005641949,0.00014044659,0.0007247759,0.0005816449,0.0001116243,0.00002275537,0.14506827],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99729943,0.00043838358,0.00039125362,0.00045187867,0.0008761868,0.00054285146],"domain_scores_gemma":[0.99834937,0.0009686424,0.00022376892,0.00011738212,0.00021499665,0.00012581694],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002017099,0.00019121182,0.00027583062,0.00017470724,0.00048381256,0.0001692837,0.00031987153,0.00012705219,0.0044025443],"category_scores_gemma":[0.00021771154,0.00019169555,0.00012447628,0.00030598967,0.000073664574,0.00034845097,0.000086103166,0.0006095305,0.0001070032],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024334431,0.0005829385,0.9368763,0.000028583208,0.00003735599,6.2963244e-7,0.0059503103,0.000104370214,0.0003577297,0.05041696,0.0044079786,0.0012125055],"study_design_scores_gemma":[0.001005154,0.000109012835,0.8243383,0.00007458145,0.000013776539,4.4814743e-7,0.027664308,0.00068127,0.000004558175,0.002396688,0.14344212,0.00026978386],"about_ca_topic_score_codex":0.0002991836,"about_ca_topic_score_gemma":0.00025432918,"teacher_disagreement_score":0.13903415,"about_ca_system_score_codex":0.00086897146,"about_ca_system_score_gemma":0.0021794639,"threshold_uncertainty_score":0.9965076},"labels":[],"label_agreement":null},{"id":"W2975877382","doi":"10.1080/0142159x.2019.1656804","title":"Meaningful feedback through a sociocultural lens","year":2019,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Sociocultural evolution; Set (abstract data type); Psychology; Sociocultural perspective; Perspective (graphical); Politeness; Pedagogy; Mathematics education; Sociology; Computer science; Political science","score_opus":0.04063133680797009,"score_gpt":0.3572131293742551,"score_spread":0.316581792566285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975877382","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4794547,0.000093016795,0.000019071736,0.009072496,0.0006142143,0.0001575784,2.5422753e-7,0.00010828736,0.5104804],"genre_scores_gemma":[0.8766846,0.00009930435,0.0001372582,0.00092897326,0.0009997581,0.000009387801,0.000004925351,0.000012988007,0.12112278],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750423,0.00020274383,0.00018010632,0.00025400205,0.0014057007,0.00045324056],"domain_scores_gemma":[0.99953264,0.000060461007,0.000053760465,0.00015061143,0.00004721411,0.00015530195],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00089911616,0.000121889745,0.00019989575,0.000015960732,0.00023865538,0.00006752821,0.00044195508,0.00024161344,0.051965147],"category_scores_gemma":[0.0002948303,0.00009424688,0.000120463075,0.00017746346,0.0002899565,0.00030965128,0.00009345505,0.00038121187,0.003808115],"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":[0.000018651263,0.00025664078,0.6969361,0.000014145772,0.00010711739,0.000016777845,0.12090965,2.8403898e-7,0.000045337518,0.05742071,0.1202895,0.003985092],"study_design_scores_gemma":[0.0010334088,0.000043274777,0.01863635,0.000045227385,0.000023335606,0.0000011735573,0.031102816,0.000077421035,0.0000051709503,0.0012766881,0.94745845,0.0002967173],"about_ca_topic_score_codex":0.00064940006,"about_ca_topic_score_gemma":0.0002537036,"teacher_disagreement_score":0.82716894,"about_ca_system_score_codex":0.00011202231,"about_ca_system_score_gemma":0.0001608898,"threshold_uncertainty_score":0.99696755},"labels":[],"label_agreement":null},{"id":"W2979056522","doi":"10.18806/tesl.v36i1.1308","title":"Sitting at 6.5: Problematizing IELTS and Admissions to Canadian Universities","year":2019,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"University of British Columbia; University of Prince Edward Island; University of Ontario Institute of Technology; University of Northern British Columbia","keywords":"Humanities; Psychology; Curriculum; Library science; Pedagogy; Philosophy; Computer science","score_opus":0.011861015996786954,"score_gpt":0.27159693781048505,"score_spread":0.2597359218136981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979056522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9294868,0.0006463023,0.0000016952432,0.014351828,0.00043870037,0.0001564329,0.000005216121,0.000010115212,0.05490289],"genre_scores_gemma":[0.9751519,0.0000175959,0.00026222764,0.009518809,0.00015366828,5.279044e-7,7.3727557e-7,0.000006205919,0.014888348],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999051,0.000047118134,0.00010054406,0.00008926805,0.00036197118,0.00035010936],"domain_scores_gemma":[0.9988168,0.00007661171,0.000052273594,0.00004834088,0.000080172926,0.0009258269],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032695098,0.000062690524,0.00009083074,0.000090401074,0.0012362396,0.00011740097,0.00015081278,0.000029310972,0.013029844],"category_scores_gemma":[0.00006352276,0.00006095217,0.000016904005,0.00014090017,0.000016883905,0.00014025233,0.00004419064,0.0001224665,0.0000122776755],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028258211,0.000015403515,0.16397506,0.000040042243,0.00012989702,0.00034896412,0.115563266,0.00012187949,0.000882873,0.01327749,0.702761,0.002855887],"study_design_scores_gemma":[0.00029536543,0.000038265087,0.030767862,0.000121523735,0.000018444214,0.000026107733,0.15845425,0.00003149035,0.000014598849,0.00013379197,0.80986005,0.00023824027],"about_ca_topic_score_codex":0.95154876,"about_ca_topic_score_gemma":0.99479574,"teacher_disagreement_score":0.13320719,"about_ca_system_score_codex":0.0018763149,"about_ca_system_score_gemma":0.006506734,"threshold_uncertainty_score":0.9991255},"labels":[],"label_agreement":null},{"id":"W2979335464","doi":"10.31468/cjsdwr.737","title":"Reflecting on Assessment: Strategies and Tools for Measuring the Impact of a Canadian WAC Program","year":2019,"lang":"en","type":"article","venue":"Discourse and Writing/Rédactologie","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Writing assessment; Exposition (narrative); Context (archaeology); Variety (cybernetics); Process (computing); Computer science; Engineering ethics; Reflection (computer programming); Engineering management; Pedagogy; Engineering; Sociology; Artificial intelligence; History","score_opus":0.27463465058214864,"score_gpt":0.5338785316821187,"score_spread":0.2592438810999701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979335464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9302627,0.00015931219,0.0000064433716,0.0011769098,0.0000775788,0.00085219194,0.000011661163,0.0000399162,0.067413285],"genre_scores_gemma":[0.99927956,0.00017665241,0.0002528965,0.000029097264,0.00011085647,0.000056680736,0.0000071635627,0.000010272936,0.00007681958],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99882245,0.00010157246,0.00017680862,0.00022626985,0.00020499699,0.00046788176],"domain_scores_gemma":[0.99895376,0.0006166645,0.00011548048,0.00012799102,0.00007712712,0.00010898831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010022469,0.00013633953,0.00021793206,0.00012985521,0.0005494786,0.0007752758,0.0001828889,0.00008658983,0.000027848433],"category_scores_gemma":[0.00013731209,0.000090189824,0.00008818645,0.00021980668,0.00023265506,0.00060012884,0.000032725042,0.0001609445,0.0000012075603],"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":[0.000057614398,0.00017714611,0.70079285,0.00008248559,0.00024236446,0.0000064457417,0.013683418,0.000034613196,0.00083812594,0.105803445,0.00032289684,0.17795862],"study_design_scores_gemma":[0.00079669786,0.00082420546,0.6541693,0.00016057724,0.00006162364,0.0000018331283,0.34004974,0.00018291436,0.00007481148,0.0023955286,0.0009623331,0.00032040724],"about_ca_topic_score_codex":0.03708243,"about_ca_topic_score_gemma":0.029538326,"teacher_disagreement_score":0.32636634,"about_ca_system_score_codex":0.00008796693,"about_ca_system_score_gemma":0.00056924106,"threshold_uncertainty_score":0.9881701},"labels":[],"label_agreement":null},{"id":"W2980323187","doi":"10.26855/er.2018.09.002","title":"A Brief Review of Washback Studies in the South Asian Countries","year":2018,"lang":"en","type":"review","venue":"The Educational Review USA","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"South asia; Sri lanka; Test (biology); Political science; Psychology; Sociology; Ecology","score_opus":0.20937722329914993,"score_gpt":0.5278685289246098,"score_spread":0.31849130562545985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980323187","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.1988113e-7,0.9480491,1.7104024e-7,0.019011997,0.0007645629,0.002818268,0.000025787871,0.0000058219016,0.029323852],"genre_scores_gemma":[0.0000012906806,0.989982,0.00003701067,0.004058764,0.0014362275,0.0006981911,0.00004851045,0.00001656379,0.0037214535],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949545,0.0020947412,0.0011347755,0.0003211307,0.0011701941,0.0003246067],"domain_scores_gemma":[0.9957864,0.0019606159,0.0010921234,0.0006619802,0.00045224602,0.000046622634],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00812409,0.00033229208,0.0017658666,0.000065917,0.00040770238,0.000050022165,0.0018320825,0.00008794816,0.0016529346],"category_scores_gemma":[0.0026280626,0.00016195016,0.0005699954,0.001212393,0.0011892768,0.000106566,0.00012436206,0.00031990168,0.0007898417],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.770181e-7,0.00009709652,0.00006511398,0.37320364,0.00024883766,5.8253084e-7,0.013075318,1.7796328e-9,4.9508025e-10,0.048484176,0.46629518,0.098529175],"study_design_scores_gemma":[0.000019231682,0.000008909049,0.000043286487,0.30070886,0.000749342,0.0000026370653,0.0013238081,2.539959e-9,1.1262119e-9,0.00034707948,0.6966747,0.00012213117],"about_ca_topic_score_codex":0.00007753969,"about_ca_topic_score_gemma":0.00018744773,"teacher_disagreement_score":0.23037954,"about_ca_system_score_codex":0.00021274654,"about_ca_system_score_gemma":0.002434217,"threshold_uncertainty_score":0.99998814},"labels":[],"label_agreement":null},{"id":"W2980647847","doi":"10.4102/sajce.v9i1.739","title":"Formative assessment as ‘formative pedagogy’ in Grade 3 mathematics","year":2019,"lang":"en","type":"article","venue":"South African Journal of Childhood Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"University of Johannesburg; National Research Foundation","keywords":"Formative assessment; Mathematics education; Curriculum; Pedagogy; Psychology; Focus group; Sociology","score_opus":0.014615595148406657,"score_gpt":0.36736591523537826,"score_spread":0.3527503200869716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980647847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90980846,0.00007979743,0.00011742976,0.001877155,0.0010154914,0.00039132262,0.0000025537508,0.000010990054,0.08669681],"genre_scores_gemma":[0.99664384,0.00004097655,0.0022910733,0.00013875011,0.00032380183,0.000008373514,0.0000037815016,0.000011243885,0.00053815637],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9980681,0.00019640576,0.0005915262,0.00010420086,0.00074940943,0.0002903636],"domain_scores_gemma":[0.99841607,0.00013448899,0.0009007857,0.00012858046,0.0002660925,0.00015400187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012310193,0.00013602326,0.00029845315,0.00034604024,0.00015337218,0.0001158819,0.00036841494,0.00006685675,0.00035464286],"category_scores_gemma":[0.00012960081,0.00011791046,0.00011965853,0.0005059672,0.00007515489,0.0008420314,0.000030323266,0.0003523555,0.00011668163],"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":[0.000008112598,0.00084994524,0.049289074,0.000013016474,0.00004470669,6.680909e-7,0.93471867,0.000015200503,0.000012775964,0.012960481,0.00036251804,0.001724851],"study_design_scores_gemma":[0.00059399527,0.00020470282,0.20751254,0.00012918712,0.000031675805,0.0000055815794,0.77940315,0.000009880778,0.000018576817,0.010446396,0.0014985338,0.00014580593],"about_ca_topic_score_codex":0.0000617709,"about_ca_topic_score_gemma":0.00003129842,"teacher_disagreement_score":0.15822347,"about_ca_system_score_codex":0.0003702974,"about_ca_system_score_gemma":0.0027249972,"threshold_uncertainty_score":0.48340282},"labels":[],"label_agreement":null},{"id":"W2980773015","doi":"10.4018/978-1-7998-0323-2.ch017","title":"Assessment in 21st Century Learning","year":2019,"lang":"en","type":"book-chapter","venue":"Advances in early childhood and K-12 education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Formative assessment; Situated; Improvisation; Narrative; Divergence (linguistics); Pedagogy; Situated learning; Assessment for learning; Space (punctuation); Curriculum; Literacy; Mathematics education; Sociology; Psychology; Computer science; Visual arts; Art; Artificial intelligence","score_opus":0.007753887984675155,"score_gpt":0.30720618080539824,"score_spread":0.2994522928207231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980773015","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018697131,0.010030544,0.0000026762023,0.00030222244,0.0017766549,0.0006154242,0.000002677982,0.000031504725,0.96854115],"genre_scores_gemma":[0.74689126,0.085439436,0.00036915694,0.00014114272,0.0008936757,0.000033384455,0.00008439147,0.00004212811,0.16610545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99847394,0.00007103917,0.0003181319,0.00043492686,0.00040380677,0.0002981322],"domain_scores_gemma":[0.99936914,0.00012465866,0.00023828034,0.00014847687,0.0000454217,0.00007403382],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032426644,0.0002297967,0.00030524784,0.0002770686,0.00017465031,0.0001205733,0.00020540135,0.00023719935,0.00018803895],"category_scores_gemma":[0.00003263048,0.00024772668,0.000056652145,0.00008340949,0.000110897694,0.000665647,0.00005714947,0.00069952424,0.00004422912],"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":[0.000005984091,0.00023521305,0.27531415,0.000040354953,0.000018647082,0.0000014494505,0.03262943,0.000014609179,0.0000026598009,0.49257308,0.0000645848,0.19909985],"study_design_scores_gemma":[0.0003318427,0.00006692411,0.5326282,0.00043561132,0.00001572864,3.666556e-7,0.011297492,8.6046293e-7,2.0180929e-7,0.010356186,0.4445412,0.00032541066],"about_ca_topic_score_codex":0.00037561738,"about_ca_topic_score_gemma":0.0020104253,"teacher_disagreement_score":0.8024357,"about_ca_system_score_codex":0.00025971798,"about_ca_system_score_gemma":0.0008742792,"threshold_uncertainty_score":0.9999975},"labels":[],"label_agreement":null},{"id":"W2981392404","doi":"10.5539/elt.v12n11p64","title":"Using Self-Assessment as a Tool for English Language Learning","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Putra Malaysia","keywords":"Formative assessment; Psychology; Learner autonomy; Context (archaeology); Self-assessment; Mathematics education; Language acquisition; Autonomy; Quality (philosophy); Class (philosophy); Pedagogy; Language education; Comprehension approach; Computer science; Artificial intelligence","score_opus":0.013233138124479972,"score_gpt":0.3512337609470111,"score_spread":0.3380006228225311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981392404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8676048,0.00017022328,0.0005022601,0.00003545485,0.0015285311,0.0008661276,0.0000050763297,0.00079028425,0.12849723],"genre_scores_gemma":[0.9761477,0.000010155461,0.0146442875,0.00013765342,0.0028211263,0.000042467862,0.00003569276,0.00005959177,0.0061013247],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99728984,0.0005170329,0.00030902273,0.000476287,0.0006821161,0.00072569074],"domain_scores_gemma":[0.9986763,0.00060077064,0.00018809098,0.00029638555,0.00011054584,0.00012791876],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027911246,0.00025270905,0.00033584927,0.00014280406,0.0008715304,0.00048162538,0.0004722178,0.00017271032,0.0006612261],"category_scores_gemma":[0.001155643,0.0002620139,0.00020386462,0.00020369484,0.000038981587,0.00069764204,0.00014649105,0.0007518224,0.000045800312],"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":[0.000015434054,0.000112757276,0.05937639,0.00004154466,0.000082628176,0.000014636289,0.9232593,0.00008361122,0.0024156466,0.010503418,0.00016278532,0.0039318423],"study_design_scores_gemma":[0.00146181,0.00012051648,0.000867873,0.00008829718,0.000087249486,8.1007e-7,0.9544178,0.0010573933,0.00014484761,0.00004973272,0.0411321,0.00057152513],"about_ca_topic_score_codex":0.0012791244,"about_ca_topic_score_gemma":0.00012491722,"teacher_disagreement_score":0.12239591,"about_ca_system_score_codex":0.00046868532,"about_ca_system_score_gemma":0.00024611256,"threshold_uncertainty_score":0.9999832},"labels":[],"label_agreement":null},{"id":"W2984367764","doi":"10.1186/s40468-019-0094-7","title":"Assessing peer review pattern and the effect of face-to-face and mobile-mediated modes on students’ academic writing development","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Academic writing; English for academic purposes; Peer feedback; Mathematics education; Cohesion (chemistry); Task (project management); Second language writing; Face-to-face; Pedagogy; Medical education; Second language; Linguistics","score_opus":0.032727561803754454,"score_gpt":0.399730670787874,"score_spread":0.36700310898411953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984367764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99303335,0.0023340744,0.000014764151,0.00044698076,0.000044238364,0.0011273244,9.702906e-7,0.000039087376,0.0029592016],"genre_scores_gemma":[0.9989048,0.0001295381,0.00032683447,0.00026416642,0.000031595413,0.000056979887,0.0000034838026,0.000011295057,0.00027125416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99813914,0.00037688072,0.0002883372,0.00022866015,0.0007193938,0.0002475729],"domain_scores_gemma":[0.99759084,0.0020567053,0.00014607051,0.00010690558,0.000045999997,0.00005349484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038383983,0.00013309157,0.00031031328,0.00005554549,0.00013310908,0.00010719962,0.00026734453,0.00006301434,0.000016861648],"category_scores_gemma":[0.0017384096,0.000091775204,0.000019420713,0.00029218005,0.00008494952,0.00015200183,0.00016369967,0.00026788193,0.000014405986],"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":[0.000008676761,0.00000994297,0.9367851,0.00024859465,0.000011661529,0.000003662041,0.027149228,0.000014975339,0.00055784825,0.000012797935,0.000018707411,0.035178784],"study_design_scores_gemma":[0.002465648,0.00016451847,0.93659735,0.007880027,0.000053733587,0.0000022617469,0.05132966,0.00053923094,0.00032918458,0.000006138485,0.0002789835,0.00035327795],"about_ca_topic_score_codex":0.0002210361,"about_ca_topic_score_gemma":0.00003098051,"teacher_disagreement_score":0.034825508,"about_ca_system_score_codex":0.000051644503,"about_ca_system_score_gemma":0.000030024641,"threshold_uncertainty_score":0.37424842},"labels":[],"label_agreement":null},{"id":"W2989650653","doi":"10.5539/elt.v12n12p132","title":"The Reality of Continuous Assessment Strategies on Saudi Students&amp;#39; Performance at University Level","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Continuous assessment; Medical education; Sample (material); Mathematics education; Medicine","score_opus":0.02738941493298204,"score_gpt":0.3477198042507374,"score_spread":0.32033038931775537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989650653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7692237,0.000035445788,0.000024038745,0.00010748312,0.00043644253,0.00024780285,0.000009557098,0.00007110892,0.22984444],"genre_scores_gemma":[0.97577477,0.00006675418,0.00015628888,0.000030093252,0.00019963189,0.0000015556893,0.000011538785,0.000009320411,0.023750069],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9979585,0.0005052855,0.00017865693,0.00022446619,0.0008111649,0.0003219235],"domain_scores_gemma":[0.998927,0.0004648669,0.00017774475,0.00031052754,0.00006179825,0.000058045618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00236167,0.00012781983,0.00019684834,0.00004329341,0.00091921614,0.00016186101,0.00069953356,0.000071097,0.00016313816],"category_scores_gemma":[0.00013283794,0.000102193735,0.00008260965,0.00011515632,0.00014270298,0.0003295833,0.00021509465,0.00037592868,0.000029266228],"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":[0.00009198749,0.00024456132,0.49818468,0.00003312516,0.00011543742,0.000005882546,0.4448194,0.000058692814,0.0009836791,0.049066495,0.0011545813,0.0052414923],"study_design_scores_gemma":[0.00076987577,0.00012018481,0.27843547,0.000066269684,0.000028842083,1.6927731e-7,0.6537547,0.000014105943,0.000053856482,0.000031348354,0.06649608,0.00022908323],"about_ca_topic_score_codex":0.0020552755,"about_ca_topic_score_gemma":0.0024970076,"teacher_disagreement_score":0.2197492,"about_ca_system_score_codex":0.00034154186,"about_ca_system_score_gemma":0.00010606677,"threshold_uncertainty_score":0.706996},"labels":[],"label_agreement":null},{"id":"W2989744490","doi":"10.22329/jtl.v13i2.5971","title":"Finnish Upper Secondary School Students’ Perceptions of Their Teachers’ Assessment Practices","year":2020,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Literacy; Mathematics education; Psychology; School teachers; Medical education; Pedagogy; Medicine","score_opus":0.03752627490038453,"score_gpt":0.3973500381577403,"score_spread":0.35982376325735577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989744490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9759103,0.0002938894,0.00030831463,0.0054612136,0.00014120419,0.00007130209,6.666768e-7,0.00001926569,0.017793862],"genre_scores_gemma":[0.99409026,0.00027126746,0.0037125545,0.0002700471,0.0006174085,8.719247e-7,8.7225675e-7,0.000009755777,0.0010269852],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974131,0.0013233697,0.0003657521,0.000121683275,0.00060525525,0.0001708648],"domain_scores_gemma":[0.99818134,0.00046689544,0.0010042593,0.000049691113,0.00009792915,0.00019989803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041647707,0.00009980158,0.00025787522,0.000081538245,0.00090241473,0.00025256796,0.00031269545,0.00006630338,0.00048725077],"category_scores_gemma":[0.0016419316,0.0000811475,0.00012396339,0.00009408962,0.000087331064,0.0006347615,0.00008680471,0.0022452187,0.000004374762],"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":[0.00001580192,0.00008669993,0.8553162,0.00001166656,0.000117073236,0.0000040183004,0.12903824,0.000031742635,0.0014499791,0.00013836396,0.0013215423,0.012468624],"study_design_scores_gemma":[0.0005159648,0.00029671006,0.59301364,0.00007579403,0.00007224682,0.000004865323,0.34203342,0.000043192533,0.0000033990354,0.00002863193,0.06380997,0.000102193015],"about_ca_topic_score_codex":0.00019056736,"about_ca_topic_score_gemma":0.000013356565,"teacher_disagreement_score":0.2623026,"about_ca_system_score_codex":0.00006018977,"about_ca_system_score_gemma":0.0002235625,"threshold_uncertainty_score":0.9754483},"labels":[],"label_agreement":null},{"id":"W2990008878","doi":"10.7202/1065164ar","title":"Quel feedback les élèves du primaire en difficulté d’apprentissage reçoivent-ils dans leur bulletin scolaire ? Vers une typologie des commentaires laissés par leurs enseignants","year":2019,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.08092896404244351,"score_gpt":0.3593135500961273,"score_spread":0.27838458605368377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990008878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9403985,0.0013588766,0.00035581266,0.04345733,0.004256638,0.0015810055,0.00004212139,0.0001735563,0.008376148],"genre_scores_gemma":[0.9868232,0.0020929882,0.0008151629,0.00026983357,0.00051138276,0.00010809035,0.00040924968,0.00006127633,0.008908814],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98976576,0.0065647247,0.00075194193,0.0008233381,0.0012780309,0.00081621425],"domain_scores_gemma":[0.997239,0.0011054822,0.00060646806,0.0004669985,0.0003863055,0.00019577252],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0075681475,0.00052553567,0.0005243431,0.00013302064,0.0011510575,0.00032064033,0.0006701144,0.00048256284,0.002184162],"category_scores_gemma":[0.0007410745,0.000538546,0.0002528692,0.0007315654,0.0007235226,0.00082461117,0.00015646589,0.0004592948,0.00089759665],"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":[0.00006109259,0.00073621224,0.537382,0.00014699716,0.00016778777,0.0000037001291,0.41598567,0.00019590303,0.0018188125,0.0030125012,0.019536942,0.020952355],"study_design_scores_gemma":[0.001146157,0.00016700767,0.7632749,0.0003274553,0.00022398987,0.0000032182759,0.21992722,0.00012573494,0.00047434217,0.0007523941,0.013100302,0.00047724912],"about_ca_topic_score_codex":0.006208612,"about_ca_topic_score_gemma":0.006610276,"teacher_disagreement_score":0.22589292,"about_ca_system_score_codex":0.0017614159,"about_ca_system_score_gemma":0.0010453666,"threshold_uncertainty_score":0.9998803},"labels":[],"label_agreement":null},{"id":"W2993413569","doi":"10.5539/elt.v13n1p43","title":"Research on the Effect of Supervisor Feedback for Undergraduate Thesis Writing","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Supervisor; Peer feedback; Psychology; Focus (optics); Corrective feedback; Expression (computer science); Negative feedback; Mathematics education; Computer science; Management; Engineering","score_opus":0.03487369127801464,"score_gpt":0.39149926914608824,"score_spread":0.3566255778680736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993413569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8372434,0.00009098422,0.000012905912,0.00090721366,0.00026402724,0.00079534884,0.0000041782137,0.00006528052,0.16061668],"genre_scores_gemma":[0.99563956,0.000008475728,0.00012636112,0.000054140313,0.00067508104,0.00005120825,0.0000048985453,0.00002252353,0.0034177718],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99680185,0.0016243536,0.00017733559,0.00023289672,0.00070777035,0.00045577544],"domain_scores_gemma":[0.9911352,0.008402075,0.00006419027,0.0002847681,0.00006605878,0.000047729605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010415715,0.00011379885,0.0002027652,0.00010316544,0.0007012043,0.00015675012,0.0005475708,0.000075850294,0.00018564935],"category_scores_gemma":[0.002348225,0.00007551005,0.00013612804,0.00022349878,0.00011261042,0.00015345379,0.00008597794,0.0005053215,0.000049893148],"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":[0.00019262827,0.00010858405,0.080374844,0.00017807749,0.00014367417,0.0000037295108,0.7040096,0.00003103499,0.004087352,0.18048836,0.003929015,0.026453082],"study_design_scores_gemma":[0.0013141583,0.0006995189,0.002254282,0.00027859947,0.000036821777,1.2444488e-7,0.9813635,0.00014703615,0.0043225028,0.0004994709,0.008804662,0.0002793242],"about_ca_topic_score_codex":0.00077007327,"about_ca_topic_score_gemma":0.00014748292,"teacher_disagreement_score":0.27735388,"about_ca_system_score_codex":0.00008145077,"about_ca_system_score_gemma":0.00003395518,"threshold_uncertainty_score":0.5393167},"labels":[],"label_agreement":null},{"id":"W2994446456","doi":"10.47678/cjhe.v35i4.184475","title":"The Immediate Feedback Assessment Technique: A Learner-centered Multiple-choice Response Form","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Grading (engineering); Multiple choice; Computer science; Suite; Mathematics education; Psychology; Mathematics; Political science; Statistics; Engineering","score_opus":0.02670177446827649,"score_gpt":0.35239603585010404,"score_spread":0.32569426138182755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994446456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91330415,0.001440311,0.000033884822,0.05989425,0.0067292564,0.0010881305,0.000004016921,0.000021559752,0.017484441],"genre_scores_gemma":[0.96679324,0.00007077165,0.0005104382,0.00049523707,0.0009080439,0.00006952919,0.000002761009,0.000014781384,0.031135218],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983308,0.00036542918,0.0003627921,0.000113036425,0.00038206362,0.00044587953],"domain_scores_gemma":[0.9976583,0.0006873305,0.00034772887,0.00017376216,0.00054187776,0.0005909633],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012936763,0.0001138563,0.0001329657,0.00019616082,0.0008940169,0.0004781194,0.00052752555,0.00009252224,0.0010008893],"category_scores_gemma":[0.00044039657,0.00008616285,0.000098064265,0.00029825154,0.00020421323,0.0005439781,0.000012572862,0.00029110172,0.00006734245],"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":[0.00006380408,0.00011755363,0.5752545,0.0000072466555,0.00008137768,0.0000048565676,0.0087130545,0.0000016533255,0.0017714822,0.0025426433,0.39898533,0.012456517],"study_design_scores_gemma":[0.00018681251,0.000043166074,0.503448,0.000024830715,0.00001216581,0.0000021847002,0.003931172,0.0000010494422,0.000015263078,0.0006078415,0.49165452,0.000072995565],"about_ca_topic_score_codex":0.027372332,"about_ca_topic_score_gemma":0.035101376,"teacher_disagreement_score":0.09266919,"about_ca_system_score_codex":0.00092655746,"about_ca_system_score_gemma":0.005439563,"threshold_uncertainty_score":0.9999123},"labels":[],"label_agreement":null},{"id":"W2994544299","doi":"","title":"The Degree of Using Alternative Assessment Strategies by the Teachers of the First Three Grades in the Tabuk Region: Survey Study","year":2016,"lang":"en","type":"article","venue":"Canadian social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Degree (music); Sample (material); Psychology; Mathematics education; Estimation; Statistics; Medical education; Mathematics; Medicine; Management; Economics","score_opus":0.15057878264938052,"score_gpt":0.3883937566217403,"score_spread":0.2378149739723598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994544299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96688807,0.00006203665,0.000027792437,0.007377887,0.00035702597,0.00074414565,0.000016773003,0.0000039961456,0.02452227],"genre_scores_gemma":[0.99965906,0.00001905745,0.0000041340872,0.00009111508,0.000093892624,0.00001802106,1.534025e-7,0.000004233438,0.00011036015],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972612,0.000711113,0.00022975243,0.00021013065,0.0011089814,0.0004788205],"domain_scores_gemma":[0.9984776,0.0007624346,0.00023982904,0.00027551383,0.00017473991,0.00006989543],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0057653436,0.00010473816,0.0001335842,0.000046107878,0.0032947033,0.00026251836,0.0026348184,0.00004193589,0.000010343909],"category_scores_gemma":[0.0002834311,0.000041874955,0.00006122232,0.00138656,0.0047330465,0.0003129653,0.0000989999,0.00015201299,5.402766e-7],"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":[0.0000024487058,0.000029515353,0.9137488,5.896415e-7,0.000013043071,8.229332e-7,0.05840386,8.823032e-7,0.000038713777,0.024854546,0.0008263015,0.0020804955],"study_design_scores_gemma":[0.00013463502,0.00002105668,0.77757573,0.00001114496,0.00000874754,1.2865006e-7,0.21974638,0.0000057720245,0.0000062847125,0.0010538194,0.0013733406,0.00006295345],"about_ca_topic_score_codex":0.41204208,"about_ca_topic_score_gemma":0.93899244,"teacher_disagreement_score":0.52695036,"about_ca_system_score_codex":0.0006018196,"about_ca_system_score_gemma":0.0020870285,"threshold_uncertainty_score":0.9980029},"labels":[],"label_agreement":null},{"id":"W2994689616","doi":"10.1080/0969594x.2019.1703171","title":"A cross-cultural comparison of German and Canadian student teachers’ assessment competence","year":2019,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Competence (human resources); German; Multitude; Psychology; Pedagogy; Cross-cultural; Mathematics education; Sociology; Social psychology; Political science; Geography","score_opus":0.06255569384159228,"score_gpt":0.5279710097896466,"score_spread":0.46541531594805435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994689616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7798889,0.00018024468,0.0000042097245,0.007867324,0.00033490313,0.0005260509,0.0000048428756,0.000013477761,0.21118],"genre_scores_gemma":[0.9930194,0.0006239272,0.0031915335,0.00063304265,0.0001656385,0.000049875394,0.000020295407,0.000009715106,0.0022865431],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977324,0.00056857965,0.00045590193,0.00032931744,0.0005295817,0.00038420194],"domain_scores_gemma":[0.99790406,0.000999268,0.00037500684,0.00021445623,0.00024914026,0.00025807598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019209845,0.00016351284,0.00027425136,0.00026539393,0.0003588272,0.00042215647,0.00027493932,0.00010941075,0.0001577346],"category_scores_gemma":[0.00040945807,0.00016476444,0.000031550087,0.00038856355,0.00027543277,0.0013656131,0.00011148588,0.0003409048,0.00000925729],"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":[0.0000067109077,0.00032141554,0.70120466,0.000017492077,0.000026819622,4.358511e-7,0.053100564,0.00001185364,0.00008801893,0.24243604,0.000058876725,0.0027271034],"study_design_scores_gemma":[0.00032288293,0.00006349017,0.7536595,0.0000357557,0.000022937773,0.0000024671633,0.100608565,0.000053427946,0.0000043142704,0.00022270408,0.14485309,0.00015087669],"about_ca_topic_score_codex":0.20906894,"about_ca_topic_score_gemma":0.07102387,"teacher_disagreement_score":0.24221332,"about_ca_system_score_codex":0.00072936056,"about_ca_system_score_gemma":0.0037651197,"threshold_uncertainty_score":0.9459275},"labels":[],"label_agreement":null},{"id":"W2995076146","doi":"10.5539/ies.v13n1p1","title":"Not All Finns Think Alike: Varying Views of Assessment in Finland","year":2019,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Narrative; Psychology; Socioeconomic status; Pedagogy; Standardized test; Narrative inquiry; Teacher education; Medical education; Educational assessment; Mathematics education; Sociology; Medicine","score_opus":0.13217833186897876,"score_gpt":0.501713879522738,"score_spread":0.3695355476537593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995076146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7956247,0.0005921924,0.000022319075,0.0099686375,0.005477742,0.00029327805,0.0000049574824,0.000014368819,0.18800186],"genre_scores_gemma":[0.97970784,0.0007814856,0.0012338046,0.00062093465,0.00020660552,0.00004007546,0.000011438526,0.000004957631,0.017392859],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988323,0.00007945791,0.00029331518,0.00016742146,0.00049964624,0.00012786413],"domain_scores_gemma":[0.99894345,0.00025807775,0.00017023791,0.00009437627,0.0005097721,0.000024091461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058543164,0.00008009265,0.00017090993,0.00014464924,0.00006483685,0.000036690315,0.000254566,0.000035116376,0.0006650275],"category_scores_gemma":[0.00019399269,0.0000746618,0.00005112224,0.0001491994,0.00006753134,0.00023298214,0.00007550196,0.00009258381,0.00009533695],"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":[0.000017216707,0.0005363693,0.8628122,0.000028748076,0.00025785266,5.2351027e-7,0.065358944,0.000040740484,0.0004999459,0.051085692,0.015418665,0.0039430554],"study_design_scores_gemma":[0.0007682416,0.00005166616,0.60466295,0.00018413621,0.000024536097,4.105237e-7,0.068815306,0.00005741878,0.000121928824,0.0044119623,0.3206624,0.00023904022],"about_ca_topic_score_codex":0.00059747015,"about_ca_topic_score_gemma":0.00038754457,"teacher_disagreement_score":0.30524376,"about_ca_system_score_codex":0.00024013946,"about_ca_system_score_gemma":0.0003204507,"threshold_uncertainty_score":0.7281585},"labels":[],"label_agreement":null},{"id":"W2996434871","doi":"10.1515/ijnes-2019-0061","title":"A, B, or C? A Quasi-experimental Multi-site Study Investigating Three Option Multiple Choice Questions","year":2019,"lang":"en","type":"article","venue":"International Journal of Nursing Education Scholarship","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Red River College; Northwestern Polytechnic; Dalhousie University","funders":"","keywords":"Replication (statistics); Multiple choice; Psychology; Item response theory; Actuarial science; Medicine; Psychometrics; Clinical psychology; Statistics; Significant difference; Economics; Mathematics; Internal medicine","score_opus":0.15817704518269934,"score_gpt":0.5024275049395138,"score_spread":0.34425045975681445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996434871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98887646,0.00017383455,0.00033276944,0.0020620297,0.0070618754,0.0004089245,0.000003008619,0.000030931405,0.0010501659],"genre_scores_gemma":[0.99322915,0.0000110164165,0.004554426,0.0001911419,0.0011865179,0.000012406722,0.000009025308,0.000013337899,0.0007929795],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99758345,0.00033532293,0.0005122671,0.00019534625,0.0011826043,0.00019101116],"domain_scores_gemma":[0.99762475,0.00042644987,0.0005789415,0.00013028752,0.0010692414,0.0001703375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013567157,0.00012930406,0.000171811,0.00034700267,0.00029678617,0.00053273694,0.00060784427,0.000077957215,0.00026384875],"category_scores_gemma":[0.0018088116,0.00012083358,0.00010040443,0.00028239697,0.00010398718,0.0016475492,0.000030261026,0.00038708866,0.00008819555],"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":[0.00007523423,0.0056676334,0.95702463,0.0000018262975,0.00007398652,0.0000019627864,0.02735223,0.000027976486,0.0039670193,0.0007023896,0.00023646737,0.0048686243],"study_design_scores_gemma":[0.0017620957,0.0004349445,0.9392119,0.00050423737,0.000044789063,0.000021976928,0.05502181,0.00013654717,0.00014925563,0.00040136228,0.0021200413,0.00019103031],"about_ca_topic_score_codex":0.0004294093,"about_ca_topic_score_gemma":0.00052050594,"teacher_disagreement_score":0.02766958,"about_ca_system_score_codex":0.0009366362,"about_ca_system_score_gemma":0.0009495652,"threshold_uncertainty_score":0.51371944},"labels":[],"label_agreement":null},{"id":"W2997403840","doi":"10.5539/elt.v13n1p180","title":"The Washback Effect of WAEC/SSCE English Test of Orals on Teachers Methodology in Senior Secondary Schools in Sokoto Metropolis","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Test (biology); Mathematics education; Curriculum; Ranking (information retrieval); Simple random sample; Population; Medical education; Pedagogy; Computer science; Medicine","score_opus":0.018941388842862547,"score_gpt":0.36298388591822156,"score_spread":0.344042497075359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997403840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91449136,0.00036753295,0.0000039348106,0.00008920231,0.0006983462,0.00071219844,0.000010833291,0.000059399536,0.08356719],"genre_scores_gemma":[0.9975475,0.00003117158,0.0007700757,0.000049190625,0.00036291283,0.000027486776,0.000008068208,0.000027382768,0.0011762287],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99412274,0.0038768908,0.0005496337,0.00035591627,0.0005431397,0.00055166264],"domain_scores_gemma":[0.99105525,0.008115147,0.00028800362,0.00040744868,0.000059332477,0.0000748048],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011713614,0.00022539406,0.00063636043,0.00029048548,0.00014937774,0.00007105377,0.0007128741,0.00020899202,0.00023999684],"category_scores_gemma":[0.016018063,0.00016925967,0.00015853315,0.0004698882,0.00017345467,0.00032048448,0.00013538433,0.0014035397,0.000014021554],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008358199,0.0001261042,0.5127671,0.00004864761,0.00004322839,0.000009498511,0.46811688,0.000023209504,0.003841299,0.0026376604,0.00034445254,0.011958371],"study_design_scores_gemma":[0.0035233803,0.00070932735,0.039866243,0.0003112045,0.00004953797,3.2872478e-7,0.94024885,0.000029174756,0.009646824,0.00014406942,0.005005963,0.00046510753],"about_ca_topic_score_codex":0.006741223,"about_ca_topic_score_gemma":0.0042518275,"teacher_disagreement_score":0.47290084,"about_ca_system_score_codex":0.00024978255,"about_ca_system_score_gemma":0.00012303553,"threshold_uncertainty_score":0.999873},"labels":[],"label_agreement":null},{"id":"W2998316675","doi":"","title":"Examining Student Preparation for Certification Examination: An Exploratory Case Study","year":2019,"lang":"en","type":"dissertation","venue":"Brock University Digital Repository (Brock University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Certification; Exploratory research; Medical education; Psychology; Mathematics education; Engineering; Medicine; Political science; Sociology","score_opus":0.046782753602780884,"score_gpt":0.3019578126824316,"score_spread":0.2551750590796507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998316675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9194839,0.00001921893,0.00037229378,8.378117e-7,0.001215876,0.002315043,0.00003451235,0.00027799883,0.076280326],"genre_scores_gemma":[0.5555801,0.000013493637,0.00002441334,0.000002048167,0.00016043807,0.0000025989527,0.00028892403,0.000027132593,0.44390085],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99667704,0.00047827372,0.00034359333,0.0010309092,0.001039199,0.0004309859],"domain_scores_gemma":[0.9971086,0.00024505646,0.0006278505,0.0005172743,0.0012200404,0.0002811757],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000033574233,0.00042964824,0.00042929096,0.0007501495,0.0019193777,0.00062975386,0.0008911878,0.00046425435,0.000009272792],"category_scores_gemma":[0.000061891675,0.0006031392,0.0002052052,0.00069375575,0.00008594871,0.00410807,0.0001425762,0.00027203368,0.000029248411],"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":[0.0047496622,0.011675923,0.7076259,0.0007478993,0.002579125,0.0033748772,0.20371628,0.00055763376,0.012526705,0.0011656318,0.032411993,0.018868359],"study_design_scores_gemma":[0.0012627483,0.0008490214,0.025162274,0.000058624584,0.0004410014,0.000014062804,0.93720144,0.0000064927804,0.000045267192,0.000003482032,0.034304857,0.00065074017],"about_ca_topic_score_codex":0.00043771547,"about_ca_topic_score_gemma":0.015716491,"teacher_disagreement_score":0.73348516,"about_ca_system_score_codex":0.0016804787,"about_ca_system_score_gemma":0.0008435062,"threshold_uncertainty_score":0.999642},"labels":[],"label_agreement":null},{"id":"W2998551013","doi":"10.5539/ijel.v10n1p255","title":"EFL Students’ Perception of Classroom Assessment Environment in Translation Courses","year":2019,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Psychology; Class (philosophy); Mathematics education; Learning environment; Medical education; Pedagogy; Medicine; Computer science","score_opus":0.024074329695309166,"score_gpt":0.3684626835152612,"score_spread":0.34438835381995203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998551013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9014025,0.00008240401,0.0004322863,0.000115464,0.014145029,0.00021737022,0.000010634914,0.0000088385805,0.083585486],"genre_scores_gemma":[0.99333453,0.0005522904,0.0024831311,0.000027852877,0.0033937818,0.0000011827775,0.0000072541857,0.000007826014,0.00019214537],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975565,0.000109914465,0.0005562812,0.000098919285,0.0015508551,0.00012752862],"domain_scores_gemma":[0.99635303,0.00021781505,0.0004367163,0.000066918044,0.0028748165,0.00005068062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010599646,0.00008315453,0.0001888341,0.00020304862,0.000029304243,0.00006608882,0.00049127766,0.00007339018,0.000515732],"category_scores_gemma":[0.0020686423,0.00008366955,0.00010042776,0.00007423788,0.00006772555,0.00011197621,0.000034266315,0.00020636238,0.000007969351],"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":[0.000074552336,0.00048384792,0.9797068,0.000007068144,0.00010730823,0.000007646694,0.0097998455,0.0008583934,0.00014683286,0.0061669345,0.0003811558,0.002259582],"study_design_scores_gemma":[0.0031794775,0.00031081156,0.70118034,0.00019865327,0.00007801221,3.1467087e-7,0.033476308,0.00022642229,0.000046091332,0.0014659482,0.2596061,0.00023152528],"about_ca_topic_score_codex":0.000058674654,"about_ca_topic_score_gemma":0.00004203341,"teacher_disagreement_score":0.27852648,"about_ca_system_score_codex":0.00035686945,"about_ca_system_score_gemma":0.00015144657,"threshold_uncertainty_score":0.56469035},"labels":[],"label_agreement":null},{"id":"W3001300584","doi":"10.24908/pceea.vi0.13858","title":"THE EFFECT OF STUDENT REFLECTION QUALITY ON A TECHNICAL WRITING ASSIGNMENT RESUBMISSION","year":2019,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Rubric; Grading (engineering); Reflection (computer programming); Computer science; Mathematics education; Quality (philosophy); Graduate students; Psychology; Medical education; Pedagogy; Engineering; Medicine","score_opus":0.013022911278381157,"score_gpt":0.34177096006534985,"score_spread":0.32874804878696867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001300584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95223284,0.000032578908,0.0000015458219,0.005146153,0.0013563614,0.00073123805,0.000002462384,0.00003897035,0.04045786],"genre_scores_gemma":[0.9960971,0.000015422558,0.000044859113,0.000043579024,0.00016799568,0.000048194106,0.0000014122792,0.000011293747,0.0035701569],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983827,0.000055728917,0.0003182669,0.00015233092,0.0008321863,0.00025882752],"domain_scores_gemma":[0.9986328,0.00038813654,0.00046964895,0.00009738837,0.00030374088,0.000108323795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003232203,0.0000984653,0.00015273155,0.00011383417,0.00043941586,0.000116793424,0.00035894514,0.00013053627,0.000018921237],"category_scores_gemma":[0.001475476,0.00007343374,0.00009749843,0.00043984267,0.00002683847,0.00011850701,0.000028337869,0.00021275147,0.000007217429],"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":[0.000017340642,0.000053019194,0.9468912,0.000081998514,0.00005719098,1.0189926e-8,0.0026100702,0.00008827234,0.009892907,0.03286083,0.00597093,0.0014762377],"study_design_scores_gemma":[0.0002742472,0.00011134996,0.9704779,0.0002077831,0.000034590015,1.1953514e-7,0.0026524416,0.000043638884,0.0038029784,0.00008199663,0.022168458,0.00014451817],"about_ca_topic_score_codex":0.005665773,"about_ca_topic_score_gemma":0.004993765,"teacher_disagreement_score":0.043864258,"about_ca_system_score_codex":0.0031878625,"about_ca_system_score_gemma":0.00037450623,"threshold_uncertainty_score":0.8564992},"labels":[],"label_agreement":null},{"id":"W3006441709","doi":"10.19173/irrodl.v20i5.4333","title":"A Systematic Review of Technology-Supported Peer Assessment Research","year":2019,"lang":"en","type":"review","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Science and Technology, Taiwan","keywords":"Peer assessment; Anonymity; Peer feedback; Peer review; Computer science; Assessment for learning; Educational technology; Technical peer review; Psychology; Formative assessment; Mathematics education","score_opus":0.2510590947545748,"score_gpt":0.602044607008705,"score_spread":0.3509855122541302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006441709","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002710769,0.9515787,0.000005029429,0.007606223,0.0001079959,0.007444695,0.00007143229,0.00001107013,0.033172153],"genre_scores_gemma":[0.00010262301,0.9944924,0.000056445642,0.000046219757,0.000051294326,0.0008601406,0.00037941232,0.00002044027,0.0039910153],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9855003,0.006677783,0.0018382502,0.00050180027,0.0048901187,0.0005917502],"domain_scores_gemma":[0.9905874,0.0045163524,0.0010744492,0.00063338724,0.0030930552,0.000095328294],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07146743,0.00023738519,0.0025836353,0.00073216954,0.0003555702,0.0002307358,0.004658713,0.00021258097,0.00068392954],"category_scores_gemma":[0.020389216,0.00015132761,0.00031098313,0.003511152,0.0008504729,0.0002079524,0.0023620191,0.0024229658,0.000070448914],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037576767,0.0000926864,0.00019716777,0.94653225,0.00023414656,0.000007929387,0.0000861619,5.420214e-8,1.2236173e-7,0.019383147,0.0055218013,0.02794076],"study_design_scores_gemma":[0.000089805384,0.000036828875,0.0000087608105,0.54881984,0.00014742851,0.0000030230049,0.002056212,0.0000028020486,6.029009e-8,0.00015988528,0.44859937,0.000076013974],"about_ca_topic_score_codex":0.00054282177,"about_ca_topic_score_gemma":0.000027842329,"teacher_disagreement_score":0.44307756,"about_ca_system_score_codex":0.00061892567,"about_ca_system_score_gemma":0.0025453898,"threshold_uncertainty_score":0.99987847},"labels":[],"label_agreement":null},{"id":"W3007758995","doi":"10.1080/0969594x.2020.1728908","title":"Making feedback effective?","year":2020,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Computer science; Psychology","score_opus":0.09632089257636077,"score_gpt":0.48106678362533445,"score_spread":0.38474589104897366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007758995","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09940084,0.0002971933,0.00023836129,0.18457705,0.00045647993,0.00089042337,0.0000024360143,0.000082760525,0.71405447],"genre_scores_gemma":[0.9820929,0.0008390172,0.005939774,0.009044613,0.0011356892,0.00010994612,0.0000060195507,0.000012683436,0.00081933633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796116,0.0008207741,0.00025181184,0.00030110587,0.00036665544,0.0002984733],"domain_scores_gemma":[0.9975784,0.0018289322,0.00020575333,0.0001205467,0.00010527877,0.00016110571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013813736,0.0001292173,0.00015257276,0.00012515746,0.0003563722,0.0002650739,0.00021091421,0.00008271297,0.00012900172],"category_scores_gemma":[0.0033280377,0.00014012739,0.00003207194,0.0006660628,0.00011227092,0.0010607846,0.00010635194,0.00028389457,0.000042399588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070431364,0.0003948126,0.07271353,0.00004265333,0.000035710327,0.0000026964512,0.055828623,0.000017489689,0.00010872761,0.82709616,0.0010513654,0.042637803],"study_design_scores_gemma":[0.00029577521,0.000053673815,0.19240287,0.000031112144,0.000025821788,0.0000024928336,0.05439495,0.000061028935,0.0000055702662,0.0012172764,0.7513362,0.00017319253],"about_ca_topic_score_codex":0.0015768154,"about_ca_topic_score_gemma":0.00025005863,"teacher_disagreement_score":0.8826921,"about_ca_system_score_codex":0.000298837,"about_ca_system_score_gemma":0.0015805203,"threshold_uncertainty_score":0.57142293},"labels":[],"label_agreement":null},{"id":"W3009011090","doi":"10.7330/9781607329329.c011","title":"Framing Graduate Teaching Assistant Preparation Around Threshold Concepts of Writing Studies","year":2020,"lang":"en","type":"book-chapter","venue":"Utah State University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Harvard University; University of Cambridge; Utah State University","keywords":"Framing (construction); Graduate students; Graduate education; Computer science; Mathematics education; Psychology; Pedagogy; Engineering","score_opus":0.1107655094268788,"score_gpt":0.3561919206657548,"score_spread":0.24542641123887599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009011090","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047500012,0.00027806254,0.00020922333,0.00006597335,0.00026852405,0.00058535114,0.000082729915,0.0001248574,0.9936353],"genre_scores_gemma":[0.23958796,0.0007539887,0.00038848075,0.000038069073,0.00023576558,0.0000010530206,0.000025084324,0.000032850297,0.75893676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979062,0.00013939205,0.00036187097,0.00046710414,0.0008196995,0.00030573548],"domain_scores_gemma":[0.9985216,0.00028149897,0.00062078785,0.00020513865,0.00025071827,0.00012024125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005293796,0.00030555314,0.00055722,0.00011940598,0.00086928066,0.0001105874,0.00045386987,0.00018311798,0.000016714233],"category_scores_gemma":[0.0000427727,0.0003546517,0.00019849685,0.000013839761,0.00062414404,0.00025302343,0.000363477,0.00056842365,0.000004499789],"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":[0.00017055891,0.00002108485,0.00015533697,0.00020227267,0.0008486156,0.00014153568,0.096199,0.000038005677,0.000089585395,0.8972536,0.0023894678,0.0024909896],"study_design_scores_gemma":[0.0011539877,0.00024898225,0.00007396585,0.0012697875,0.0007524558,9.3124544e-7,0.07648626,0.00027516208,0.00013097347,0.006745982,0.9117398,0.0011216721],"about_ca_topic_score_codex":0.0005401621,"about_ca_topic_score_gemma":0.00031624,"teacher_disagreement_score":0.9093504,"about_ca_system_score_codex":0.00031103854,"about_ca_system_score_gemma":0.00018309608,"threshold_uncertainty_score":0.99989057},"labels":[],"label_agreement":null},{"id":"W3009513072","doi":"10.3138/jvme.0418-045r","title":"Using the Digital Platform ExamSoft in Veterinary Anatomy and Parasitology Assessments in Written and Laboratory Components","year":2020,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Veterinary parasitology; Standardization; Medical education; Test (biology); Process (computing); Computer science; Medical physics; Veterinary medicine; Medicine; Engineering; Biology","score_opus":0.1472560376084991,"score_gpt":0.47630665501173014,"score_spread":0.32905061740323105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009513072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940896,0.00040033396,0.000016907392,0.0047077634,0.0003711503,0.000103814185,9.034293e-7,0.0000033892538,0.0003061064],"genre_scores_gemma":[0.99864453,0.00031700838,0.0002394147,0.0005371774,0.00024873007,0.0000024329868,0.0000015708628,0.000004793509,0.0000043406085],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99881476,0.00017625754,0.00032572102,0.0001065216,0.0004254688,0.00015125214],"domain_scores_gemma":[0.9993834,0.00017115114,0.00016400564,0.000039863662,0.000044030847,0.0001975853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006880108,0.00007585441,0.00017708905,0.00009192974,0.00009047036,0.00007499282,0.0001804745,0.000087011824,0.000031202013],"category_scores_gemma":[0.0002927124,0.00006003052,0.000018565233,0.00022513398,0.00020079795,0.0005189262,0.000078356396,0.00028999697,6.2962584e-7],"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":[0.00024737578,0.00035221982,0.9557683,0.00003715413,0.00002441659,0.00022502503,0.01233075,8.901819e-7,0.000987322,0.00021919023,0.00018102788,0.029626332],"study_design_scores_gemma":[0.00088005554,0.0005854816,0.96787584,0.00015217297,0.000010622588,0.00013011225,0.017740991,0.00036736293,8.6669286e-7,0.00012383882,0.01203608,0.00009660491],"about_ca_topic_score_codex":0.000084074796,"about_ca_topic_score_gemma":0.000012450824,"teacher_disagreement_score":0.029529726,"about_ca_system_score_codex":0.00009109465,"about_ca_system_score_gemma":0.00058160065,"threshold_uncertainty_score":0.24479736},"labels":[],"label_agreement":null},{"id":"W3010193995","doi":"","title":"Reform Through Assessment in Ontario Schools","year":2001,"lang":"en","type":"dissertation","venue":"OpenBU (Boston University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Mathematics education; Pedagogy; Public administration; Psychology","score_opus":0.034477647699919275,"score_gpt":0.3333817733728638,"score_spread":0.2989041256729445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010193995","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18995558,0.000022088318,0.000005430534,0.00029124567,0.0008554912,0.0005740018,0.0000035818234,0.000045738525,0.80824685],"genre_scores_gemma":[0.10174567,0.00069564686,0.0005644598,0.000060503357,0.000106128,0.0000036535503,0.0004765122,0.000024844896,0.8963226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784213,0.00015375738,0.0002462832,0.000514146,0.00072406116,0.00051961927],"domain_scores_gemma":[0.9991606,0.000034460256,0.00025124557,0.00028230847,0.00014500138,0.0001263674],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000357988,0.00028493445,0.0004175166,0.0004040033,0.0006063166,0.00019714702,0.00092798984,0.00047265494,0.0037338429],"category_scores_gemma":[0.000013411511,0.00033488256,0.00016180378,0.0009099963,0.00006530819,0.0010225095,0.00009522663,0.0010478409,0.00017837874],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000726811,0.001069342,0.3266752,0.00007586837,0.00042726813,0.0014075399,0.12792939,0.000013308367,0.00010608875,0.5243326,0.012258997,0.004977627],"study_design_scores_gemma":[0.00081931154,0.000053335043,0.1051903,0.00016142563,0.00007143252,2.632641e-7,0.16706452,5.7971016e-7,0.000009345683,0.0005338997,0.7256642,0.00043139103],"about_ca_topic_score_codex":0.6241092,"about_ca_topic_score_gemma":0.97226685,"teacher_disagreement_score":0.7134052,"about_ca_system_score_codex":0.0072056507,"about_ca_system_score_gemma":0.0028242439,"threshold_uncertainty_score":0.9999103},"labels":[],"label_agreement":null},{"id":"W3011346301","doi":"10.3138/jvme.2019-0058","title":"Developing Miller’s Pyramid to Support Students’ Assessment Literacy","year":2020,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pyramid (geometry); Curriculum; Literacy; Miller; Relevance (law); Needs assessment; Work (physics); Computer science; Psychology; Engineering ethics; Medical education; Mathematics education; Pedagogy; Sociology; Engineering; Medicine; Political science; Social science","score_opus":0.1434371480127097,"score_gpt":0.5190844493078557,"score_spread":0.375647301295146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011346301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91160846,0.00007613698,0.0020021584,0.08010909,0.002618249,0.00019694454,5.349134e-7,0.00001839754,0.0033700585],"genre_scores_gemma":[0.97811455,0.00028266644,0.009045357,0.010035765,0.0021963425,0.00000896891,0.0000038445105,0.0000102107215,0.00030230422],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99700624,0.00020115908,0.00053711084,0.00014271258,0.0018847828,0.00022797422],"domain_scores_gemma":[0.9984774,0.000095923824,0.00025538454,0.00007242323,0.00033279302,0.0007660964],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013430857,0.000102200436,0.00021985735,0.00010659975,0.00018431857,0.00016161041,0.00069355033,0.00008015639,0.0017173231],"category_scores_gemma":[0.0008672012,0.000091551134,0.00008860815,0.00035716768,0.000063947795,0.00041643018,0.00012983016,0.00027226264,0.000054353153],"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":[0.00043880765,0.0021034144,0.22814849,0.0001496506,0.00026273646,0.00036873203,0.19195025,0.000004869719,0.0009465483,0.007070919,0.14539,0.4231656],"study_design_scores_gemma":[0.0006188192,0.0016896726,0.1617229,0.00021956387,0.000031098123,0.00004187793,0.014396828,0.000012338954,0.000008677829,0.00015609397,0.8209107,0.00019141892],"about_ca_topic_score_codex":0.000029901485,"about_ca_topic_score_gemma":0.0000049270775,"teacher_disagreement_score":0.6755207,"about_ca_system_score_codex":0.0003263806,"about_ca_system_score_gemma":0.0042289104,"threshold_uncertainty_score":0.9991952},"labels":[],"label_agreement":null},{"id":"W3013727910","doi":"10.4018/978-1-7998-2943-0.ch001","title":"Innovation, Critical Pedagogy, and Appreciative Feedback","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Dialogic; Scope (computer science); Dyad; Power (physics); Pedagogy; Process (computing); Critical pedagogy; Appreciative inquiry; Through-the-lens metering; Psychology; Sociology; Engineering; Computer science; Lens (geology); Social psychology","score_opus":0.04357742160523497,"score_gpt":0.4046063351145801,"score_spread":0.36102891350934513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013727910","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025258271,0.029593574,0.000003574369,0.023813166,0.0044780443,0.0005209674,0.000008092353,0.000055514953,0.94127446],"genre_scores_gemma":[0.004878275,0.012498845,0.0021047438,0.0019820174,0.00057962665,0.00012342837,0.0001073988,0.000026716141,0.9776989],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842715,0.00006798927,0.00045662918,0.0004330113,0.00039977793,0.0002154337],"domain_scores_gemma":[0.99909765,0.0002704499,0.00018608247,0.00007364095,0.0002603521,0.00011181151],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025259762,0.00027055605,0.00029778102,0.00019163279,0.0005344265,0.00008214207,0.00014209257,0.00024681556,0.0015917266],"category_scores_gemma":[0.00006370276,0.00026271,0.000018639426,0.00013558414,0.0005618949,0.0012238169,0.00014166941,0.00034581177,0.000038819802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003415495,0.000053993306,0.0037582547,0.000113211376,0.000016675544,9.550976e-7,0.014356051,3.6729528e-8,0.0000014390041,0.9619699,0.005273866,0.014421468],"study_design_scores_gemma":[0.00013909685,0.000019161655,0.021280795,0.00040135352,0.00001014134,6.486899e-7,0.0032950558,5.858961e-8,0.0000035090395,0.06213284,0.91240364,0.00031367847],"about_ca_topic_score_codex":0.000006434717,"about_ca_topic_score_gemma":0.00013540204,"teacher_disagreement_score":0.9071298,"about_ca_system_score_codex":0.0001427537,"about_ca_system_score_gemma":0.001886755,"threshold_uncertainty_score":0.99998254},"labels":[],"label_agreement":null},{"id":"W3016349227","doi":"10.17632/hfkt24zxcw.1","title":"2012-2018 Direct Writing Assessment Scores for an international school (K-12) in Bangkok, Thailand","year":2020,"lang":"en","type":"article","venue":"Data Archiving and Networked Services (DANS)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Political science; Geography","score_opus":0.06343688411253688,"score_gpt":0.3663497340823161,"score_spread":0.3029128499697792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016349227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9255182,0.0003493911,0.001393019,0.0024853288,0.00077632547,0.00084366667,0.0005313351,0.00019278457,0.067909926],"genre_scores_gemma":[0.99183166,0.00066331675,0.0035582476,0.0006407215,0.001862941,0.000034073568,0.0012198733,0.000021118562,0.00016804182],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99817044,0.00021707146,0.00028318822,0.00055071275,0.00036587924,0.0004126944],"domain_scores_gemma":[0.9989207,0.0003902557,0.0001174211,0.00029637618,0.000025735264,0.00024954366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010953223,0.00016573544,0.00022144691,0.0000634261,0.00045557626,0.00045632923,0.0013516421,0.000054205648,0.000057871846],"category_scores_gemma":[0.000039519047,0.00015621346,0.000035018846,0.0001661288,0.00009020525,0.0013454952,0.0005234585,0.00018293415,0.0000051499896],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008758159,0.000067881905,0.97562903,0.00006414419,0.000055653207,0.0000040142454,0.012481836,0.00010724189,0.00016958157,0.00043367615,0.00220912,0.008690256],"study_design_scores_gemma":[0.001102125,0.00012578168,0.7659079,0.00028953992,0.000047806905,6.8597535e-7,0.015021626,0.1489685,0.0000030197236,0.00030589997,0.067831375,0.00039572173],"about_ca_topic_score_codex":0.0019734197,"about_ca_topic_score_gemma":0.023503916,"teacher_disagreement_score":0.2097211,"about_ca_system_score_codex":0.000038243354,"about_ca_system_score_gemma":0.0000787552,"threshold_uncertainty_score":0.9943146},"labels":[],"label_agreement":null},{"id":"W3028174053","doi":"10.37590/able.v41.abs78","title":"Examining the efficacy of peer feedback as part of the writing process in an introductory biology course","year":2020,"lang":"en","type":"article","venue":"Advances in Biology Laboratory Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Course (navigation); Peer feedback; Writing process; Process (computing); Mathematics education; Computer science; Psychology; Physics; Programming language; Astronomy","score_opus":0.029020089710651183,"score_gpt":0.4120239851794286,"score_spread":0.38300389546877744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028174053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917113,0.0017899899,0.0000016885361,0.0037187978,0.0009624679,0.0003021336,0.0000062203458,0.0000107692495,0.0014966073],"genre_scores_gemma":[0.99865216,0.00026980435,0.00007742563,0.00040941744,0.00051969645,0.000036263897,0.000012211804,0.000005810676,0.000017233027],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99842125,0.00067409454,0.00033633134,0.00024676794,0.0001297755,0.00019176365],"domain_scores_gemma":[0.9988209,0.0003558691,0.00029569102,0.00017450859,0.00031966186,0.000033397097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097605324,0.00008842463,0.000179246,0.000042336043,0.0001170037,0.00000867402,0.0004901817,0.00009943798,0.00004970399],"category_scores_gemma":[0.0011479784,0.00006180127,0.000018133693,0.00083309173,0.0007852031,0.00027527,0.000041504616,0.00018874255,0.000002719246],"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":[0.00002307911,0.00015764497,0.96093255,0.000013388535,0.000005020156,4.825114e-8,0.024372373,0.00004143277,0.001883795,0.00864522,0.0000713366,0.003854109],"study_design_scores_gemma":[0.0005319038,0.00019666964,0.7894206,0.00007509315,0.000020244855,1.21034e-7,0.17800623,0.000010799467,0.0013109917,0.002545447,0.027700918,0.0001809694],"about_ca_topic_score_codex":0.00006119502,"about_ca_topic_score_gemma":0.0006752245,"teacher_disagreement_score":0.17151195,"about_ca_system_score_codex":0.000044289274,"about_ca_system_score_gemma":0.0008306918,"threshold_uncertainty_score":0.28931135},"labels":[],"label_agreement":null},{"id":"W3033487789","doi":"10.1186/s41039-020-00134-8","title":"Can automated item generation be used to develop high quality MCQs that assess application of knowledge?","year":2020,"lang":"en","type":"article","venue":"Research and Practice in Technology Enhanced Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Ottawa; Ottawa Hospital; Medical Council of Canada","funders":"","keywords":"Quality (philosophy); Multiple choice; Cognition; Recall; Item analysis; Wilcoxon signed-rank test; Sample (material); Computer science; Test (biology); Modalities; Psychology; Psychometrics; Significant difference; Statistics; Clinical psychology; Mathematics; Cognitive psychology","score_opus":0.2606414184306209,"score_gpt":0.5297904732686232,"score_spread":0.2691490548380023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033487789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9283825,0.00014554006,0.0024804599,0.059503675,0.0000425679,0.0006257017,0.0000016331813,0.00033769046,0.008480248],"genre_scores_gemma":[0.9959963,0.0002726961,0.0032666225,0.00006661401,0.00006936661,0.000115511764,0.000015751673,0.000010212668,0.00018694293],"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","domain_scores_codex":[0.9971117,0.0013571703,0.00025958187,0.00035956257,0.0005286425,0.00038337713],"domain_scores_gemma":[0.99607193,0.002777051,0.00016647812,0.00012602186,0.0007502103,0.000108310334],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0039814147,0.000088265515,0.00020687583,0.00032093163,0.00042255156,0.00007467996,0.00028792245,0.00023918817,0.000018879935],"category_scores_gemma":[0.022185722,0.00009526653,0.000010603413,0.0030160346,0.0002695814,0.00030704835,0.00018578372,0.0007175058,0.000016083142],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031027853,0.0003285569,0.11547403,0.00010405365,0.00008115801,0.000008692599,0.1052999,0.00013990125,0.56904763,0.046435613,0.000909178,0.161861],"study_design_scores_gemma":[0.002921801,0.0018162311,0.08137865,0.00018516615,0.000044930905,0.0000033964238,0.455408,0.007267222,0.2632423,0.003869704,0.1827301,0.0011324945],"about_ca_topic_score_codex":0.0010726097,"about_ca_topic_score_gemma":0.0040729702,"teacher_disagreement_score":0.3501081,"about_ca_system_score_codex":0.00013399654,"about_ca_system_score_gemma":0.00036579507,"threshold_uncertainty_score":0.98605084},"labels":[],"label_agreement":null},{"id":"W3036912581","doi":"10.18438/eblip29709","title":"Using Assessment Tools to Develop a Workshop for Library Staff: Establishing a Culture of Assessment","year":2020,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Illinois at Chicago; University of Illinois at Urbana-Champaign","keywords":"Computer science; Library science; Data science; Engineering management; World Wide Web; Medical education; Medicine; Engineering","score_opus":0.08634915348694418,"score_gpt":0.391862556407179,"score_spread":0.3055134029202348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036912581","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023865575,0.00057689566,0.3743684,0.49741587,0.0007481471,0.0050947806,0.00017155871,0.00058403576,0.09717475],"genre_scores_gemma":[0.23153055,0.0010197922,0.6949739,0.07148534,0.00041112964,0.00012028677,0.00015464993,0.000023443457,0.0002809172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802387,0.00033179298,0.0005606717,0.00020590387,0.0006050552,0.00027268045],"domain_scores_gemma":[0.99622387,0.0026604454,0.0005107992,0.00013701238,0.00018955658,0.00027832677],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0008716574,0.00016082477,0.00022777617,0.00012457544,0.0004552705,0.0018781979,0.00039051563,0.00011246165,0.00027868172],"category_scores_gemma":[0.003601092,0.00015344306,0.000052002983,0.0014436514,0.00006125875,0.26226765,0.00022021549,0.00022856251,0.000004880081],"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":[0.0015083327,0.0002745965,0.013345949,0.000845604,0.00016760963,0.000006743635,0.06908577,0.002040267,0.00075476716,0.80111617,0.06512905,0.045725122],"study_design_scores_gemma":[0.00055699766,0.00028622866,0.004016361,0.00046101815,0.00007486133,7.0599583e-7,0.07015112,0.007194103,0.0003587883,0.000091145484,0.91650116,0.00030749588],"about_ca_topic_score_codex":0.000010135119,"about_ca_topic_score_gemma":1.4760894e-7,"teacher_disagreement_score":0.8513721,"about_ca_system_score_codex":0.00003341027,"about_ca_system_score_gemma":0.0017128744,"threshold_uncertainty_score":0.99915797},"labels":[],"label_agreement":null},{"id":"W3046538170","doi":"10.1111/emip.12382","title":"Synergy and Tension between Large‐Scale and Classroom Assessment: International Trends","year":2020,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; Brock University","funders":"","keywords":"Scale (ratio); Test (biology); Political science; Mathematics education; Pedagogy; Sociology; Psychology; Geography; Geology; Cartography","score_opus":0.09632131387335943,"score_gpt":0.42067691106516314,"score_spread":0.32435559719180374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046538170","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06594703,0.003649217,0.000281559,0.80060315,0.00082050875,0.00023685837,0.000025174471,0.00005304952,0.12838344],"genre_scores_gemma":[0.98926497,0.001826033,0.0042086686,0.0014336434,0.0016408261,0.000013792584,0.00004049318,0.000009167736,0.0015623894],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982424,0.00024852817,0.00017367216,0.00029056263,0.00087135914,0.00017351263],"domain_scores_gemma":[0.9988795,0.00044813173,0.00012170651,0.00005784315,0.00029093173,0.0002019014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013380293,0.000110519926,0.00013323821,0.000055484117,0.0004620808,0.00028404087,0.0001031014,0.00005820222,0.00039355477],"category_scores_gemma":[0.0007046846,0.000107482105,0.000019817593,0.00014496403,0.000091269205,0.000678461,0.00007887384,0.00013397678,0.000008068414],"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":[0.00012221112,0.00043747245,0.8149075,0.000037741338,0.0003562179,0.000002594953,0.050003715,9.0795663e-7,0.0006667293,0.063975565,0.039591245,0.029898124],"study_design_scores_gemma":[0.00032442992,0.000053311116,0.3227398,0.000016539068,0.00007424561,0.0000014832684,0.016131815,0.000040290728,0.0000038478547,0.00046357646,0.66003126,0.00011937006],"about_ca_topic_score_codex":0.00036348545,"about_ca_topic_score_gemma":0.000121781835,"teacher_disagreement_score":0.92331797,"about_ca_system_score_codex":0.00006137519,"about_ca_system_score_gemma":0.00012818491,"threshold_uncertainty_score":0.43829933},"labels":[],"label_agreement":null},{"id":"W3046571216","doi":"10.5430/jct.v9n3p33","title":"The Effect of Formative Assessment on the Academic Achievement Levels of Prospective Teachers","year":2020,"lang":"en","type":"article","venue":"Journal of Curriculum and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Qualitative property; Mathematics education; Data collection; Qualitative research; Test (biology); Documentation; Research design; Academic year; Academic achievement; Affect (linguistics); Medical education; Computer science; Mathematics; Medicine; Statistics","score_opus":0.024088470971229545,"score_gpt":0.3627800769070531,"score_spread":0.33869160593582354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046571216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9827825,0.00019685252,0.00024097436,0.006738873,0.00015941027,0.00032616386,0.000001958135,0.0000046228256,0.009548649],"genre_scores_gemma":[0.99948245,0.00010527704,0.00008598355,0.00007734617,0.00020871132,0.000003921496,9.711135e-8,0.000004487026,0.000031720578],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99784636,0.00078531844,0.00041717524,0.00007512094,0.0007130139,0.00016298024],"domain_scores_gemma":[0.99810857,0.0009381418,0.00075005455,0.000055869066,0.000073559124,0.000073818126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004287508,0.00010333141,0.00025532657,0.000032226475,0.0005562218,0.000046785928,0.00034485527,0.000047605667,0.000010915875],"category_scores_gemma":[0.00047729322,0.000047234065,0.00013175655,0.00009442259,0.00018310924,0.00023175102,0.00006449496,0.00083930755,5.080885e-7],"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":[0.00010756599,0.00011674303,0.69621944,0.000036743404,0.00043638624,0.0000022491577,0.17726608,0.000028364544,0.0014765724,0.09245709,0.0013906616,0.030462112],"study_design_scores_gemma":[0.0033105032,0.006392823,0.6756988,0.0006366202,0.000407638,0.000004292536,0.2986335,0.00041701828,0.0029603336,0.0025192401,0.008681728,0.00033748618],"about_ca_topic_score_codex":0.000043944343,"about_ca_topic_score_gemma":0.0000062115614,"teacher_disagreement_score":0.12136742,"about_ca_system_score_codex":0.00007467391,"about_ca_system_score_gemma":0.00006381223,"threshold_uncertainty_score":0.42780647},"labels":[],"label_agreement":null},{"id":"W3076472937","doi":"10.5539/elt.v13n9p10","title":"A Review of the Washback of English Language Tests on Classroom Teaching","year":2020,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Syllabus; Psychology; Mathematics education; English language; Test (biology); Empirical research; Language education; Teaching method; Language assessment; Pedagogy; Mathematics","score_opus":0.02859189116016439,"score_gpt":0.3774667469147653,"score_spread":0.34887485575460087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3076472937","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023083593,0.8302048,0.000002637805,0.00006292119,0.0018087003,0.0013644345,0.00007924791,0.0001931743,0.16605327],"genre_scores_gemma":[0.001705968,0.99211013,0.0003298493,0.00038362114,0.0038711326,0.000056178167,0.00007796358,0.00010621391,0.001358913],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928447,0.0034206908,0.0012262808,0.00063938776,0.001286923,0.0005820461],"domain_scores_gemma":[0.99558926,0.0016635557,0.0014417631,0.0009785922,0.00015366556,0.00017317741],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004223777,0.00061181077,0.002352792,0.00017048005,0.0004543665,0.00010200497,0.0021468145,0.00038284253,0.0002554177],"category_scores_gemma":[0.022831565,0.0004311079,0.0013004874,0.0006230311,0.00021756381,0.00023554623,0.00049240986,0.0028529817,0.000023945397],"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":[0.000002815252,0.00014237742,0.00005453642,0.029637536,0.0001898213,0.000014822262,0.39061508,1.5434193e-7,0.0000019500972,0.0033194686,0.0071465033,0.56887496],"study_design_scores_gemma":[0.0001651427,0.000045236357,0.0000031017412,0.09871786,0.0005859561,4.9356987e-7,0.06124909,3.893103e-7,0.0000017390104,0.00000446288,0.83885944,0.0003670897],"about_ca_topic_score_codex":0.00059604895,"about_ca_topic_score_gemma":0.00015900531,"teacher_disagreement_score":0.83171296,"about_ca_system_score_codex":0.00030401468,"about_ca_system_score_gemma":0.0004835338,"threshold_uncertainty_score":0.9998141},"labels":[],"label_agreement":null},{"id":"W3084220926","doi":"","title":"Exploring science teachers’ conceptions and efficacy of assessment in Manitoba schools: A case study.","year":2019,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Pedagogy; Sociology; Psychology","score_opus":0.08932588436502209,"score_gpt":0.33666609939273756,"score_spread":0.24734021502771547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084220926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98996043,0.000051206025,0.00000844429,0.0001174635,0.0004482892,0.0010081276,0.00000600478,0.000027911805,0.0083721075],"genre_scores_gemma":[0.9986445,0.0002595215,0.0004182757,0.000001999906,0.000040636773,0.000002515848,0.000010917154,0.000012048591,0.0006096421],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99798095,0.00019779032,0.00018161244,0.00045660321,0.00086679606,0.00031625718],"domain_scores_gemma":[0.998872,0.00014465125,0.0003605574,0.00026807765,0.00024419234,0.00011053809],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010313403,0.00018804347,0.00042379525,0.0006198124,0.00065302715,0.00007281995,0.0005584059,0.00012232708,0.000015193495],"category_scores_gemma":[0.000068415444,0.00025040263,0.00008661875,0.0008547741,0.0004285358,0.00089900405,0.00015557649,0.00043637952,0.000010197273],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047871294,0.0005465622,0.8614991,0.00007036462,0.000076348835,0.00024940638,0.13339952,0.000013183789,0.00030816766,0.0009433541,0.00005638648,0.0027897486],"study_design_scores_gemma":[0.0006838184,0.000087289736,0.47263736,0.00009638147,0.00006787411,0.0000012070275,0.52620775,0.000013056108,0.0000032120965,0.000004622562,0.00007801079,0.00011946878],"about_ca_topic_score_codex":0.09302608,"about_ca_topic_score_gemma":0.8427667,"teacher_disagreement_score":0.7497406,"about_ca_system_score_codex":0.00049742486,"about_ca_system_score_gemma":0.00070007937,"threshold_uncertainty_score":0.9999948},"labels":[],"label_agreement":null},{"id":"W3084713209","doi":"10.4018/978-1-7998-5030-4.ch008","title":"Chinese International Graduate Students' Perceptions of Classroom Assessment at a Canadian University","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Data collection; Medical education; Perception; Psychology; Graduate students; Qualitative property; Diversity (politics); Transparency (behavior); Pedagogy; Mathematics education; Medicine; Sociology; Political science; Computer science; Social science","score_opus":0.027426370367356873,"score_gpt":0.37094936101189274,"score_spread":0.34352299064453584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084713209","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008772209,0.0014716461,0.0000016117593,0.011183233,0.006020528,0.00058371905,0.0000481463,0.000032269683,0.97188663],"genre_scores_gemma":[0.06561711,0.009003301,0.0011330752,0.00047530732,0.0002133175,0.000021054493,0.00029138653,0.00001698352,0.92322844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983628,0.00006462671,0.00032413233,0.0003368009,0.00072167616,0.00018996478],"domain_scores_gemma":[0.9992077,0.000069858586,0.00023157017,0.00009220556,0.00018540678,0.00021330582],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019208065,0.00022779335,0.00026143188,0.0002675121,0.00051895814,0.00003660796,0.00037472293,0.00016662615,0.0047677355],"category_scores_gemma":[0.000009067113,0.00022757624,0.00004874572,0.00008965561,0.00026363265,0.0007667294,0.00020441053,0.00027268584,0.000033804627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095768664,0.00018140131,0.4642174,0.00009119489,0.000121402605,0.000010955375,0.017793458,0.0000013312227,0.000005602053,0.504911,0.007789899,0.0047806026],"study_design_scores_gemma":[0.0001522063,0.000010255081,0.3236379,0.00016474837,0.000009834502,4.3543008e-7,0.0023492472,1.1235583e-7,2.5680927e-7,0.0022264638,0.6712739,0.00017465108],"about_ca_topic_score_codex":0.00069345644,"about_ca_topic_score_gemma":0.044470694,"teacher_disagreement_score":0.663484,"about_ca_system_score_codex":0.0010807991,"about_ca_system_score_gemma":0.0029958554,"threshold_uncertainty_score":0.996142},"labels":[],"label_agreement":null},{"id":"W3088489015","doi":"","title":"Critical Education: Increasing Student Achievement through Formative Assessments","year":2020,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Mathematics education; Academic achievement; Student achievement; Pedagogy; Psychology; Medical education; Political science; Medicine","score_opus":0.1605869940978424,"score_gpt":0.4477805437303521,"score_spread":0.28719354963250965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088489015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97596884,0.00007262512,0.0011980215,0.0055929045,0.00065676705,0.00050924084,0.0000121317335,0.00020186347,0.015787613],"genre_scores_gemma":[0.99423087,0.00009942694,0.0004677527,0.0027606585,0.00047469998,0.0000039328447,0.000021139986,0.000025919559,0.0019156241],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996613,0.0008454442,0.00030846812,0.000535365,0.0010941208,0.0006035759],"domain_scores_gemma":[0.99850726,0.00026120723,0.00017452097,0.00026133278,0.00031268952,0.00048298028],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006084429,0.00028780196,0.00032091537,0.00013593411,0.0010599816,0.00075816043,0.0010872858,0.00016807932,0.00016975089],"category_scores_gemma":[0.00014837067,0.00033408226,0.00014510896,0.00067768904,0.00029088403,0.0043614637,0.00053212454,0.00050656,0.00034189914],"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":[0.00008661603,0.00042604856,0.9693351,0.000030245961,0.00008462222,0.000038402453,0.02230351,0.0000013649491,0.000087227956,0.0071021165,0.000009518462,0.00049521663],"study_design_scores_gemma":[0.00082548475,0.0002077797,0.9192252,0.00011657296,0.00013127353,0.0000018950341,0.048109487,1.67645e-7,0.00009705712,0.00027909875,0.030575017,0.00043093378],"about_ca_topic_score_codex":0.000042077016,"about_ca_topic_score_gemma":0.00062144955,"teacher_disagreement_score":0.050109874,"about_ca_system_score_codex":0.00055010954,"about_ca_system_score_gemma":0.00054404925,"threshold_uncertainty_score":0.9999111},"labels":[],"label_agreement":null},{"id":"W3090347405","doi":"10.16986/huje.2020063705","title":"Guidelines for Generating Effective Feedback from E-Assessments","year":2020,"lang":"en","type":"article","venue":"Hacettepe University Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Psychology","score_opus":0.07753533092986926,"score_gpt":0.39255052791016115,"score_spread":0.3150151969802919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090347405","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9320668,0.0001983752,0.023080135,0.035860483,0.0017902105,0.00047229393,0.00001053141,0.000020715823,0.00650046],"genre_scores_gemma":[0.88879,0.00022730046,0.09996128,0.0033528837,0.0054322933,0.0000013775295,0.000021634545,0.000015085078,0.002198132],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991853,0.0001305943,0.000179988,0.00011132234,0.00027115914,0.00012161642],"domain_scores_gemma":[0.99823064,0.00017827339,0.00033344034,0.000045604756,0.0010731431,0.00013891248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033155602,0.00007090552,0.00014310192,0.00006500869,0.00034134803,0.000065367494,0.00025054478,0.000053166623,0.000113781316],"category_scores_gemma":[0.00039527475,0.000075519725,0.00010541019,0.00019149829,0.000039554783,0.00044222779,0.000024866451,0.00009777418,0.000008352869],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000630621,0.00054544,0.101545356,0.000038973933,0.0005568501,0.000010289859,0.07265773,0.00030961528,0.016434021,0.009485135,0.6654139,0.13237207],"study_design_scores_gemma":[0.0032993094,0.00065097644,0.033305775,0.0001742524,0.00046911323,0.00000146688,0.27846926,0.0011269604,0.00064679777,0.0011482061,0.68025035,0.00045753975],"about_ca_topic_score_codex":0.00024732001,"about_ca_topic_score_gemma":0.00007865229,"teacher_disagreement_score":0.20581155,"about_ca_system_score_codex":0.0002077218,"about_ca_system_score_gemma":0.00068652263,"threshold_uncertainty_score":0.30796048},"labels":[],"label_agreement":null},{"id":"W3092500786","doi":"10.47670/wuwijar201821lh","title":"Direct assessment of second language writing: Holistic and analytic scoring","year":2018,"lang":"en","type":"article","venue":"Westcliff International Journal of Applied Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Rubric; Writing assessment; Language assessment; Task (project management); Test (biology); Mathematics education; Standards-based assessment; Reliability (semiconductor); Peer assessment; Psychology; Educational assessment; Computer science","score_opus":0.09942307377488162,"score_gpt":0.5055932593544762,"score_spread":0.40617018557959456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092500786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7533541,0.000060714472,0.00007115144,0.0003409313,0.00031437265,0.00009369109,0.000004478331,0.000005431968,0.24575515],"genre_scores_gemma":[0.9965631,0.00013650986,0.0010405579,0.000033893124,0.0014643802,0.0000028831103,0.0000014102982,0.000008569677,0.0007487255],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972514,0.00012960739,0.0003962625,0.00014198442,0.0018249617,0.00025581484],"domain_scores_gemma":[0.9978742,0.0005815964,0.00024077897,0.00008946581,0.0010855292,0.00012844561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041187475,0.00007336249,0.00019953918,0.00045827092,0.00021193139,0.00017929713,0.00058316154,0.000052297357,0.0007771702],"category_scores_gemma":[0.00023200043,0.00006502123,0.000057033634,0.00029062165,0.0006044782,0.0001516358,0.00016285713,0.00031893188,0.0000101808855],"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":[0.00083922344,0.0010809078,0.37645552,0.0001414287,0.0017399846,0.00029438527,0.06999467,0.000027151775,0.1291042,0.3705464,0.008854318,0.04092182],"study_design_scores_gemma":[0.003641723,0.00079869427,0.854688,0.000519008,0.000094539304,0.00002918697,0.100675404,0.0004099937,0.008513853,0.006755574,0.023409044,0.00046499734],"about_ca_topic_score_codex":0.00013453425,"about_ca_topic_score_gemma":0.0002706816,"teacher_disagreement_score":0.47823247,"about_ca_system_score_codex":0.0001753167,"about_ca_system_score_gemma":0.00032712557,"threshold_uncertainty_score":0.85094684},"labels":[],"label_agreement":null},{"id":"W3094750526","doi":"10.5539/ijel.v10n6p381","title":"Promoted Peer Review in EFL Writing: Development in Students’ Perceptions and Feedback","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University","keywords":"Psychology; Medical education; Session (web analytics); Perception; Peer feedback; Promotion (chess); Mathematics education; Medicine; Computer science","score_opus":0.051053419853868846,"score_gpt":0.3924193996363336,"score_spread":0.34136597978246475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094750526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88538414,0.0023820798,0.00008760624,0.0101228645,0.008448816,0.0006607358,0.000012214549,0.000041886113,0.09285967],"genre_scores_gemma":[0.9903643,0.0025271638,0.0019438056,0.00076003105,0.004188629,0.0000029697783,0.000006622973,0.000008355361,0.0001981038],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762857,0.000091601134,0.00061618816,0.000112840324,0.0014061815,0.00014459371],"domain_scores_gemma":[0.99054956,0.00012676805,0.0002195079,0.000032491385,0.008957064,0.000114627794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013153983,0.00008479776,0.0001999464,0.000121688245,0.000050411352,0.0001340595,0.00047492093,0.000048856375,0.00014956947],"category_scores_gemma":[0.053672504,0.00008538892,0.000040837724,0.00019980757,0.000057446243,0.00008079869,0.00009853836,0.00030094845,0.0000056837866],"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":[0.000047794954,0.0003301271,0.9218635,0.000076100245,0.000085883614,0.00012219019,0.059721246,0.000016335262,0.0000068023073,0.0029772287,0.012336441,0.0024163495],"study_design_scores_gemma":[0.0014017808,0.000055141918,0.2804721,0.0012886642,0.000025862935,6.872502e-7,0.011610199,0.000017267921,0.000006090739,0.00017185722,0.7047662,0.00018411897],"about_ca_topic_score_codex":0.000022406286,"about_ca_topic_score_gemma":0.00015718144,"teacher_disagreement_score":0.6924298,"about_ca_system_score_codex":0.00018433819,"about_ca_system_score_gemma":0.00021787136,"threshold_uncertainty_score":0.9542988},"labels":[],"label_agreement":null},{"id":"W3094847424","doi":"10.5539/ijel.v10n6p347","title":"The Practical Perceptions of Vietnamese Lecturers and Students Towards Written Peer Feedback","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vietnamese; Perception; Context (archaeology); Peer feedback; Mathematics education; Psychology; Medical education; Pedagogy; Medicine; Geography","score_opus":0.033070435731891674,"score_gpt":0.39738003538951,"score_spread":0.36430959965761833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094847424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6566451,0.0007444649,0.0012959777,0.048808236,0.04419695,0.00055586663,0.00007259,0.00006990419,0.2476109],"genre_scores_gemma":[0.9875044,0.00045358817,0.0013208272,0.0003261641,0.010142133,7.417637e-7,0.0000018269047,0.000007614717,0.00024267368],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975983,0.000106468215,0.00038992704,0.00008628869,0.0016870932,0.00013195844],"domain_scores_gemma":[0.9844316,0.00039829832,0.0003210453,0.00005036793,0.014652387,0.00014629563],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008972959,0.00007889876,0.00014756565,0.000044238008,0.00017493474,0.00025508847,0.0005759037,0.000059369235,0.00010068774],"category_scores_gemma":[0.093389645,0.00005891116,0.00009620222,0.00010146797,0.00026866922,0.000081746264,0.00011919827,0.00030188359,0.0000030916829],"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":[0.0008769595,0.0007304913,0.419331,0.00002531872,0.0018585768,0.00015033424,0.24756059,0.00011507266,0.000088595225,0.088281356,0.23533863,0.0056430814],"study_design_scores_gemma":[0.0009920866,0.00019248058,0.05090222,0.000035893583,0.00012613428,0.0000017504848,0.05799124,0.000052302366,0.000018241624,0.0010878877,0.8884654,0.00013434277],"about_ca_topic_score_codex":0.000026912441,"about_ca_topic_score_gemma":0.000031454852,"teacher_disagreement_score":0.6531268,"about_ca_system_score_codex":0.000070918846,"about_ca_system_score_gemma":0.00025803203,"threshold_uncertainty_score":0.9142471},"labels":[],"label_agreement":null},{"id":"W3095163032","doi":"10.37213/cjal.2020.31121","title":"Portfolio Based Language Assessment (PBLA) in Language Instruction for Newcomers to Canada (LINC) Programs: Taking Stock of Teachers' Experience","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Summative assessment; Formative assessment; Portfolio; Mathematics education; Psychological intervention; Psychology; Medical education; Medicine; Business","score_opus":0.03401772351194283,"score_gpt":0.34175259535421443,"score_spread":0.3077348718422716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095163032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9773196,0.000055915756,0.0008820376,0.00056057016,0.000923278,0.00066236913,0.000027228254,0.000009675405,0.019559348],"genre_scores_gemma":[0.98888427,0.0000014765412,0.009767029,0.000517119,0.000767834,0.000013369038,0.000008375755,0.000015213678,0.000025333593],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99860317,0.00002957184,0.00044351202,0.0001453728,0.00041486774,0.00036353598],"domain_scores_gemma":[0.99857754,0.000074800286,0.00039631868,0.00008753205,0.00021894417,0.00064484385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039568386,0.00011791328,0.00026879643,0.0001684447,0.00014437191,0.00006199056,0.00035312586,0.00006696726,0.000061081046],"category_scores_gemma":[0.00089416973,0.00012860769,0.000056310968,0.00045214215,0.000081899474,0.000019240533,0.000011591301,0.00021073307,2.637621e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002442343,0.000119233875,0.2898646,0.00016224448,0.00014769348,0.00047652362,0.5979195,0.0029743437,0.0010434774,0.021059748,0.0040999013,0.081888475],"study_design_scores_gemma":[0.0030191606,0.00044318388,0.026223106,0.00022664489,0.00011428083,0.0000016301642,0.7814806,0.000978904,0.00063086185,0.00008996797,0.18610823,0.0006834161],"about_ca_topic_score_codex":0.5783837,"about_ca_topic_score_gemma":0.93459773,"teacher_disagreement_score":0.35621405,"about_ca_system_score_codex":0.0006843444,"about_ca_system_score_gemma":0.005986681,"threshold_uncertainty_score":0.99964845},"labels":[],"label_agreement":null},{"id":"W3095324430","doi":"10.1080/00131881.2020.1839353","title":"From sea to sea: The Canadian landscape of assessment education","year":2020,"lang":"en","type":"article","venue":"Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Syllabus; Documentation; Context (archaeology); Teacher education; Pace; Pedagogy; Assessment for learning; Psychology; Mathematics education; Focus group; Formative assessment; Sociology; Medical education; Geography; Medicine","score_opus":0.16246924222224482,"score_gpt":0.5141131410749168,"score_spread":0.351643898852672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095324430","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3068899,0.000087253655,0.000003957033,0.42119554,0.00042130036,0.00041887938,0.000030339614,0.0000048427905,0.270948],"genre_scores_gemma":[0.99170953,0.000018352906,0.00058805157,0.001094454,0.0021854667,0.00009482841,0.00007200591,0.0000060247926,0.0042312625],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9978926,0.00031886096,0.00012100424,0.00018207256,0.0011960104,0.0002894199],"domain_scores_gemma":[0.99797404,0.00083015126,0.00002686343,0.00013965405,0.0005903341,0.00043895908],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001144667,0.000049780087,0.000069863985,0.00011225514,0.0007820532,0.00015497682,0.00054624345,0.00004265014,0.0055998126],"category_scores_gemma":[0.0008683783,0.000041131607,0.000029689365,0.00085294957,0.00013742669,0.00008933869,0.00005950537,0.00021774549,0.00041413293],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066722832,0.00009117053,0.39772364,0.000003881793,0.000018984798,1.11955735e-7,0.0281083,0.000004223359,0.00006837858,0.05940507,0.51264024,0.0019293098],"study_design_scores_gemma":[0.0000526167,0.000025685185,0.6982134,0.000009654182,0.0000037827217,2.5920048e-8,0.03146914,0.000029336197,0.000015498636,0.002571073,0.267554,0.00005581233],"about_ca_topic_score_codex":0.51363313,"about_ca_topic_score_gemma":0.4243149,"teacher_disagreement_score":0.6848197,"about_ca_system_score_codex":0.00036147417,"about_ca_system_score_gemma":0.015859146,"threshold_uncertainty_score":0.9953092},"labels":[],"label_agreement":null},{"id":"W3095528190","doi":"10.1177/016146812012201115","title":"“The Tail Wagging the Dog”: High-Stakes Testing as a Mediating Context in Secondary Literacy-Related","year":2020,"lang":"en","type":"article","venue":"Teachers College Record The Voice of Scholarship in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Psychology; Test (biology); Curriculum; Graduation (instrument); Focus group; Literacy; Qualitative research; Mathematics education; Standardized test; Distress; Pedagogy; Medical education; Medicine; Sociology; Clinical psychology","score_opus":0.03671470962516018,"score_gpt":0.340418104589002,"score_spread":0.30370339496384186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095528190","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9501089,0.0014579978,0.000001154408,0.029993482,0.0009383131,0.0007939014,0.0000030668311,0.000044697117,0.016658485],"genre_scores_gemma":[0.99745184,0.0001493855,0.00037208633,0.00067850266,0.00033494015,0.00010540904,0.0000049725386,0.000019979261,0.0008828588],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99675286,0.0014390992,0.00062167837,0.00027612,0.0005207515,0.00038948187],"domain_scores_gemma":[0.99531883,0.0036858127,0.00047522364,0.00023967418,0.0001912167,0.0000892186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055723824,0.00016390452,0.00021509391,0.000102102684,0.0009915378,0.000290543,0.000942346,0.00012575371,0.00007116592],"category_scores_gemma":[0.00657082,0.00010874194,0.00006599062,0.0018805534,0.0002946363,0.0007603067,0.00008887824,0.0011479087,0.00003823188],"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":[0.00005157997,0.00013849461,0.38038734,0.000021832015,0.00003764842,0.0000017634308,0.3106695,0.000009161865,0.0004435555,0.0071700043,0.00058588065,0.30048323],"study_design_scores_gemma":[0.0007615423,0.00008087306,0.3707136,0.00031793077,0.000037562957,0.000001209683,0.60298157,0.0003208291,0.000061448896,0.005394019,0.019073779,0.0002556254],"about_ca_topic_score_codex":0.0049806065,"about_ca_topic_score_gemma":0.0034026492,"teacher_disagreement_score":0.3002276,"about_ca_system_score_codex":0.0003500654,"about_ca_system_score_gemma":0.0012160572,"threshold_uncertainty_score":0.786636},"labels":[],"label_agreement":null},{"id":"W3096093179","doi":"10.5206/cjsotl-rcacea.2020.2.8009","title":"Moving Forward or Holding Back? Creating a Culture of Academic Assessment","year":2020,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Skepticism; Resistance (ecology); Liberal arts education; Perception; Space (punctuation); Psychology; Medical education; The arts; Higher education; Pedagogy; Sociology; Political science; Medicine; Computer science","score_opus":0.08040758083284723,"score_gpt":0.39121290642895906,"score_spread":0.31080532559611185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096093179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96782124,0.001828396,0.0016436321,0.014224657,0.00036846168,0.00046561897,0.0000060195816,0.000021359314,0.013620603],"genre_scores_gemma":[0.99528515,0.000115256335,0.0022050294,0.0003136242,0.0005292827,0.0000031679547,8.803521e-7,0.000015091161,0.0015324897],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9978525,0.0009815057,0.00031008606,0.00012263466,0.0003657997,0.0003674763],"domain_scores_gemma":[0.9979173,0.001183506,0.00038684052,0.00007326777,0.00010785424,0.00033126227],"candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008875833,0.0001131685,0.00020808594,0.0000647187,0.0071384967,0.00036896628,0.0006042612,0.00010548296,0.0000891982],"category_scores_gemma":[0.0049365773,0.00006524492,0.00012477096,0.00016708515,0.00020457755,0.00034833443,0.000040909254,0.0033902035,0.0000010099923],"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":[0.00016661527,0.0000103103375,0.31628186,0.0001296865,0.00038988804,0.0000069240878,0.60008633,0.002487076,0.0023123648,0.02274004,0.0010591259,0.05432978],"study_design_scores_gemma":[0.0020521893,0.0009690184,0.06498034,0.001468828,0.0006152534,0.000049140763,0.7365669,0.004606767,0.00009575712,0.0032745202,0.18467836,0.0006429234],"about_ca_topic_score_codex":0.006358937,"about_ca_topic_score_gemma":0.0047239973,"teacher_disagreement_score":0.2513015,"about_ca_system_score_codex":0.00011004674,"about_ca_system_score_gemma":0.00062887056,"threshold_uncertainty_score":0.998909},"labels":[],"label_agreement":null},{"id":"W3096667251","doi":"10.1075/itl.20006.rez","title":"Peer and teacher assessment of second-language writing in high- and low-stakes conditions","year":2020,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Psychology; Rasch model; Peer assessment; Writing assessment; Consistency (knowledge bases); Inter-rater reliability; Variation (astronomy); Rating scale; Mathematics education; English language; Peer evaluation; Medical education; Developmental psychology; Medicine; Higher education; Computer science","score_opus":0.025057942438654435,"score_gpt":0.3707478996727184,"score_spread":0.3456899572340639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096667251","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4397283,0.0126857525,0.000040212904,0.0017962967,0.000184531,0.0011283566,0.00010448631,0.0000410279,0.5442911],"genre_scores_gemma":[0.9924665,0.004737506,0.0019920114,0.0004020122,0.0002469638,0.000011891854,0.000020367803,0.000008090163,0.000114639166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989424,0.00004469359,0.0003860942,0.00015776537,0.00033547656,0.00013357593],"domain_scores_gemma":[0.9993304,0.0001829783,0.00019203019,0.00007827915,0.00014243904,0.00007387624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007129246,0.000090039015,0.0003490303,0.000030426536,0.00006310609,0.000020351228,0.000103584855,0.000047110876,0.00032906845],"category_scores_gemma":[0.0009319531,0.00008825362,0.000027786497,0.0001671825,0.00018060759,0.000013042616,0.00005260376,0.00013098022,0.0000014913936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016549924,0.0002674828,0.05673374,0.013721429,0.000104307706,0.00001719382,0.03554767,0.0000032063194,0.0018766029,0.8777627,0.0062455917,0.0077035283],"study_design_scores_gemma":[0.005581974,0.0004243424,0.40637875,0.015391378,0.0010320211,0.0000012587058,0.14970459,0.00067400536,0.00071402045,0.007632767,0.41048256,0.0019823317],"about_ca_topic_score_codex":0.00006386395,"about_ca_topic_score_gemma":0.00006595807,"teacher_disagreement_score":0.87012994,"about_ca_system_score_codex":0.000018529669,"about_ca_system_score_gemma":0.00008135935,"threshold_uncertainty_score":0.3603069},"labels":[],"label_agreement":null},{"id":"W3096866469","doi":"10.5539/ijel.v11n1p68","title":"Washback in Language Testing: An Exploration with a Focus on a Specific EFL Context in Oman","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Tourism; Language assessment; Psychology; Focus (optics); Section (typography); Mathematics education; English language; Construct (python library); Language education; Pedagogy; Computer science; Political science; Geography","score_opus":0.07812477684966987,"score_gpt":0.3580429468002768,"score_spread":0.2799181699506069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096866469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79262537,0.00016075723,0.00032641203,0.0012052308,0.0053949743,0.0002741728,0.0000109955645,0.000043568383,0.1999585],"genre_scores_gemma":[0.9897935,0.000033639903,0.0012634525,0.00021746517,0.008653504,0.0000016853711,0.0000038761495,0.00001045868,0.000022430953],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99859667,0.00009707579,0.00036102496,0.00012089712,0.0006876157,0.00013671003],"domain_scores_gemma":[0.996084,0.00025815133,0.00024384359,0.000048854017,0.0032637108,0.00010148922],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00043107875,0.00008769991,0.00015297621,0.00016494669,0.000033691354,0.00013990929,0.0003726252,0.000046410565,0.000045972374],"category_scores_gemma":[0.018466234,0.000079592566,0.000030452458,0.0002535874,0.000054846623,0.00021064053,0.000021484491,0.00027696247,0.00000572709],"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":[0.0019885367,0.0014145771,0.3646983,0.000014040689,0.0001298645,0.0020868608,0.46798974,0.0026542488,0.00016221342,0.1355203,0.003914149,0.019427188],"study_design_scores_gemma":[0.017015263,0.004826088,0.08153233,0.0013306703,0.00006683289,0.0000040436307,0.519507,0.0019956029,0.0007030437,0.008846252,0.36288658,0.0012862795],"about_ca_topic_score_codex":0.00015341605,"about_ca_topic_score_gemma":0.0012249734,"teacher_disagreement_score":0.35897243,"about_ca_system_score_codex":0.00016179756,"about_ca_system_score_gemma":0.00013802803,"threshold_uncertainty_score":0.98980165},"labels":[],"label_agreement":null},{"id":"W3108940771","doi":"10.4018/978-1-7998-3473-1.ch019","title":"Automating the Generation of Test Items","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in logistics, operations, and management science book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Computer science; Domain (mathematical analysis); Data science; Machine learning; Artificial intelligence; Information retrieval; Mathematics","score_opus":0.04221560599566671,"score_gpt":0.3313379888908244,"score_spread":0.2891223828951577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108940771","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025907908,0.0058661285,0.0025765083,0.002679468,0.0007571763,0.0010375989,0.00001960254,0.00005724392,0.9869804],"genre_scores_gemma":[0.08852676,0.3302948,0.018078811,0.001695139,0.0012766656,0.00016886687,0.0000771027,0.000047623544,0.55983424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983163,0.000027478089,0.0004153036,0.00039132038,0.0006333097,0.00021630972],"domain_scores_gemma":[0.9993272,0.00011826928,0.00016982952,0.00020485463,0.00012676661,0.000053101347],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007823466,0.00017728683,0.00022226623,0.00014037892,0.0011298716,0.00031202854,0.0004828892,0.000060096005,0.000070167305],"category_scores_gemma":[0.0002939786,0.00014468111,0.0000315834,0.0001503547,0.002944719,0.0016954059,0.0002178945,0.00012737811,0.0000094769675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022258673,0.000010590393,0.00046353228,0.00004657165,0.0000074802874,0.0000029047148,0.0018112928,0.0005333659,0.00002752402,0.99302506,0.00033288175,0.0037365663],"study_design_scores_gemma":[0.00027541808,0.00017317494,0.0009921371,0.00025951164,0.000093792616,9.0615544e-7,0.0076163383,0.0025078172,0.000043498258,0.019909678,0.9675831,0.0005445864],"about_ca_topic_score_codex":0.000054127304,"about_ca_topic_score_gemma":0.0021575221,"teacher_disagreement_score":0.9731154,"about_ca_system_score_codex":0.00009163886,"about_ca_system_score_gemma":0.00012485901,"threshold_uncertainty_score":0.9997687},"labels":[],"label_agreement":null},{"id":"W3109481489","doi":"10.18806/tesl.v37i2.1333","title":"The Amount and Usefulness of Written Corrective Feedback Across Different Educational Contexts and Levels","year":2020,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corrective feedback; Psychology; Mathematics education; Humanities; Art","score_opus":0.03637841302817352,"score_gpt":0.31789534108808604,"score_spread":0.2815169280599125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109481489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97472984,0.0031872906,0.000010118802,0.020819683,0.00048147832,0.000114974275,0.000025036818,0.000003441194,0.0006281292],"genre_scores_gemma":[0.9964298,0.000110103654,0.000010768227,0.0028562052,0.0002993312,0.0000031691168,6.25729e-7,0.0000049928935,0.00028500595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988635,0.00010229103,0.00018489291,0.00010580152,0.0005109443,0.0002325542],"domain_scores_gemma":[0.9989465,0.00045528056,0.00014989573,0.000041417203,0.00017571985,0.00023117867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030886693,0.00008414867,0.00014332027,0.000009416404,0.0010460248,0.0001928031,0.00018444638,0.000028222039,0.00059878355],"category_scores_gemma":[0.00021520072,0.000058123696,0.00002230412,0.00009117772,0.00028580503,0.00010454746,0.0000568437,0.0001828969,4.196937e-7],"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":[0.0002092309,0.000103970946,0.6946209,0.00003145244,0.00038221755,0.00001913236,0.13935088,0.0000047899257,0.00044543072,0.025244132,0.109120876,0.030467007],"study_design_scores_gemma":[0.00041565023,0.000038725982,0.9552731,0.000016283158,0.000015071244,0.000007643221,0.03062943,0.0000121407675,0.000044083892,0.0006842623,0.012768949,0.00009465406],"about_ca_topic_score_codex":0.044327892,"about_ca_topic_score_gemma":0.30786613,"teacher_disagreement_score":0.26353824,"about_ca_system_score_codex":0.00015019329,"about_ca_system_score_gemma":0.00087182724,"threshold_uncertainty_score":0.962036},"labels":[],"label_agreement":null},{"id":"W3109962707","doi":"10.18806/tesl.v37i2.1339","title":"Dynamic Written Corrective Feedback among Graduate Students: The Effects of Feedback Timing","year":2020,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Brigham Young University","keywords":"Corrective feedback; Fluency; Grammar; Peer feedback; Psychology; Curriculum; Linguistics; Computer science; Mathematics education; Pedagogy; Philosophy","score_opus":0.023733882282623613,"score_gpt":0.3048955972167413,"score_spread":0.2811617149341177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109962707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844944,0.002152342,0.000095021736,0.007324896,0.0018803733,0.00052171113,0.0000064010237,0.000033503933,0.0034913656],"genre_scores_gemma":[0.99177736,0.00019764321,0.00006815073,0.007006399,0.00037921098,0.000007175344,0.0000016617224,0.000021378391,0.00054104725],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9966247,0.00034840926,0.00038098774,0.00021008693,0.0019247942,0.0005110118],"domain_scores_gemma":[0.99823916,0.00059694675,0.0003884201,0.00013385467,0.00028155424,0.00036007588],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000705559,0.00019247866,0.00031481066,0.000047696096,0.00093109463,0.00022746896,0.0010533711,0.00006090968,0.0011406313],"category_scores_gemma":[0.00063301815,0.00014581885,0.00012126921,0.0005308348,0.0002896391,0.0002512101,0.00013798039,0.00060548563,0.000009402927],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027951895,0.00035315612,0.39052305,0.00021531153,0.0017018564,0.0006181872,0.17055969,0.00022726582,0.0012491376,0.0007113263,0.41583857,0.017722925],"study_design_scores_gemma":[0.0017067796,0.00028054745,0.9283313,0.0002221468,0.0002496881,0.0000118717835,0.059820607,0.00041160505,0.00013535046,0.00023667578,0.008128073,0.00046536315],"about_ca_topic_score_codex":0.131387,"about_ca_topic_score_gemma":0.22633564,"teacher_disagreement_score":0.53780824,"about_ca_system_score_codex":0.0005340177,"about_ca_system_score_gemma":0.0010945566,"threshold_uncertainty_score":0.9997725},"labels":[],"label_agreement":null},{"id":"W3109972545","doi":"10.20343/teachlearninqu.9.1.20","title":"Exploring the Emotional Responses of Undergraduate Students to Assessment Feedback: Implications for Instructors","year":2021,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"MacEwan University; Ohio State University; University of Gloucestershire; Purdue University; Monash University; Leeds Beckett University","keywords":"Psychology; Summative assessment; Peer feedback; Psychological resilience; Variety (cybernetics); Social psychology; Cognition; Negative feedback; Formative assessment; Medical education; Pedagogy","score_opus":0.17912409354407574,"score_gpt":0.44624243943902614,"score_spread":0.2671183458949504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109972545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93178153,0.000040293417,0.007162285,0.058161967,0.0014401588,0.00030084114,0.0000032498194,0.000048630973,0.0010610339],"genre_scores_gemma":[0.9922998,0.00016573582,0.0031905684,0.0002750478,0.0012075448,0.000046026988,0.000004714862,0.000025611045,0.002784932],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99605024,0.0018629134,0.00046876777,0.00023193334,0.0009495745,0.0004365484],"domain_scores_gemma":[0.99715513,0.0017309671,0.00036868828,0.0002589748,0.00034431435,0.00014193072],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0058633653,0.00015828332,0.00022058304,0.00012026761,0.0049663833,0.0005934593,0.0010001778,0.00004185488,0.00003917356],"category_scores_gemma":[0.0018185835,0.00009841958,0.00021278854,0.00036572025,0.00024326764,0.00038880648,0.00026202653,0.0010127528,0.000007627411],"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":[0.00012734573,0.00033170806,0.6802977,0.00001630673,0.00053571956,0.000005194866,0.1365667,0.0033208064,0.0039319587,0.12901285,0.003532376,0.042321347],"study_design_scores_gemma":[0.0004967331,0.00011556781,0.86937153,0.00012708262,0.00008410478,0.000024842066,0.07325613,0.000022182052,0.000044804183,0.0041815545,0.052099004,0.00017646588],"about_ca_topic_score_codex":0.00007312398,"about_ca_topic_score_gemma":0.000062208666,"teacher_disagreement_score":0.18907385,"about_ca_system_score_codex":0.00030210125,"about_ca_system_score_gemma":0.0005506782,"threshold_uncertainty_score":0.996329},"labels":[],"label_agreement":null},{"id":"W3113029542","doi":"10.1007/978-3-030-56838-2_2","title":"Mathematics Teacher Education in Ontario, Canada and Mainland China","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Institute for Christian Studies","funders":"","keywords":"Certification; Mainland China; Teacher education; China; Certificate in Education; Comparative education; Position (finance); Political science; Service (business); Pedagogy; Mainland; Professional development; Education policy; Mathematics education; Higher education; Medical education; Sociology; Geography; Education; Psychology; Medicine; Business; Marketing","score_opus":0.018091966074435667,"score_gpt":0.2767506281673541,"score_spread":0.25865866209291843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113029542","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042823064,0.00006210131,0.00000368725,0.00095651386,0.00022087968,0.0002373178,0.000001278011,0.000011532311,0.99422437],"genre_scores_gemma":[0.017573018,0.00005604591,0.00040418326,0.00018464684,0.00015143788,0.000003645001,0.000013267633,0.000012070128,0.9816017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925935,0.0000095125415,0.00015084185,0.00016247404,0.00030115797,0.00011664358],"domain_scores_gemma":[0.9997318,0.000026383485,0.000068674985,0.00007180899,0.000015890813,0.000085460546],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012131586,0.00012277176,0.00017971023,0.000033598346,0.000079693964,0.000055921457,0.00011546049,0.00011678126,0.0044819447],"category_scores_gemma":[0.000011129475,0.000114588125,0.000020818256,0.000015108276,0.00004452572,0.000044270444,0.000038486018,0.00023140025,0.000010886388],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040547798,0.00005411382,0.08667565,0.000033689183,0.00003519346,0.000009300841,0.021329407,9.197937e-8,4.9522004e-7,0.79436135,0.09239303,0.0051036426],"study_design_scores_gemma":[0.00014677636,0.000012636001,0.09578598,0.000078194156,0.000033404147,4.9478626e-7,0.0036151998,0.0000029532869,1.2086649e-7,0.033227015,0.86679107,0.0003061677],"about_ca_topic_score_codex":0.9945606,"about_ca_topic_score_gemma":0.9999216,"teacher_disagreement_score":0.774398,"about_ca_system_score_codex":0.00055580836,"about_ca_system_score_gemma":0.0042508394,"threshold_uncertainty_score":0.9964281},"labels":[],"label_agreement":null},{"id":"W3116449517","doi":"10.31002/ijome.v3i2.3079","title":"Challenges with Implementing Oral Exams in Post-Secondary Mathematics Courses","year":2020,"lang":"en","type":"article","venue":"Indonesian Journal of Mathematics Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Span (engineering); Mathematics education; Attention span; Life span; Mathematics; Psychology; Medicine; Gerontology; Engineering; Cognition","score_opus":0.06228160648665003,"score_gpt":0.3619901061220255,"score_spread":0.29970849963537544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116449517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661065,0.00065584446,0.00059051637,0.017470162,0.00024305341,0.00034172364,0.0000013277364,0.00001857287,0.014572302],"genre_scores_gemma":[0.9779218,0.00028211297,0.02104247,0.00024663043,0.00042981375,0.000007793107,0.0000019340418,0.000021259872,0.00004617707],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9983179,0.00010034774,0.00061112834,0.00011338046,0.0005890974,0.00026816048],"domain_scores_gemma":[0.99850816,0.00018899978,0.0007456719,0.00010145667,0.00029746364,0.00015827008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013385928,0.00013347818,0.00030676136,0.00016053834,0.00013721187,0.00011609635,0.00034379162,0.00006045518,0.00014779896],"category_scores_gemma":[0.00021201829,0.00011092406,0.00006669419,0.00025313787,0.000079334,0.00043515002,0.000028168146,0.0002303384,0.000011134201],"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":[0.00005357421,0.0025277906,0.052951805,0.0007637211,0.00022198028,0.00003956113,0.8006657,0.00000832392,0.0005625315,0.048784524,0.001557801,0.09186271],"study_design_scores_gemma":[0.0012497724,0.00037650016,0.041654944,0.00054614077,0.00013044722,0.00005409156,0.9470789,0.000054642194,0.00017686975,0.005136808,0.0032158187,0.00032508286],"about_ca_topic_score_codex":0.000027351763,"about_ca_topic_score_gemma":0.0003393074,"teacher_disagreement_score":0.1464132,"about_ca_system_score_codex":0.000085298474,"about_ca_system_score_gemma":0.0009006349,"threshold_uncertainty_score":0.4523352},"labels":[],"label_agreement":null},{"id":"W3117672137","doi":"10.3968/11905","title":"Backwash in Higher Education: Calibrating assessment and swinging the pendulum From Summative Assessment","year":2020,"lang":"en","type":"article","venue":"Canadian social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Phenomenon; Affect (linguistics); Higher education; Pedagogy; Mathematics education; Sociology; Psychology; Formative assessment; Epistemology; Philosophy; Political science; Law","score_opus":0.059165992595048456,"score_gpt":0.3728504895420151,"score_spread":0.31368449694696665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117672137","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25431395,0.00009514691,0.00002612827,0.07842728,0.0009318694,0.0004735399,0.000016802953,0.00003658977,0.6656787],"genre_scores_gemma":[0.9940386,0.000011917898,0.0005907728,0.0040370566,0.0008887806,0.00002801025,0.000004866246,0.0000073316232,0.000392697],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99807316,0.00018818428,0.00018838003,0.00037005806,0.00064314605,0.0005370824],"domain_scores_gemma":[0.9991284,0.00013595456,0.00008874485,0.00008675424,0.00008379058,0.00047634981],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009045666,0.00011408382,0.00014549475,0.000079875055,0.002189597,0.0006752152,0.00060860976,0.00006144213,0.000816129],"category_scores_gemma":[0.000060949278,0.00010300745,0.000031128875,0.0012305995,0.0008304195,0.0006188083,0.00010507553,0.0002602326,0.000009440249],"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":[0.0000011606282,0.000021669903,0.6700149,0.000003944785,0.000009604328,0.000006033014,0.060861595,9.708933e-7,0.00034872917,0.25813,0.0030645626,0.0075368118],"study_design_scores_gemma":[0.0001806407,0.000012716279,0.81733054,0.000020965195,0.000010643681,6.1471475e-8,0.13443004,0.00021767759,0.000005402712,0.0012174321,0.046350718,0.00022316755],"about_ca_topic_score_codex":0.085085005,"about_ca_topic_score_gemma":0.07411961,"teacher_disagreement_score":0.73972464,"about_ca_system_score_codex":0.0010745877,"about_ca_system_score_gemma":0.004898382,"threshold_uncertainty_score":0.9991094},"labels":[],"label_agreement":null},{"id":"W3117676024","doi":"10.1002/jee.20376","title":"Peer review as developmental: Exploring the ripple effects of the <scp><i>JEE</i></scp> Mentored Reviewer Program","year":2020,"lang":"en","type":"article","venue":"Journal of Engineering Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Peer mentoring; Ripple; Psychology; Medical education; Engineering; Pedagogy; Medicine","score_opus":0.039213288960016884,"score_gpt":0.3378162465782725,"score_spread":0.2986029576182556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117676024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83532465,0.07098719,0.00019595736,0.06077386,0.016225856,0.0039421623,0.0000011555303,0.00011138438,0.012437805],"genre_scores_gemma":[0.92302865,0.052248307,0.0091616325,0.003367985,0.0048975665,0.00043162212,0.0000056015624,0.00007154671,0.0067870845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985765,0.00008326305,0.00032343905,0.00006919781,0.000808618,0.00013896641],"domain_scores_gemma":[0.9988061,0.00019374673,0.00028975273,0.000079803256,0.0005457441,0.00008480801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010231662,0.00008619753,0.00017826965,0.000026896123,0.00010868778,0.000050580682,0.00038474653,0.000022134242,0.000014419141],"category_scores_gemma":[0.0051047504,0.000052481184,0.00012474117,0.00046099012,0.0000261354,0.0002268115,0.00003737852,0.00017569184,0.000007212771],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005702489,0.00071496237,0.016913781,0.0059697665,0.0004569797,0.000003074449,0.13634726,0.00010428608,0.004979033,0.0038149417,0.7328022,0.09788801],"study_design_scores_gemma":[0.00010342117,0.00005046827,0.018355208,0.001960292,0.000102345,0.000002350199,0.0029724739,0.000006039222,0.0007560208,0.000020971012,0.97563404,0.00003637125],"about_ca_topic_score_codex":0.00001603676,"about_ca_topic_score_gemma":0.000001839249,"teacher_disagreement_score":0.24283184,"about_ca_system_score_codex":0.00010757857,"about_ca_system_score_gemma":0.00035510416,"threshold_uncertainty_score":0.6111232},"labels":[],"label_agreement":null},{"id":"W3117986551","doi":"10.22215/etd/2019-13853","title":"An Investigation of Jordanian English as a Foreign Language (EFL) Teachers' Perceptions of and Practices in Classroom Assessment","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Active listening; Perception; Psychology; Variety (cybernetics); English as a foreign language; Mathematics education; Reading (process); Foreign language; Pedagogy; English language; Medical education; Computer science; Medicine; Political science","score_opus":0.02351437807181366,"score_gpt":0.4057533098005282,"score_spread":0.38223893172871454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117986551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8216195,0.000056371093,0.0000042899933,0.000045051234,0.0001445676,0.00052498025,0.0000070123547,0.000023333838,0.17757489],"genre_scores_gemma":[0.9897917,0.00018597908,0.0015266304,0.00002013692,0.00010725725,0.000029440134,0.00040391972,0.000016733062,0.007918237],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9982151,0.00033658813,0.00039439346,0.00029318064,0.00057865813,0.00018212372],"domain_scores_gemma":[0.9984553,0.00020855629,0.0008391087,0.00018848806,0.00022760713,0.00008092843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009698808,0.00016040755,0.00033203303,0.00025975742,0.00009419817,0.0000837155,0.00025036396,0.00030098186,0.0004873897],"category_scores_gemma":[0.00022264046,0.00015918999,0.000060800267,0.0002937516,0.000113029964,0.00066303374,0.000017592336,0.000273515,0.000003855676],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019633604,0.000112893125,0.65348285,0.00009045733,0.00003475921,6.7883633e-7,0.32524478,0.0000012305063,0.0037726408,0.015551339,0.00008722712,0.0016014813],"study_design_scores_gemma":[0.0002574824,0.0001193686,0.3773087,0.000082428145,0.000055210105,5.117467e-8,0.62154824,0.00004160475,0.00007941152,0.0003295229,0.000057944402,0.00012002515],"about_ca_topic_score_codex":0.013967808,"about_ca_topic_score_gemma":0.044446874,"teacher_disagreement_score":0.29630345,"about_ca_system_score_codex":0.00010407199,"about_ca_system_score_gemma":0.00056653906,"threshold_uncertainty_score":0.99259824},"labels":[],"label_agreement":null},{"id":"W3118099899","doi":"10.5539/ijel.v11n1p206","title":"A Study on APSACS Karachi Zone ESL Teachers’ Notion About Assessment and Its Numerous Employment in English Pedagogy","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Likert scale; Summative assessment; Pedagogy; Mathematics education; Medical education; Medicine","score_opus":0.05076778133382033,"score_gpt":0.4085462471080892,"score_spread":0.35777846577426886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118099899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93512505,0.00018889987,0.00015826941,0.00061728456,0.013331093,0.00039699135,0.000014504845,0.000047726575,0.050120194],"genre_scores_gemma":[0.98421645,0.00016915878,0.00032896877,0.0003556405,0.01479861,0.0000055366795,0.000004931209,0.000017269922,0.00010341868],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99724174,0.00025816113,0.0006521742,0.00022420268,0.0013966407,0.00022706673],"domain_scores_gemma":[0.9937227,0.00031755434,0.00044483042,0.00006790324,0.0052141836,0.00023284188],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001100514,0.00016699503,0.00029251096,0.00019332855,0.00011243214,0.00024251369,0.0005012933,0.00008774209,0.000084887346],"category_scores_gemma":[0.025151588,0.00016568402,0.00008142869,0.00016702455,0.00005149206,0.00013596559,0.00010291937,0.0005639114,0.0000041986823],"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":[0.0003181687,0.0025355744,0.46443605,0.000009390619,0.00049325125,0.00044736578,0.49988022,0.00061674137,0.000015629521,0.025761299,0.0020960781,0.0033902088],"study_design_scores_gemma":[0.00846739,0.0026734541,0.47374088,0.00024032396,0.00022459452,0.0000013755874,0.19414103,0.00032725142,0.00003545106,0.0003419519,0.3191175,0.0006888306],"about_ca_topic_score_codex":0.00007543773,"about_ca_topic_score_gemma":0.0001592334,"teacher_disagreement_score":0.3170214,"about_ca_system_score_codex":0.00036611347,"about_ca_system_score_gemma":0.0003317398,"threshold_uncertainty_score":0.98306},"labels":[],"label_agreement":null},{"id":"W3119940242","doi":"10.5539/ijel.v11n1p266","title":"The Practice of Cross-Grading in Assessing Writing: The Case of EFL Teachers and Students in a Saudi Arabian Context","year":2021,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; English as a foreign language; Mathematics education; English language; Context (archaeology); Perception; Pedagogy; Medical education; Medicine","score_opus":0.03303773342466218,"score_gpt":0.43774144187120445,"score_spread":0.40470370844654224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119940242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97196436,0.00078262726,0.000017309614,0.0003521623,0.0030258428,0.00006428391,0.000002214076,0.0000019652587,0.023789236],"genre_scores_gemma":[0.99768597,0.0003905104,0.00037371847,0.00006109599,0.0014340931,7.4573e-7,4.363813e-7,0.000005114193,0.00004830126],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9981889,0.0003216315,0.0006366604,0.00007939711,0.00064704655,0.00012633833],"domain_scores_gemma":[0.98825055,0.0031142577,0.0006893236,0.00006475295,0.007844454,0.000036631995],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035137085,0.00006339874,0.00015804284,0.00008438309,0.00012900156,0.00039411912,0.00040826036,0.000046434212,0.0000069674697],"category_scores_gemma":[0.13097903,0.000047502625,0.00005538257,0.00017892987,0.00027790607,0.00016473337,0.00009738514,0.00034140682,8.4183796e-8],"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":[0.000059518123,0.00025062513,0.912468,0.0000069273606,0.0001518884,0.000998399,0.05830419,0.000075282864,0.000022037659,0.023667656,0.00013409548,0.003861373],"study_design_scores_gemma":[0.002875755,0.00007803881,0.21749838,0.0006727789,0.000095772615,0.000062983796,0.7002289,0.00013137155,0.0001721911,0.002410467,0.07559573,0.00017761164],"about_ca_topic_score_codex":0.00047971404,"about_ca_topic_score_gemma":0.0017290186,"teacher_disagreement_score":0.69496965,"about_ca_system_score_codex":0.00012736343,"about_ca_system_score_gemma":0.00023765594,"threshold_uncertainty_score":0.8763411},"labels":[],"label_agreement":null},{"id":"W3122537597","doi":"10.5430/jnep.v11n5p54","title":"Nursing student perception and performance with collaborative testing","year":2021,"lang":"en","type":"article","venue":"Journal of Nursing Education and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Psychology; Medical education; Test (biology); Nursing; Medicine","score_opus":0.08733587536504024,"score_gpt":0.48235061016355796,"score_spread":0.39501473479851773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122537597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88522315,0.0010847633,0.0001000773,0.015818989,0.0006415204,0.00006546471,1.3187001e-7,0.0000052048654,0.097060695],"genre_scores_gemma":[0.97762614,0.0011771382,0.02002066,0.00020947063,0.00042667403,8.3980314e-7,4.6326556e-7,0.00000415404,0.0005344617],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99914724,0.0002609997,0.00013519313,0.00007660436,0.00029377535,0.00008621906],"domain_scores_gemma":[0.998214,0.00043989418,0.00028303845,0.000032999156,0.00095337763,0.00007670081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007213688,0.000050181603,0.00008376132,0.0000514761,0.0006328805,0.00021162891,0.000035877034,0.00002766643,0.00001812486],"category_scores_gemma":[0.0005684204,0.000043767363,0.000007932274,0.00030144837,0.00012319868,0.0009948824,0.000004820653,0.00013214114,6.610549e-7],"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":[0.00019632904,0.0010256637,0.05406141,0.000012112324,0.000040572162,0.0000052539167,0.43541962,0.0000037174086,0.0010363875,0.001463736,0.0016937926,0.5050414],"study_design_scores_gemma":[0.0002717516,0.00024167939,0.33105126,0.00074177515,0.00014103898,0.00045098524,0.6572231,0.000012682258,0.000016894333,0.00011860681,0.009653764,0.00007643945],"about_ca_topic_score_codex":0.00000842642,"about_ca_topic_score_gemma":0.0000043735877,"teacher_disagreement_score":0.50496495,"about_ca_system_score_codex":0.00016788892,"about_ca_system_score_gemma":0.0009040307,"threshold_uncertainty_score":0.48676687},"labels":[],"label_agreement":null},{"id":"W3128610517","doi":"10.1016/j.stueduc.2021.100977","title":"The long-term washback effects of the National Matriculation English Test on college English learning in China: Tertiary student perspectives","year":2021,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Matriculation; Active listening; Competence (human resources); Psychology; Test (biology); College English; Curriculum; Perception; Mathematics education; China; Medical education; Pedagogy; Medicine; Political science","score_opus":0.031240674061682346,"score_gpt":0.419786253443572,"score_spread":0.38854557938188966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128610517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98097533,0.0020698472,5.6310716e-7,0.0037720778,0.002308043,0.0009357651,0.000002761888,0.000012645534,0.009922994],"genre_scores_gemma":[0.99689007,0.00072531763,0.000024096244,0.000042928925,0.0009575095,0.00030140812,0.000014403374,0.0000074431127,0.0010368525],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964652,0.0009977238,0.00034138083,0.00026832134,0.00173321,0.00019413515],"domain_scores_gemma":[0.9937923,0.0039099692,0.00021265895,0.00010674474,0.001957797,0.000020551754],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026556675,0.00011838742,0.00014805216,0.0001058725,0.000732247,0.000053543412,0.00023295468,0.000055615576,0.000050944927],"category_scores_gemma":[0.02011385,0.00008689506,0.00007141533,0.000895014,0.000279045,0.00019478962,0.00010467049,0.00020326994,0.0000030999636],"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":[0.000007635882,0.0005537834,0.8097692,0.000022435055,0.000054479246,3.6229147e-7,0.17357905,0.00090828346,0.000028183367,0.014033242,0.00069848716,0.0003448444],"study_design_scores_gemma":[0.00054839527,0.000023550312,0.8842094,0.00013739815,0.00002734641,1.3445455e-7,0.112840556,0.00006991737,0.000043873784,0.0019290777,0.00008752631,0.00008283731],"about_ca_topic_score_codex":0.000023572977,"about_ca_topic_score_gemma":0.0012807475,"teacher_disagreement_score":0.07444018,"about_ca_system_score_codex":0.0014457525,"about_ca_system_score_gemma":0.00096099323,"threshold_uncertainty_score":0.98814017},"labels":[],"label_agreement":null},{"id":"W3128960566","doi":"10.18733/cpi29569","title":"All that Glitters is not Gold: Culturally responsive online Assessment and Pedagogy in uncertain times","year":2021,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Pedagogy; Psychology","score_opus":0.5374877977163827,"score_gpt":0.554900221389048,"score_spread":0.017412423672665378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128960566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9574883,0.0010891107,0.00000387504,0.03563501,0.00030760656,0.00021439059,0.00002318777,0.000046792393,0.0051917527],"genre_scores_gemma":[0.9674003,0.004760468,0.0009466818,0.0060175196,0.0005631607,0.000018062645,0.00010481397,0.000009638777,0.020179313],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99780566,0.0003954581,0.0002819194,0.00054081593,0.0004991025,0.000477053],"domain_scores_gemma":[0.9991103,0.00028032716,0.00008656351,0.00012396013,0.0001579255,0.00024094732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036613236,0.00024472468,0.00035862942,0.000047493693,0.00027575792,0.00032106045,0.00018833819,0.00020380109,0.0007364062],"category_scores_gemma":[0.00009969535,0.00017019286,0.00009024166,0.00022976473,0.00060766767,0.000427607,0.00022571003,0.00032110713,0.000013814579],"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":[0.0004608985,0.0007179688,0.26391855,0.000099084325,0.00025679596,0.00071490364,0.6177774,0.000007323943,0.010264106,0.04135707,0.03994004,0.02448583],"study_design_scores_gemma":[0.0011210656,0.00011158343,0.42101118,0.000068294634,0.00005259681,0.00001880605,0.39529505,0.000043928674,0.00010740816,0.00079261104,0.18088658,0.0004908889],"about_ca_topic_score_codex":0.00071215665,"about_ca_topic_score_gemma":0.001128283,"teacher_disagreement_score":0.22248237,"about_ca_system_score_codex":0.00010708932,"about_ca_system_score_gemma":0.00015906605,"threshold_uncertainty_score":0.8063131},"labels":[],"label_agreement":null},{"id":"W3131800560","doi":"10.29173/isotl532","title":"Conversations and Reflections on Authentic Assessment","year":2021,"lang":"en","type":"article","venue":"Imagining SoTL","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"ROWE; Taxonomy (biology); Point (geometry); Computer science; Sociology; Mathematics education; Pedagogy; Knowledge management; Engineering ethics; Psychology; Management; Engineering","score_opus":0.061162770415292445,"score_gpt":0.44456000084983166,"score_spread":0.3833972304345392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131800560","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13794835,0.00010614537,0.0010020258,0.04760139,0.0014413995,0.00015667832,0.000004559942,0.00020452085,0.81153494],"genre_scores_gemma":[0.9889771,0.000058077632,0.0023478523,0.0004543494,0.00015888346,0.000010718638,0.0000054533984,0.0000065073473,0.007981064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992529,0.000096348806,0.000085340274,0.00016481515,0.00023560478,0.00016498253],"domain_scores_gemma":[0.9995863,0.00014487597,0.000032906642,0.00009718465,0.000075189055,0.0000635428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022390933,0.00005588978,0.00007087202,0.000045536854,0.0005881537,0.00018799161,0.000062350184,0.000026683929,0.00052623445],"category_scores_gemma":[0.00008143371,0.00006136977,0.000029344495,0.00021010193,0.0001310941,0.00013381048,0.000031248244,0.0001102091,0.000052477026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060259686,0.00021956937,0.12923265,0.000008605328,0.0001003283,0.000032851516,0.07103013,0.000006415553,0.0016035184,0.78420925,0.0076418947,0.005908783],"study_design_scores_gemma":[0.0012718454,0.000112245005,0.25955763,0.00008357382,0.00013904268,0.0000061222204,0.15559356,0.00033211132,0.00031657875,0.01132385,0.57077664,0.00048679663],"about_ca_topic_score_codex":0.0002184273,"about_ca_topic_score_gemma":0.00035335714,"teacher_disagreement_score":0.85102874,"about_ca_system_score_codex":0.00007191242,"about_ca_system_score_gemma":0.00020970368,"threshold_uncertainty_score":0.5761898},"labels":[],"label_agreement":null},{"id":"W3133706844","doi":"10.1017/9781108589789.027","title":"Teachers’ and Students’ Beliefs and Perspectives about Corrective Feedback","year":2021,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Victoria","funders":"","keywords":"Corrective feedback; Situational ethics; Psychology; Mathematics education; Social psychology","score_opus":0.03148769182241588,"score_gpt":0.26908976789327804,"score_spread":0.23760207607086217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133706844","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008836271,0.0023347973,0.000023992261,0.00007978122,0.0002953058,0.0005587288,0.00006553767,0.000101350444,0.9877042],"genre_scores_gemma":[0.011947253,0.003996466,0.00007173544,0.00004294591,0.00032333203,0.000001226689,0.000014736957,0.00003570447,0.9835666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99795216,0.0001382188,0.0001505783,0.00075600616,0.00064204825,0.00036098415],"domain_scores_gemma":[0.998846,0.00016359937,0.00019180212,0.00025634607,0.00026495368,0.00027733354],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026934783,0.0003759333,0.0004829292,0.00015267661,0.0008450185,0.00030240358,0.00045500472,0.00042071566,0.00003269754],"category_scores_gemma":[0.000031740383,0.00046242453,0.00013857949,0.000019031904,0.0011850283,0.00017904486,0.0007256666,0.0005493829,0.000007077148],"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":[0.000053190284,0.00003893538,0.0015470351,0.000029539555,0.0005078241,0.00018378094,0.056518365,6.383076e-8,0.000010379289,0.9261174,0.012368107,0.002625357],"study_design_scores_gemma":[0.001080042,0.00007103123,0.01531197,0.00025188082,0.00038168542,0.0000053502777,0.06660604,0.0000011284424,0.000006755332,0.000015205898,0.915587,0.0006819098],"about_ca_topic_score_codex":0.0011007442,"about_ca_topic_score_gemma":0.00015239093,"teacher_disagreement_score":0.9261022,"about_ca_system_score_codex":0.0003879552,"about_ca_system_score_gemma":0.00019788858,"threshold_uncertainty_score":0.99978274},"labels":[],"label_agreement":null},{"id":"W3135544085","doi":"10.5430/elr.v10n1p1","title":"Construction and Application of OBE-based Multiple Formative Assessment System in the “Micro-lecture + PAD Class”","year":2021,"lang":"en","type":"article","venue":"English Linguistics Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Enthusiasm; Construct (python library); Class (philosophy); Computer science; Mathematics education; Curriculum; Quality (philosophy); Psychology; Pedagogy; Artificial intelligence","score_opus":0.038455158807855175,"score_gpt":0.4054706823467402,"score_spread":0.36701552353888506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135544085","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5086582,0.00080717244,0.023826761,0.0010761273,0.003331972,0.0034960294,0.00010909697,0.00016570576,0.458529],"genre_scores_gemma":[0.9954526,0.000050888535,0.0037292421,0.000018102455,0.0006328927,0.000058120448,0.000027505866,0.0000061431374,0.000024528943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99760836,0.0008382664,0.00023047692,0.00018749178,0.0008689674,0.00026641393],"domain_scores_gemma":[0.9951835,0.0015734901,0.000081401085,0.00018461805,0.002930109,0.00004685138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029261808,0.000070808695,0.00013805773,0.00011605155,0.0004302648,0.000142342,0.00021830665,0.000101752965,0.00000890072],"category_scores_gemma":[0.008079805,0.000059267713,0.000029641738,0.00073127827,0.00038446276,0.00003242414,0.00006189148,0.00042658378,0.0000017024357],"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":[0.000064855776,0.00039768117,0.38994294,0.00048424993,0.000053790416,0.000020254403,0.10977583,0.00019189344,0.0010718172,0.49024498,0.0015089547,0.00624275],"study_design_scores_gemma":[0.0024901638,0.00016779896,0.050935183,0.00028597083,0.00003907135,8.4782886e-7,0.63578564,0.01611625,0.003547831,0.0030959733,0.28717688,0.00035836315],"about_ca_topic_score_codex":0.00045366443,"about_ca_topic_score_gemma":0.0010734439,"teacher_disagreement_score":0.52600986,"about_ca_system_score_codex":0.00022457528,"about_ca_system_score_gemma":0.00045056775,"threshold_uncertainty_score":0.9672865},"labels":[],"label_agreement":null},{"id":"W3135578950","doi":"10.1016/j.tate.2021.103316","title":"Toward a pedagogy for slow and significant learning about assessment in teacher education","year":2021,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Coursework; Mathematics education; Teacher preparation; Teacher education; Psychology; Pedagogy; Higher education; Institution; Taxonomy (biology); Sociology; Political science","score_opus":0.04098595074252736,"score_gpt":0.4212046423058825,"score_spread":0.38021869156335514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135578950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95202076,0.0012279731,0.0007690315,0.0074495086,0.0005378296,0.0004161969,6.729316e-7,0.000061362734,0.037516646],"genre_scores_gemma":[0.9593176,0.00020637721,0.0043912795,0.0001925589,0.00062224845,0.00016960337,0.000050177572,0.000017445149,0.035032663],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99824727,0.0006792753,0.00022357576,0.00037062494,0.00020929438,0.00026995112],"domain_scores_gemma":[0.99941313,0.00018084665,0.00010735526,0.000106862055,0.0000813958,0.00011039002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019249637,0.00013517689,0.00017728949,0.00011590812,0.00060047786,0.00025872726,0.0000883876,0.00011247695,0.000083951185],"category_scores_gemma":[0.00043864228,0.00014416524,0.00003905476,0.0001195278,0.000071068476,0.00025428683,0.0000358508,0.0005613336,0.0000023965065],"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":[0.000008608307,0.0008891659,0.3909735,0.00004571,0.000013553976,3.3779372e-7,0.10560159,0.0000018391016,0.00047395262,0.015808173,0.0015127638,0.48467082],"study_design_scores_gemma":[0.0004527539,0.000053369262,0.6444274,0.00010406709,0.000054478205,0.0000023516186,0.23667412,0.00023239083,0.000011241434,0.0021717222,0.11553568,0.00028042376],"about_ca_topic_score_codex":0.004211286,"about_ca_topic_score_gemma":0.00043700682,"teacher_disagreement_score":0.48439038,"about_ca_system_score_codex":0.00022393095,"about_ca_system_score_gemma":0.0016763286,"threshold_uncertainty_score":0.63662326},"labels":[],"label_agreement":null},{"id":"W3136573347","doi":"10.1177/21582440211016838","title":"A Baseline for Multiple-Choice Testing in the University Classroom","year":2021,"lang":"en","type":"preprint","venue":"SAGE Open","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Trent University","funders":"","keywords":"Baseline (sea); Reliability (semiconductor); Context (archaeology); Test (biology); Multiple choice; Variety (cybernetics); Psychometrics; Item response theory; Psychology; Quality (philosophy); Applied psychology; Standardized test; Computer science; Medical education; Mathematics education; Statistics; Clinical psychology; Artificial intelligence; Medicine; Significant difference","score_opus":0.12406051353992756,"score_gpt":0.38601464641380895,"score_spread":0.26195413287388136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136573347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49284393,0.00063740974,0.0051485426,0.016734218,0.0022271713,0.012626559,0.00021767676,0.00014476628,0.46941975],"genre_scores_gemma":[0.9798705,0.000095971205,0.010623426,0.0004142696,0.00052096124,0.000058815916,0.00010253121,0.000014599394,0.008298899],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983835,0.00056333304,0.0001479799,0.0003646023,0.00027663214,0.00026395798],"domain_scores_gemma":[0.9957234,0.0037256002,0.00012390931,0.00028003787,0.00010501846,0.000041984953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002477158,0.00012164651,0.00021441176,0.00004261333,0.00050994265,0.0005678641,0.0018689797,0.00015415903,0.00015838078],"category_scores_gemma":[0.002805929,0.00010931678,0.000085170606,0.0003347148,0.00007289059,0.00019151553,0.0014049823,0.00035380194,0.000006222826],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006507572,0.0003423315,0.9005555,0.00009560563,0.00008378552,0.000083655745,0.060916387,0.00012564495,0.00006040515,0.0011129506,0.0066962056,0.029862447],"study_design_scores_gemma":[0.0025577846,0.00004582934,0.37100407,0.0007065193,0.00013705446,3.885871e-7,0.23367903,0.0023238994,0.0000059064187,0.00095851906,0.38791096,0.0006700217],"about_ca_topic_score_codex":0.021445243,"about_ca_topic_score_gemma":0.10961474,"teacher_disagreement_score":0.52955145,"about_ca_system_score_codex":0.00016965112,"about_ca_system_score_gemma":0.00053795456,"threshold_uncertainty_score":0.98507106},"labels":[],"label_agreement":null},{"id":"W3138121929","doi":"10.1080/13803611.2021.1902354","title":"Linking personality to teachers’ literacy in classroom assessment: a cross-cultural study","year":2020,"lang":"en","type":"article","venue":"Educational Research and Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Summative assessment; Formative assessment; Psychology; Literacy; Competence (human resources); Personality; Pedagogy; Big Five personality traits; Empathy; Mathematics education; Social psychology","score_opus":0.3451683761205265,"score_gpt":0.6177916604486202,"score_spread":0.27262328432809374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138121929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94579124,0.00008685523,0.000006110958,0.034674983,0.000114377784,0.0010386071,0.0000023977072,0.000008689523,0.018276747],"genre_scores_gemma":[0.9973008,0.000015978392,0.00041064274,0.00017834677,0.00082546595,0.00024464767,0.000042053398,0.0000050850667,0.0009769781],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99598855,0.0010107084,0.00020050327,0.0003464323,0.0021269675,0.00032681343],"domain_scores_gemma":[0.9979138,0.0006380613,0.000035489968,0.00007600218,0.0010893929,0.00024725628],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0072262613,0.00007393266,0.00009562528,0.0001254399,0.0006990921,0.00078900915,0.00020713097,0.000045075154,0.0012701683],"category_scores_gemma":[0.0022940726,0.00007151397,0.000021584885,0.00081726594,0.00013979748,0.0007060949,0.00008402336,0.00031133124,0.00008254984],"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":[0.00002413306,0.0002702442,0.80486053,0.0000042623833,0.000008065348,2.4367787e-7,0.18618186,0.000008242295,0.00007859927,0.002309792,0.00092388125,0.0053301468],"study_design_scores_gemma":[0.0005006884,0.00016715395,0.9386687,0.000015587433,0.0000044086596,6.134508e-8,0.053355854,0.0005311088,0.0000011470805,0.002368171,0.004310113,0.0000769745],"about_ca_topic_score_codex":0.00126924,"about_ca_topic_score_gemma":0.0010935996,"teacher_disagreement_score":0.13380821,"about_ca_system_score_codex":0.00051204144,"about_ca_system_score_gemma":0.0012011823,"threshold_uncertainty_score":0.9996428},"labels":[],"label_agreement":null},{"id":"W3148929026","doi":"10.5430/elr.v10n1p10","title":"Is Peer Feedback Helpful When Learning Literature Review Writing? A Study of Feedback Features and Quantity","year":2021,"lang":"en","type":"review","venue":"English Linguistics Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Peer feedback; Constructive; Reading (process); Psychology; Quality (philosophy); Process (computing); Writing process; Peer review; Mathematics education; Peer assessment; Computer science; Linguistics","score_opus":0.1447313827313703,"score_gpt":0.4989814303663223,"score_spread":0.35425004763495205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3148929026","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048743746,0.9454742,5.698685e-7,0.00008590776,0.0014031619,0.0023881656,0.0000704626,0.000077147924,0.050451662],"genre_scores_gemma":[0.00026472102,0.97273076,0.00026881677,0.000040144838,0.006207243,0.00012000582,0.00018582195,0.00009955796,0.020082934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98669595,0.0050984966,0.0012678052,0.0012431705,0.004546291,0.0011483096],"domain_scores_gemma":[0.97516096,0.00302884,0.00057398126,0.0008151876,0.02002508,0.0003959291],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01222037,0.00062604336,0.002831365,0.00057229045,0.0013015912,0.0013599341,0.001377478,0.0007671035,0.00047936355],"category_scores_gemma":[0.12059065,0.0005724876,0.000513063,0.0026998923,0.0005860138,0.000104236715,0.0011839087,0.00461153,0.000032527332],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028554217,0.0017594012,0.005768183,0.17255181,0.0014514452,0.0004768936,0.17927697,3.5464717e-7,8.6240775e-8,0.008658206,0.45854625,0.17148183],"study_design_scores_gemma":[0.00030269954,0.0002424474,0.00006828466,0.082819715,0.0005148003,0.0000017260509,0.02146749,4.8815855e-7,8.50866e-8,0.00005617777,0.89406425,0.0004618248],"about_ca_topic_score_codex":0.0006633283,"about_ca_topic_score_gemma":0.0005041337,"teacher_disagreement_score":0.435518,"about_ca_system_score_codex":0.00025765965,"about_ca_system_score_gemma":0.0012040169,"threshold_uncertainty_score":0.99999857},"labels":[],"label_agreement":null},{"id":"W3153021973","doi":"","title":"International trends in the implementation of assessment for learning : Implications for policy and practice","year":2015,"lang":"en","type":"article","venue":"Research Bank (Australian Catholic University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; Queen's University","funders":"","keywords":"Summative assessment; Globe; Policy learning; Political science; Assessment for learning; Impact assessment; Public administration; Regional science; Economic growth; Public relations; Formative assessment; Sociology; Pedagogy; Economics; Psychology; Computer science","score_opus":0.25869321118650285,"score_gpt":0.5606460194164312,"score_spread":0.30195280822992837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153021973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36076653,0.000012623756,0.0010813335,0.35627362,0.0001490133,0.0023006531,0.00013783053,0.00003849118,0.2792399],"genre_scores_gemma":[0.99117213,0.000069626665,0.0020489378,0.000029110255,0.00020807543,0.000020285797,0.000046914312,0.000004160005,0.0064007444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998783,0.0003788471,0.00009766148,0.00014186127,0.00034410617,0.00025452458],"domain_scores_gemma":[0.99855435,0.0007869971,0.000072311916,0.00008041479,0.00044502944,0.00006089873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00319773,0.00004631094,0.00006856811,0.00064179173,0.0003239034,0.000088715235,0.00033523815,0.00004081028,0.000013671972],"category_scores_gemma":[0.00043195012,0.00004514088,0.000034963254,0.00092001044,0.00019718551,0.0003953996,0.000057150977,0.00012405554,5.213926e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010225628,0.00014940716,0.03775566,0.000011379315,0.000044067943,0.0000017981895,0.074155174,0.000015205522,0.0003857186,0.84033334,0.0038986772,0.043147285],"study_design_scores_gemma":[0.0008084333,0.00011221974,0.07836158,0.0000032817306,0.000013461494,6.977962e-7,0.13461864,0.000009892269,0.0000071428694,0.00069176196,0.7853266,0.000046311587],"about_ca_topic_score_codex":0.005468244,"about_ca_topic_score_gemma":0.0015419555,"teacher_disagreement_score":0.83964163,"about_ca_system_score_codex":0.00039437172,"about_ca_system_score_gemma":0.0004588261,"threshold_uncertainty_score":0.8266386},"labels":[],"label_agreement":null},{"id":"W3153702187","doi":"10.7202/1076184ar","title":"L’apport d’une communauté de pratique au développement professionnel de superviseurs de stage en enseignement","year":2021,"lang":"fr","type":"article","venue":"Phronesis","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.0733994065175714,"score_gpt":0.35655211090586114,"score_spread":0.28315270438828977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153702187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8651477,0.0017916084,0.0025674452,0.1052785,0.0012360979,0.00064415357,0.000031458116,0.000099258716,0.023203762],"genre_scores_gemma":[0.9354054,0.0036086505,0.009424635,0.002049817,0.00074956875,0.00023161244,0.00005036444,0.00005420213,0.048425753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948393,0.0019349937,0.0005385458,0.00047925496,0.0007889536,0.0014189136],"domain_scores_gemma":[0.9982375,0.00047996652,0.00020134532,0.00047044392,0.0001752925,0.00043548198],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00292791,0.0003603389,0.00042836624,0.000067451096,0.0012068407,0.00016132544,0.000620455,0.00033949278,0.0040688454],"category_scores_gemma":[0.00018895241,0.0003974656,0.00020829852,0.0006866411,0.00031003155,0.00028191236,0.00043782397,0.00043156746,0.00014810376],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048738875,0.0020093701,0.47545436,0.00033082245,0.0003929131,0.00031304572,0.45832315,0.000055633755,0.005195774,0.021496536,0.026307601,0.010072066],"study_design_scores_gemma":[0.0012416292,0.00013977788,0.6065152,0.0004302144,0.00031605596,0.000011409034,0.33474496,0.0005005448,0.0040437668,0.0019366062,0.049428884,0.00069094746],"about_ca_topic_score_codex":0.0121041555,"about_ca_topic_score_gemma":0.014002355,"teacher_disagreement_score":0.13106087,"about_ca_system_score_codex":0.0036333243,"about_ca_system_score_gemma":0.0053743212,"threshold_uncertainty_score":0.9998477},"labels":[],"label_agreement":null},{"id":"W3156065537","doi":"10.24908/iqurcp.10488","title":"3 Minute Thesis: “One slide, no props, 3 minutes”","year":2018,"lang":"en","type":"article","venue":"Inquiry Queen s Undergraduate Research Conference Proceedings","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer graphics (images); Engineering drawing; Computer science; Engineering","score_opus":0.1767653312492937,"score_gpt":0.424596863444695,"score_spread":0.2478315321954013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156065537","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25913653,0.00022820012,0.00068810105,0.13167174,0.0016917263,0.0036464613,0.00002153692,0.00096829794,0.6019474],"genre_scores_gemma":[0.9373072,0.001008119,0.0019206173,0.00021137088,0.0034337128,0.00025656115,0.0000084455,0.00005431455,0.05579969],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925069,0.00032690502,0.00056228583,0.0010374257,0.00349603,0.0020704365],"domain_scores_gemma":[0.9918078,0.00041219484,0.0002163469,0.00034108807,0.006583018,0.00063952064],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.0053045293,0.0003780378,0.0004780526,0.0005682875,0.0021252162,0.0012731393,0.0018343927,0.00033647352,0.00075851235],"category_scores_gemma":[0.0019345564,0.0003607406,0.00014002623,0.0018961093,0.0045469073,0.0014604625,0.0005902766,0.0008480106,0.0032800457],"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":[0.00041653722,0.0006654211,0.032939974,0.00018137666,0.0003116097,0.00002235022,0.08152696,3.6267984e-8,0.011570031,0.5809096,0.2782214,0.013234706],"study_design_scores_gemma":[0.0020212925,0.0018932114,0.008809812,0.0010105037,0.00010359836,0.000005331284,0.07680995,0.00038275894,0.0052003316,0.1840831,0.7178965,0.0017835719],"about_ca_topic_score_codex":0.0024701876,"about_ca_topic_score_gemma":0.0005432545,"teacher_disagreement_score":0.6781706,"about_ca_system_score_codex":0.00047666387,"about_ca_system_score_gemma":0.0014353467,"threshold_uncertainty_score":0.9998845},"labels":[],"label_agreement":null},{"id":"W3158042421","doi":"10.1080/01587919.2021.1910494","title":"Revisioning the potential of Freire’s principles of assessment: Influences on the art of assessment in open and online learning through blogging","year":2021,"lang":"en","type":"article","venue":"Distance Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Calgary; Thompson Rivers University; University of British Columbia","funders":"","keywords":"Dialogical self; Critical consciousness; Pedagogy; Sociology; Craft; Consciousness; Critical thinking; Distance education; Critical pedagogy; Psychology; Epistemology; Social psychology; Visual arts","score_opus":0.04593780520966546,"score_gpt":0.41824886776978143,"score_spread":0.372311062560116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158042421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96502966,0.00039995386,0.00022421815,0.004378026,0.00021058189,0.00031129044,0.0000039326815,0.0000040369428,0.029438281],"genre_scores_gemma":[0.996745,0.0006763634,0.0016851657,0.000072089635,0.00006245506,0.000020992364,0.000018616172,0.000004480901,0.00071482087],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998574,0.0003808459,0.0003500342,0.00016819841,0.00040781993,0.00011908215],"domain_scores_gemma":[0.998852,0.0003670744,0.00041691863,0.00017005384,0.00017855312,0.000015374457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011752767,0.00007268747,0.00017873815,0.000028060267,0.00025930503,0.00008361542,0.00033837592,0.000032187676,0.00008915913],"category_scores_gemma":[0.0002702422,0.00004969924,0.000035096622,0.00036619394,0.000224744,0.00024960111,0.0001203734,0.00017374787,3.0586406e-7],"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":[0.000012604666,0.0004506901,0.6093918,0.00005363658,0.000034583652,3.9133474e-7,0.019110013,0.00045167503,0.0018891818,0.36505923,0.00013611089,0.0034100607],"study_design_scores_gemma":[0.00015616111,0.000033651155,0.8375841,0.000446661,0.00002457307,1.4734792e-7,0.15418868,0.00017026054,0.00020165222,0.0020883593,0.005038555,0.00006725481],"about_ca_topic_score_codex":0.00066574576,"about_ca_topic_score_gemma":0.00079631957,"teacher_disagreement_score":0.36297086,"about_ca_system_score_codex":0.00006249323,"about_ca_system_score_gemma":0.0006660624,"threshold_uncertainty_score":0.20266761},"labels":[],"label_agreement":null},{"id":"W3158490995","doi":"10.18733/cpi29603","title":"All that Glitters is not Gold:","year":2021,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology","score_opus":0.7089623333028044,"score_gpt":0.527925278176974,"score_spread":0.18103705512583046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158490995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9376653,0.0005934262,0.0000065246218,0.020009557,0.0006497077,0.0000788987,0.0000045909283,0.000061492574,0.040930513],"genre_scores_gemma":[0.9516904,0.0014522909,0.00013361592,0.0077104107,0.0009761544,0.0000064224046,0.000017894203,0.0000044271947,0.038008425],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988656,0.00009772026,0.000114362265,0.00027164223,0.00035273514,0.00029792287],"domain_scores_gemma":[0.9995612,0.00007328492,0.00003448373,0.00008337681,0.0000728141,0.00017484391],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015131221,0.0001143899,0.00015346058,0.000011294597,0.00026395285,0.00025372117,0.00014179877,0.000113628,0.0017878816],"category_scores_gemma":[0.0000398154,0.00007856217,0.00009000054,0.00011445512,0.00038084292,0.00025929313,0.00010702893,0.0001291938,0.000116932824],"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":[0.00008272104,0.00024448032,0.10837309,0.00004012409,0.00017519866,0.00018133306,0.51850444,4.7048331e-7,0.0066237487,0.06537018,0.27834877,0.022055428],"study_design_scores_gemma":[0.00029787436,0.000022514001,0.053788636,0.0000126763,0.000028301967,0.000004110256,0.111348934,0.0000025306113,0.00041272532,0.0005018198,0.833357,0.00022291418],"about_ca_topic_score_codex":0.00017139781,"about_ca_topic_score_gemma":0.00007922099,"teacher_disagreement_score":0.5550082,"about_ca_system_score_codex":0.000024736095,"about_ca_system_score_gemma":0.00002957133,"threshold_uncertainty_score":0.99912465},"labels":[],"label_agreement":null},{"id":"W3159797685","doi":"10.5430/ijhe.v11n1p1","title":"University Academics’ Perceptions Regarding the Use of Information Technology Tools for Effective Formative Assessment: Implications for Quality Assessment through Professional Development","year":2021,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Cronbach's alpha; Medical education; Perception; Quality (philosophy); Psychology; Reliability (semiconductor); Consistency (knowledge bases); Data collection; Sample (material); Knowledge management; Pedagogy; Computer science; Sociology; Medicine; Psychometrics","score_opus":0.10811282267608271,"score_gpt":0.47594031694344857,"score_spread":0.36782749426736583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159797685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48158178,0.000095212104,0.38912544,0.11000286,0.009973203,0.0028179218,0.00026299132,0.000046485075,0.0060941023],"genre_scores_gemma":[0.9012048,0.000082067534,0.09581122,0.00039007972,0.00036027064,0.00011422152,0.00018032562,0.0000060544694,0.0018509201],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986037,0.00019258409,0.000537354,0.00009670117,0.0004348412,0.00013481884],"domain_scores_gemma":[0.99402326,0.0012111823,0.00095072604,0.00009500173,0.0036835698,0.000036258214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081398705,0.00008694655,0.00016192645,0.00018214143,0.00051475957,0.00014489441,0.000414141,0.000116078896,0.00005139322],"category_scores_gemma":[0.00039092219,0.0000734713,0.00013844078,0.00028126608,0.000115353614,0.0027701652,0.000072316245,0.00020705462,0.0000010159397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115518334,0.0005621548,0.048011143,0.000033033684,0.0004924092,1.2326366e-7,0.021892132,0.000089296635,0.0013999349,0.8603133,0.014886025,0.05220493],"study_design_scores_gemma":[0.00062269485,0.00003419685,0.4869557,0.00008314073,0.000053885582,0.0000023635146,0.022436902,0.00000976717,0.00019509779,0.010358098,0.47916353,0.000084617874],"about_ca_topic_score_codex":0.000020644417,"about_ca_topic_score_gemma":0.000023685945,"teacher_disagreement_score":0.8499552,"about_ca_system_score_codex":0.0009643114,"about_ca_system_score_gemma":0.002219054,"threshold_uncertainty_score":0.39591664},"labels":[],"label_agreement":null},{"id":"W3160530669","doi":"10.5539/elt.v14n6p12","title":"Research on the Effect of Peer Feedback Training in English Writing Teaching—A Case Study of Students in Business English Major","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Psychology; Quality (philosophy); Perspective (graphical); Mathematics education; Point (geometry); Teaching method; Pedagogy; Computer science","score_opus":0.04366160629069881,"score_gpt":0.4157351404646889,"score_spread":0.3720735341739901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160530669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94969916,0.00013556183,0.0000015067378,0.0000804176,0.00074647204,0.0010803321,0.0000067981487,0.00008990474,0.04815984],"genre_scores_gemma":[0.99804944,0.0000055592036,0.00007184822,0.00002196348,0.0011661821,0.00008665152,0.000009711288,0.000045450357,0.0005432],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98602575,0.008970083,0.00083255226,0.0006328007,0.0026882156,0.00085061195],"domain_scores_gemma":[0.9919521,0.006492986,0.00023358768,0.0005578028,0.00066008436,0.000103409606],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033048283,0.00029150187,0.00067933457,0.00055147044,0.000723283,0.00033734774,0.0009990326,0.00018386143,0.00010877121],"category_scores_gemma":[0.030443989,0.00024489968,0.00011573709,0.0015218623,0.00019044912,0.00044080845,0.00048543722,0.0025809598,0.0000018011857],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046202367,0.00060807244,0.2640757,0.000046892685,0.00004672176,0.0012319213,0.73019904,0.000059213937,0.0000923967,0.0007772675,0.00006811532,0.0027484505],"study_design_scores_gemma":[0.0026919395,0.00027018346,0.022275303,0.00043308781,0.000030684565,0.0000032693476,0.97367656,0.000014343437,0.00014658817,0.000008919534,0.00022464318,0.00022448739],"about_ca_topic_score_codex":0.015418524,"about_ca_topic_score_gemma":0.021606091,"teacher_disagreement_score":0.2434775,"about_ca_system_score_codex":0.000287485,"about_ca_system_score_gemma":0.00018819897,"threshold_uncertainty_score":0.9997201},"labels":[],"label_agreement":null},{"id":"W3160550689","doi":"10.1080/2331186x.2021.1921903","title":"Exploring assessment across cultures: Teachers’ approaches to assessment in the U.S., China, and Canada","year":2021,"lang":"en","type":"article","venue":"Cogent Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Context (archaeology); Assessment for learning; Educational assessment; Psychology; China; Scale (ratio); Latent class model; Pedagogy; Class (philosophy); Mathematics education; Formative assessment; Geography; Computer science","score_opus":0.20288863404547883,"score_gpt":0.4023957242216135,"score_spread":0.1995070901761347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160550689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96053267,0.00019110888,0.00006552059,0.020401547,0.0008688224,0.0004228108,0.0000030392773,0.000011924527,0.017502543],"genre_scores_gemma":[0.99653083,0.00020231906,0.00079518807,0.0005790377,0.00031805743,0.00036190325,0.000031858373,0.000006709843,0.001174107],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984516,0.00027635126,0.00016790167,0.00027200457,0.000540593,0.00029156238],"domain_scores_gemma":[0.99954164,0.000075932454,0.00005208478,0.00017736842,0.000048304322,0.00010466474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008525828,0.00010644507,0.000110616966,0.000025788017,0.0005349586,0.00028321982,0.00022484535,0.000032343483,0.000043497694],"category_scores_gemma":[0.00006497298,0.00008797111,0.000025727233,0.000321507,0.00003984223,0.00022874668,0.00006905107,0.00017621693,0.000002011084],"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":[0.0000029311095,0.0005449693,0.52646774,0.000019841644,0.000034146604,0.0000059119243,0.40135995,0.0000296096,0.00021807765,0.027093297,0.008643834,0.035579715],"study_design_scores_gemma":[0.000082670056,0.0000073716483,0.5964236,0.000016439197,0.000008073803,6.5833063e-7,0.35155755,0.0000046866107,0.000029009081,0.000090580084,0.05168927,0.00009006313],"about_ca_topic_score_codex":0.31870997,"about_ca_topic_score_gemma":0.7427092,"teacher_disagreement_score":0.42399925,"about_ca_system_score_codex":0.0006530545,"about_ca_system_score_gemma":0.0026769536,"threshold_uncertainty_score":0.6858268},"labels":[],"label_agreement":null},{"id":"W3161754782","doi":"10.3968/12015","title":"Moroccan EFL Secondary School Teachers’ Current Practices and Challenges of Formative Assessment","year":2021,"lang":"en","type":"article","venue":"Canadian social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Mathematics education; Psychology; Pedagogy; Medical education; Medicine","score_opus":0.06726235339531093,"score_gpt":0.4018378190155934,"score_spread":0.33457546562028245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161754782","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2717542,0.0034585432,0.000006959569,0.008077279,0.0006339939,0.00022681082,0.00002312652,0.000020633885,0.71579844],"genre_scores_gemma":[0.9972522,0.0019103081,0.0002079916,0.00014845062,0.0002391387,0.00001140644,0.0000022940314,0.0000047987346,0.0002233713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9981635,0.00017522967,0.00017569077,0.0003018921,0.0006735804,0.0005101102],"domain_scores_gemma":[0.99865526,0.00009467181,0.00026179227,0.000106212865,0.0003094945,0.0005725667],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0014677836,0.00010015277,0.00017170151,0.00013268134,0.0013441526,0.00022555866,0.00038867467,0.00006513656,0.00032467287],"category_scores_gemma":[0.00048088635,0.00010743759,0.000042205294,0.00065074145,0.0011900244,0.0010276833,0.000090645386,0.00024026523,0.000007670595],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003780315,0.0001215151,0.118540704,0.000074963566,0.000052677013,0.000020269892,0.25680527,2.07075e-7,0.00064771465,0.34110668,0.0026471964,0.27997902],"study_design_scores_gemma":[0.00032884642,0.000034366083,0.3350029,0.00003855521,0.000028553392,0.0000011277883,0.44190857,0.000012271703,0.00009848539,0.0012310594,0.2210456,0.00026967417],"about_ca_topic_score_codex":0.014567474,"about_ca_topic_score_gemma":0.12436369,"teacher_disagreement_score":0.725498,"about_ca_system_score_codex":0.0006885316,"about_ca_system_score_gemma":0.0071653007,"threshold_uncertainty_score":0.99995595},"labels":[],"label_agreement":null},{"id":"W3161805550","doi":"10.4018/978-1-7998-7106-4.ch014","title":"Appreciative Assessment in Graphic Design Education Using UDL Strategies","year":2021,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Formative assessment; Universal Design for Learning; Class (philosophy); Computer science; Face (sociological concept); Appreciative inquiry; Best practice; Mathematics education; Pedagogy; Human–computer interaction; Engineering ethics; Psychology; Engineering; Sociology; Artificial intelligence; Political science","score_opus":0.03732473664692976,"score_gpt":0.3524010662162964,"score_spread":0.31507632956936665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161805550","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021677925,0.14003296,0.007901558,0.0077978265,0.0057243784,0.003540406,0.00005622522,0.00047643442,0.8323024],"genre_scores_gemma":[0.028678548,0.42959186,0.40973583,0.00021452522,0.0010889422,0.0009980358,0.00023496848,0.00012485367,0.12933244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977753,0.00013163015,0.0005404681,0.0006297922,0.000578792,0.00034398105],"domain_scores_gemma":[0.99867105,0.0004468505,0.00037822354,0.00020248747,0.00025762382,0.00004378303],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043707222,0.00038326203,0.00043946196,0.0007250946,0.00046303688,0.00021196247,0.00034554096,0.0004792534,0.00028961804],"category_scores_gemma":[0.00012739243,0.00042180868,0.00007394067,0.0003312213,0.0012988775,0.0029721104,0.00011523975,0.00063188915,0.000002306082],"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":[0.000028218734,0.00007890023,0.0011298137,0.000036751768,0.000032967255,0.0000023110401,0.0005828429,0.00046893556,0.000022722024,0.96948856,0.00015324251,0.027974706],"study_design_scores_gemma":[0.00019123264,0.00008022728,0.0027142449,0.0005032839,0.000026262853,0.000016469046,0.05374544,0.000027061309,0.000020087386,0.7927995,0.14934115,0.0005350887],"about_ca_topic_score_codex":0.00008809908,"about_ca_topic_score_gemma":0.0005495838,"teacher_disagreement_score":0.70296997,"about_ca_system_score_codex":0.0007953337,"about_ca_system_score_gemma":0.004719936,"threshold_uncertainty_score":0.9998234},"labels":[],"label_agreement":null},{"id":"W3163600682","doi":"10.48325/rleee.001.06","title":"L'articulation de l’évaluation dans une recherche collaborative sur l’évaluation des compétences en formation à distance (FAD) en enseignement supérieur","year":2020,"lang":"fr","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"General partnership; Articulation (sociology); Valuation (finance); Context (archaeology); Sociology; Empirical research; Structuring; Higher education; Political science; Epistemology; Business; Accounting; Law; Philosophy","score_opus":0.46832230800859775,"score_gpt":0.5787659544646687,"score_spread":0.11044364645607097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163600682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89638275,0.015291481,0.06568451,0.007967625,0.0009106055,0.0018743376,0.00007356741,0.0000625704,0.011752549],"genre_scores_gemma":[0.96000654,0.028139314,0.009737855,0.00035855334,0.0005826039,0.000110748646,0.00009568493,0.000040925555,0.00092780153],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9891158,0.006366939,0.0013640983,0.0005410773,0.002004976,0.0006071522],"domain_scores_gemma":[0.99468315,0.0018759969,0.0014882914,0.00024015886,0.0013620092,0.00035041277],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00936944,0.00042137175,0.0007251786,0.00026334095,0.0010221158,0.0018516114,0.0016633526,0.00033761602,0.0033032838],"category_scores_gemma":[0.0024455097,0.00043333502,0.00019659399,0.0043961164,0.0005090634,0.006904512,0.00037644757,0.00055107835,0.00004282888],"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":[0.0004102183,0.00058112515,0.3831699,0.00029823475,0.00038333127,0.0000139005515,0.41289002,0.008118806,0.06486731,0.002402603,0.022915676,0.10394888],"study_design_scores_gemma":[0.0012072574,0.00009037331,0.8616355,0.00081460335,0.0004674382,0.0000023062692,0.05994614,0.024816222,0.009702429,0.03320629,0.0074261846,0.0006852621],"about_ca_topic_score_codex":0.004943097,"about_ca_topic_score_gemma":0.0033899995,"teacher_disagreement_score":0.47846562,"about_ca_system_score_codex":0.0015654768,"about_ca_system_score_gemma":0.0010929577,"threshold_uncertainty_score":0.9998118},"labels":[],"label_agreement":null},{"id":"W316755295","doi":"","title":"A Triumph of Politics over Pedagogy? The Case of the Ontario Teacher Qualifying Test, 2000-2005","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Certification; Bachelor; Test (biology); Teacher preparation; Government (linguistics); Teacher education; Politics; Pedagogy; Alternative teacher certification; Political science; Medical education; Psychology; Mathematics education; Sociology; Medicine; Law","score_opus":0.0407775116742853,"score_gpt":0.4037780738310834,"score_spread":0.3630005621567981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W316755295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8927488,0.00019435663,9.448856e-7,0.08209479,0.00014951783,0.00008557682,0.000022167462,5.171973e-7,0.024703348],"genre_scores_gemma":[0.97946745,0.000013139416,0.0000872706,0.0006399706,0.0012814911,0.0000012213204,0.0000013976236,0.0000033559993,0.018504713],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99919486,0.00009742961,0.0003252956,0.000050277617,0.00016847032,0.00016366022],"domain_scores_gemma":[0.9988844,0.00029165894,0.00031465755,0.000078686026,0.00017535665,0.00025526682],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047183453,0.000060825452,0.00009602009,0.00011286532,0.00036899067,0.000054383523,0.0001718,0.000047411442,0.001350428],"category_scores_gemma":[0.000474275,0.000042199452,0.000069359,0.00015530104,0.00030334882,0.00013015134,0.000005159545,0.00013544332,0.0000014054333],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010859714,0.00017690827,0.46125305,0.00001141453,0.00006211026,0.0000056941967,0.13467978,0.000008179462,0.00004105669,0.38101807,0.02143407,0.0012988226],"study_design_scores_gemma":[0.0004522892,0.00009743792,0.6881002,0.000038797163,0.00007490713,0.00031063196,0.024412544,0.000007454026,0.00006276387,0.0034689654,0.28284684,0.0001271182],"about_ca_topic_score_codex":0.29234058,"about_ca_topic_score_gemma":0.912155,"teacher_disagreement_score":0.6198144,"about_ca_system_score_codex":0.0003698313,"about_ca_system_score_gemma":0.027855383,"threshold_uncertainty_score":0.9995625},"labels":[],"label_agreement":null},{"id":"W3167671009","doi":"10.1007/s40037-021-00670-z","title":"Don’t be reviewer&amp;nbsp;2! Reflections on writing effective peer review comments","year":2021,"lang":"en","type":"editorial","venue":"Perspectives on Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; Sinai Health System; University of Toronto; Western University","funders":"","keywords":"Medical education; Peer review; Psychology; Computer science; Medicine; Chemistry; Biochemistry","score_opus":0.05392581346621207,"score_gpt":0.5045142607564723,"score_spread":0.45058844729026026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167671009","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000049664217,0.029058244,0.00002707967,0.0955229,0.682434,0.0018712555,0.0000422432,0.00014271757,0.1908519],"genre_scores_gemma":[0.0001999275,0.1833054,0.00027725697,0.0064536477,0.7791968,0.0009761141,0.0013070758,0.00006722313,0.028216563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888442,0.0019504037,0.00062678783,0.0010790279,0.006944709,0.00055485795],"domain_scores_gemma":[0.99117345,0.0031240967,0.00049489556,0.00059412216,0.004086668,0.000526792],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054902625,0.00046576886,0.00086146954,0.00022647968,0.0011198344,0.00025277847,0.0007307061,0.0008899334,0.0071628615],"category_scores_gemma":[0.10985494,0.00044596134,0.00039819808,0.0009371186,0.0003851806,0.00018819835,0.000109002736,0.002464657,0.00029065847],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018662566,0.0012009914,0.000031465745,0.00041673193,0.000118221666,0.0000020238217,0.019495707,4.98767e-8,4.171745e-7,0.0031633235,0.9635829,0.011969512],"study_design_scores_gemma":[0.0002946329,0.00013513172,0.00015178886,0.009089471,0.0002190287,3.63261e-7,0.044241168,2.079693e-7,4.613346e-7,0.00016034278,0.9453146,0.00039282927],"about_ca_topic_score_codex":0.0013168012,"about_ca_topic_score_gemma":0.0010947378,"teacher_disagreement_score":0.16263533,"about_ca_system_score_codex":0.002642421,"about_ca_system_score_gemma":0.004893199,"threshold_uncertainty_score":0.9998367},"labels":[],"label_agreement":null},{"id":"W3169110767","doi":"10.5539/elt.v14n7p21","title":"The Impact of Language Testing Washback in Promoting Teaching and Learning Processes: A Theoretical Review","year":2021,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Context (archaeology); Mathematics education; Test (biology); Government (linguistics); Pedagogy; Language assessment; Process (computing); Language change; Foreign language; Language education; Teaching method; Linguistics; Computer science","score_opus":0.026372066115280254,"score_gpt":0.40898340271917705,"score_spread":0.3826113366038968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169110767","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064019472,0.9592141,0.00000533475,0.000026631022,0.000104271625,0.0010474323,0.000005093377,0.00013207,0.033063136],"genre_scores_gemma":[0.0147854015,0.9831918,0.0007311434,0.000014825384,0.00070782093,0.00007651445,0.00004117499,0.00007450228,0.00037680985],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99081844,0.006334272,0.0009373269,0.0005586306,0.00062141975,0.00072993187],"domain_scores_gemma":[0.9909932,0.007712936,0.0007183699,0.00033434402,0.00010829668,0.00013283972],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.015131312,0.00046674538,0.0016167515,0.00014227822,0.0012632437,0.00043001585,0.0007109476,0.0002420231,0.000067211484],"category_scores_gemma":[0.0768168,0.00030766442,0.00037737214,0.00071448524,0.00030413133,0.0002907757,0.0003756637,0.00406614,0.0000025778154],"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":[8.10629e-7,0.000044998866,0.0002692899,0.008839818,0.00007291828,0.000040107017,0.28955397,6.3277616e-7,9.834874e-7,0.0013532703,0.000029161842,0.69979405],"study_design_scores_gemma":[0.00042767325,0.00015467433,0.00002100942,0.30337122,0.00079063565,0.000028349968,0.51476896,0.00006373555,4.5944262e-7,0.000046020483,0.1791423,0.0011849648],"about_ca_topic_score_codex":0.0016994367,"about_ca_topic_score_gemma":0.00020691619,"teacher_disagreement_score":0.6986091,"about_ca_system_score_codex":0.0002744576,"about_ca_system_score_gemma":0.00076492544,"threshold_uncertainty_score":0.99993753},"labels":[],"label_agreement":null},{"id":"W3170208555","doi":"10.5430/wjel.v11n2p1","title":"Students’ Perspectives as Providers and Receivers of Peer Formative Feedback on Writing","year":2021,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Formative assessment; Feeling; Quality (philosophy); Certainty; Peer review; Technical peer review; Computer science; Psychology; Medical education; Mathematics education; Social psychology; Medicine; Political science","score_opus":0.013191724688976893,"score_gpt":0.3307774514420382,"score_spread":0.3175857267530613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170208555","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84148437,0.0010091126,0.00000299944,0.00079921196,0.0003716485,0.000087588065,0.0000028356806,0.000010251121,0.15623197],"genre_scores_gemma":[0.9930477,0.00030177797,0.00042638765,0.000102550315,0.000564701,9.038163e-7,0.00000102013,0.000008263673,0.005546706],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9982378,0.00018434656,0.00029652216,0.00011529606,0.0009739268,0.00019209135],"domain_scores_gemma":[0.9980404,0.00028908503,0.0003296854,0.00007800554,0.0011606493,0.000102189864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010304465,0.000096212985,0.0002371338,0.00016788082,0.00016502423,0.00015334322,0.00022446437,0.000037039506,0.00039109722],"category_scores_gemma":[0.0019706227,0.00008687555,0.000110378525,0.0003527704,0.00016149065,0.00047907405,0.00005979504,0.0002634498,0.0000030558385],"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":[0.00008614532,0.00020315069,0.04259764,0.000018340623,0.00017050856,0.00009863792,0.9449533,0.0000046097593,0.00020926398,0.0057038898,0.0028207612,0.0031337235],"study_design_scores_gemma":[0.0009405689,0.00010228006,0.020589046,0.00016906836,0.000043695334,0.0000020430111,0.96797234,4.7836164e-7,0.00045713366,0.000097806835,0.0095255235,0.00010004415],"about_ca_topic_score_codex":0.00008037805,"about_ca_topic_score_gemma":0.00031921436,"teacher_disagreement_score":0.15156332,"about_ca_system_score_codex":0.0001123895,"about_ca_system_score_gemma":0.00014289594,"threshold_uncertainty_score":0.42822403},"labels":[],"label_agreement":null},{"id":"W3170640792","doi":"10.18806/tesl.v37i1.1333","title":"Does the Quality of Source Notes Matter? An Exploratory Study of Source-based Academic Writing","year":2020,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Copying; Redaction; Quality (philosophy); Popularity; Exploratory research; Humanities; Face (sociological concept); Psychology; Linguistics; Mathematics education; Pedagogy; Sociology; Literature; Art; Philosophy; Political science; Social psychology; Epistemology","score_opus":0.08123880349729176,"score_gpt":0.36819923467237226,"score_spread":0.2869604311750805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170640792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919523,0.00035747036,0.00017552238,0.007026762,0.0001599929,0.00017726436,0.000005803143,0.000013581973,0.0001313181],"genre_scores_gemma":[0.99201506,0.0000070503065,0.000031852087,0.0074000624,0.0005074326,0.0000031083737,5.9170384e-7,0.000011161266,0.000023669932],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99697804,0.0008031756,0.00057375414,0.00013879889,0.0012419289,0.00026428216],"domain_scores_gemma":[0.9983402,0.0005944936,0.0005569538,0.00012518709,0.00017607518,0.00020710133],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019376302,0.00010731972,0.00025553998,0.000033017197,0.0005794378,0.00005824691,0.00064308837,0.000048068057,0.0018401514],"category_scores_gemma":[0.00031217912,0.00006520369,0.00005873078,0.00024983365,0.00015309123,0.00017000412,0.00005517334,0.00046566795,0.0000011445098],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006920356,0.00013611958,0.87760144,0.000029627976,0.00007626619,0.0000052662035,0.1147454,0.0003698526,0.0015862528,0.0000538082,0.0033091223,0.0020176435],"study_design_scores_gemma":[0.0011734453,0.00024000845,0.21001132,0.000050373823,0.000074614014,6.4420595e-7,0.7825564,0.00016421195,0.000476417,0.000076393975,0.0049193376,0.00025683403],"about_ca_topic_score_codex":0.14110565,"about_ca_topic_score_gemma":0.29235965,"teacher_disagreement_score":0.667811,"about_ca_system_score_codex":0.00010876778,"about_ca_system_score_gemma":0.0010752035,"threshold_uncertainty_score":0.9990723},"labels":[],"label_agreement":null},{"id":"W3172002384","doi":"10.3968/12122","title":"A Review Research of Washback in Language Testing","year":2021,"lang":"en","type":"review","venue":"Studies in literature and language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Phenomenon; Empirical research; Psychology; Test (biology); Mathematics education; Mathematics; Physics","score_opus":0.2682666067829474,"score_gpt":0.5816010816506939,"score_spread":0.3133344748677465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172002384","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008064756,0.9761094,1.9031706e-8,0.00006170111,0.0001710345,0.0007467508,0.000018455503,0.000011998594,0.022799997],"genre_scores_gemma":[0.000041706564,0.9967859,0.00017853618,0.0000791929,0.0003412861,0.00010107736,0.000039522354,0.000016975971,0.0024158084],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99685735,0.0013039564,0.0005713575,0.00040558435,0.00042957274,0.00043218263],"domain_scores_gemma":[0.997779,0.0015513437,0.00016389242,0.00026149844,0.00019893203,0.00004534212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032889196,0.00023846386,0.0016778633,0.00033238812,0.00012365241,0.00006606072,0.00031168148,0.00021896715,0.000045453162],"category_scores_gemma":[0.0028042893,0.00018027126,0.00014493399,0.003096322,0.0003641634,0.00010100143,0.00034196058,0.0009086607,0.000004087936],"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":[0.0000016634318,0.000073298885,0.00024384263,0.09747577,0.00011831855,0.00064502744,0.2672171,6.836986e-9,6.4217767e-7,0.0011668893,0.00798501,0.6250724],"study_design_scores_gemma":[0.00009590248,0.000018375657,0.0000119794795,0.28155404,0.00006774854,0.000003335431,0.04493245,3.181667e-8,6.779741e-8,0.00002167936,0.673139,0.00015539359],"about_ca_topic_score_codex":0.00031044264,"about_ca_topic_score_gemma":0.0011888742,"teacher_disagreement_score":0.665154,"about_ca_system_score_codex":0.0001249427,"about_ca_system_score_gemma":0.00019776252,"threshold_uncertainty_score":0.7351249},"labels":[],"label_agreement":null},{"id":"W3172290871","doi":"10.1139/cjc-2020-0398","title":"Examining chemistry students’ perceptions toward multiple-choice assessment tools that vary in feedback and partial credit","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Chemistry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Psychology; Multiple choice; Preference; Test anxiety; Perception; Anxiety; Test (biology); Mathematics education; Statistics; Mathematics; Significant difference","score_opus":0.07628932059813516,"score_gpt":0.34230333238870675,"score_spread":0.2660140117905716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172290871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9780855,0.00039163383,0.00002379104,0.0010958262,0.0003249379,0.000070861155,0.000018711678,0.000008064731,0.01998067],"genre_scores_gemma":[0.99674714,0.00019529629,0.00025422117,0.00011312127,0.0009791093,0.0000061121264,0.000015704343,0.000014874935,0.0016744286],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99816227,0.00008514173,0.00040083987,0.00024799714,0.0006126053,0.0004911712],"domain_scores_gemma":[0.99823713,0.00038114772,0.00021066124,0.00015701712,0.00020508474,0.0008089635],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006561857,0.00016981259,0.00030531455,0.0000456751,0.0003506857,0.0004989032,0.00046125744,0.00019548516,0.0024276667],"category_scores_gemma":[0.00075125514,0.00019319948,0.00009280148,0.00023197061,0.00026649667,0.0003963769,0.00006260482,0.00053301617,0.0000031325137],"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":[0.0000053635854,0.000053433076,0.9812136,0.000039359584,0.000055158685,0.000323581,0.0053370195,0.000009283243,0.011056183,0.0000058312776,0.0011669599,0.00073421944],"study_design_scores_gemma":[0.0014369552,0.000015988839,0.91347206,0.0002209064,0.00005285854,0.00006079112,0.06692533,0.000014908718,0.0027018809,0.00003453336,0.014749138,0.00031464058],"about_ca_topic_score_codex":0.0016946584,"about_ca_topic_score_gemma":0.0063366117,"teacher_disagreement_score":0.06774154,"about_ca_system_score_codex":0.0005783624,"about_ca_system_score_gemma":0.002839451,"threshold_uncertainty_score":0.99848425},"labels":[],"label_agreement":null},{"id":"W3176463368","doi":"10.5539/elt.v14n7p107","title":"Teachers’ Perception towards Formative Assessment in Saudi Universities’ Context: A Review of Literature","year":2021,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Summative assessment; Context (archaeology); Perception; Knowledge survey; Medical education; Pedagogy; Medicine","score_opus":0.02417926377044678,"score_gpt":0.3972648817651881,"score_spread":0.3730856179947413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176463368","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022159555,0.9021118,0.000027374766,0.000054241606,0.00045419432,0.0007866071,0.000054093314,0.0000699464,0.09622011],"genre_scores_gemma":[0.0009821788,0.994652,0.0006081073,0.00011740432,0.0005229764,0.000039328523,0.00056796795,0.00003062398,0.002479411],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950953,0.0027187965,0.0006853531,0.0003835728,0.00072916027,0.00038782408],"domain_scores_gemma":[0.99859136,0.0003076251,0.0005555227,0.0003195349,0.00013459663,0.00009133232],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033759116,0.000373744,0.0017141664,0.00028852548,0.00022764469,0.00015327439,0.00057310634,0.00036147682,0.0006782726],"category_scores_gemma":[0.0005326673,0.00033825877,0.00062204077,0.0006580162,0.00009796448,0.0006154635,0.00019729321,0.0018625511,0.0000052858904],"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":[4.2383564e-7,0.00004913672,0.000010517452,0.010929257,0.00006419948,0.0000335149,0.5048431,2.2928122e-8,1.0028718e-7,0.0016523751,0.00063734635,0.48177996],"study_design_scores_gemma":[0.00012337141,0.000013583202,0.000009009323,0.12718308,0.00018290224,9.2820727e-7,0.40263918,3.2307105e-7,2.0677803e-8,0.0000018784428,0.46964535,0.00020037578],"about_ca_topic_score_codex":0.0011823362,"about_ca_topic_score_gemma":0.00039577813,"teacher_disagreement_score":0.48157957,"about_ca_system_score_codex":0.0015062487,"about_ca_system_score_gemma":0.0012736982,"threshold_uncertainty_score":0.99990696},"labels":[],"label_agreement":null},{"id":"W3183541999","doi":"10.1002/prp2.833","title":"Answering questions in a co‐created formative exam question bank improves summative exam performance, while students perceive benefits from answering, authoring, and peer discussion: A mixed methods analysis of PeerWise","year":2021,"lang":"en","type":"article","venue":"Pharmacology Research & Perspectives","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Summative assessment; Formative assessment; Test (biology); Medical education; Multiple choice; Peer assessment; Class (philosophy); Psychology; Mathematics education; Computer science; Medicine; Internal medicine; Artificial intelligence","score_opus":0.0832141660436603,"score_gpt":0.5168632575806068,"score_spread":0.43364909153694653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183541999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99211705,0.0013074315,0.00019576619,0.0014006322,0.00024382795,0.00073829654,0.000075368516,0.00006795088,0.003853651],"genre_scores_gemma":[0.9927993,0.003471605,0.001741119,0.000015158374,0.0001575563,0.00027010962,0.00007017438,0.000021234271,0.0014537594],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99229234,0.0042742086,0.0005018188,0.0007823506,0.0013719415,0.0007773353],"domain_scores_gemma":[0.9965599,0.0013258172,0.00019306273,0.0002202748,0.0014263812,0.00027454694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057008625,0.0002800191,0.0007134087,0.0012043276,0.00095760403,0.0002058151,0.0005012124,0.00019998128,0.00082599715],"category_scores_gemma":[0.0008119964,0.00023983567,0.00015245612,0.0029388107,0.0010857829,0.0010454712,0.0004544411,0.0008204043,0.0000064772007],"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":[0.000354689,0.0010560368,0.4154256,0.000041875443,0.0023467115,0.000028856326,0.5476269,0.00029234475,0.025746386,0.0014534341,0.00043051745,0.005196645],"study_design_scores_gemma":[0.000914013,0.00017249714,0.720435,0.00007424169,0.00040754245,5.8365373e-7,0.27103013,0.0025525421,0.0036965194,0.00013313514,0.00036310495,0.00022067719],"about_ca_topic_score_codex":0.0032227624,"about_ca_topic_score_gemma":0.0042103096,"teacher_disagreement_score":0.30500942,"about_ca_system_score_codex":0.0006623521,"about_ca_system_score_gemma":0.00036538293,"threshold_uncertainty_score":0.9780215},"labels":[],"label_agreement":null},{"id":"W3183841095","doi":"10.5539/elt.v14n8p58","title":"Online Proctoring of High-Stakes English Language Examinations: A Survey of Past Candidates’ Attitudes and Perceptions","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cheating; Psychology; Perception; Constructive; Test (biology); Medical education; Mathematics education; Social psychology; Pedagogy; Medicine; Computer science; Process (computing)","score_opus":0.020986810649177012,"score_gpt":0.33866034351838115,"score_spread":0.31767353286920413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183841095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936271,0.00080057525,0.00005156416,0.000028580347,0.00032200228,0.00015638575,0.00016787248,0.000094223666,0.004751731],"genre_scores_gemma":[0.9962008,0.000055722598,0.0016633095,0.000013260505,0.0005738608,0.000008368267,0.00026854224,0.000016718624,0.0011994399],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9982395,0.00056658784,0.00029697586,0.00025249537,0.00040377452,0.00024066836],"domain_scores_gemma":[0.9986994,0.0005777812,0.00014981268,0.00020913946,0.00028798904,0.000075848926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013408981,0.00012916111,0.0002806727,0.00011081641,0.00026819107,0.00009057649,0.00020328803,0.000082113525,0.00022957186],"category_scores_gemma":[0.0037478271,0.00013212711,0.000048896116,0.00031023246,0.00015066851,0.00032285217,0.00010928566,0.00026813193,8.6322666e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004043052,0.00023461817,0.37301415,0.00005179028,0.000041149528,0.000008094057,0.62042254,0.0000024401168,0.0018602605,0.0010800646,0.000058355432,0.0032225212],"study_design_scores_gemma":[0.00030435025,0.000025218287,0.5105397,0.0000962917,0.00002708977,2.8949015e-7,0.4884198,0.0000059619865,0.00027572297,0.0000053970775,0.00017371582,0.00012644663],"about_ca_topic_score_codex":0.019487116,"about_ca_topic_score_gemma":0.04593112,"teacher_disagreement_score":0.13752556,"about_ca_system_score_codex":0.000068743204,"about_ca_system_score_gemma":0.00011350638,"threshold_uncertainty_score":0.9870422},"labels":[],"label_agreement":null},{"id":"W3185590891","doi":"10.22034/elt.2021.43932.2334","title":"A New Dilemma for Language Teachers and Students: Self-assessment or Teacher Assessment (Research Article)","year":2021,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Dilemma; Self-assessment; Likert scale; Reading (process); Psychology; Reading comprehension; Mathematics education; Comprehension; Set (abstract data type); Test (biology); Medical education; Pedagogy; Computer science; Medicine","score_opus":0.32538256722417375,"score_gpt":0.6670082438301432,"score_spread":0.3416256766059695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185590891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9746712,0.0039555933,0.0006219186,0.0015375285,0.00052645797,0.0015457324,0.00001747878,0.000078046105,0.01704608],"genre_scores_gemma":[0.9766451,0.0064482708,0.006994335,0.00024990155,0.00074660516,0.00021122706,0.00001302312,0.000066472734,0.008625034],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99373823,0.0012913618,0.0007736597,0.0006975421,0.0026046846,0.0008945067],"domain_scores_gemma":[0.99665695,0.001137499,0.00042617007,0.0004679523,0.0006732245,0.00063822547],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070305164,0.0003194946,0.00072883244,0.000461513,0.0011107171,0.00488732,0.0027326941,0.00017472234,0.015777145],"category_scores_gemma":[0.00048435736,0.000276856,0.00019617139,0.0014494587,0.00020440055,0.002229186,0.0016858341,0.0007027903,0.000011206835],"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":[0.00010395762,0.0010576316,0.88840723,0.000050686744,0.0005361791,0.00007867889,0.011584318,0.000004731796,0.008555352,0.0015944811,0.061465845,0.026560925],"study_design_scores_gemma":[0.0020367964,0.000042083175,0.9195396,0.00020383924,0.00017243698,0.000003547386,0.021270165,0.00004998223,0.0008159699,0.0022015367,0.053219467,0.00044459055],"about_ca_topic_score_codex":0.00484219,"about_ca_topic_score_gemma":0.0018946045,"teacher_disagreement_score":0.031132374,"about_ca_system_score_codex":0.00066894403,"about_ca_system_score_gemma":0.0019795294,"threshold_uncertainty_score":0.99996835},"labels":[],"label_agreement":null},{"id":"W3186678687","doi":"10.3390/educsci11070366","title":"Generative Unit Assessment: Authenticity in Mathematics Classroom Assessment Practices","year":2021,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; University of Alberta","funders":"University of Alberta","keywords":"Unit (ring theory); Generative grammar; Mathematics education; Task (project management); Action (physics); Authentic assessment; Citizen journalism; Alternative assessment; Process (computing); Computer science; Dynamic assessment; Generative model; Pedagogy; Psychology; Artificial intelligence; Engineering; Curriculum","score_opus":0.141037056081307,"score_gpt":0.5097772346579433,"score_spread":0.3687401785766363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186678687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5227207,0.00021097621,0.0007442835,0.015130606,0.001747762,0.0003328072,0.0000024657518,0.000046701247,0.45906368],"genre_scores_gemma":[0.9316341,0.00024318368,0.05380717,0.000323201,0.00031606943,0.000076740136,0.000011726055,0.0000071023665,0.013580686],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9971732,0.0005711242,0.00035549098,0.0004235405,0.0011027711,0.00037388288],"domain_scores_gemma":[0.998288,0.000567151,0.00049804006,0.00020050298,0.00032983552,0.00011647629],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023553334,0.00013111864,0.00018867617,0.0001865475,0.0010039904,0.00078690524,0.00048480337,0.000075462114,0.0014164788],"category_scores_gemma":[0.0006941484,0.0001239868,0.000053070613,0.001695953,0.00044547915,0.0010677198,0.00009128654,0.00020973099,0.000047461304],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[7.7676657e-7,0.0012971298,0.5263492,0.000016024233,0.000018035738,0.0000036721744,0.031431466,0.000016715949,0.0005933813,0.43574816,0.0014004991,0.003124936],"study_design_scores_gemma":[0.00032732918,0.00005796017,0.43433914,0.00013125865,0.000041185285,0.0000024627645,0.48480526,0.0011875837,0.00025225288,0.03954597,0.038904265,0.0004053613],"about_ca_topic_score_codex":0.0007460945,"about_ca_topic_score_gemma":0.004193605,"teacher_disagreement_score":0.4533738,"about_ca_system_score_codex":0.0002863144,"about_ca_system_score_gemma":0.006807606,"threshold_uncertainty_score":0.99949634},"labels":[],"label_agreement":null},{"id":"W3187362732","doi":"10.3390/educsci11080400","title":"Teacher Education during the COVID-19 Lockdown: Insights from a Formative Intervention Approach Involving Online Feedback","year":2021,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Universidade do Minho; Ministério da Ciência, Tecnologia e Ensino Superior; International Council for Canadian Studies","keywords":"Formative assessment; CLARITY; Psychology; Intervention (counseling); Mathematics education; Meaning (existential); Computer-mediated communication; Coronavirus disease 2019 (COVID-19); Teacher education; Higher education; Pedagogy; Medical education; Computer science; The Internet; Medicine","score_opus":0.06289100403871921,"score_gpt":0.4044985134050234,"score_spread":0.3416075093663042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187362732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9411414,0.0027961293,0.00052849075,0.009991435,0.0020794007,0.00037008658,0.000004640304,0.00006774807,0.04302062],"genre_scores_gemma":[0.9854618,0.0001802016,0.001427036,0.0011425812,0.00094624213,0.000086777254,0.00008540676,0.000006100399,0.0106638735],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9978193,0.0005380501,0.00030614698,0.00039073563,0.0007060673,0.00023967671],"domain_scores_gemma":[0.99889046,0.00022767366,0.0002508713,0.00021224112,0.00025382004,0.0001649404],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006504209,0.00012577273,0.00012613645,0.00013497715,0.0021214853,0.00061815477,0.0005842777,0.000069859474,0.000705145],"category_scores_gemma":[0.0008496629,0.00009550975,0.00008988016,0.0012549933,0.00050001085,0.0011023117,0.00011446648,0.00016878908,0.00004754153],"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":[0.000018688268,0.004933097,0.22459638,0.00009447972,0.00007365283,7.745605e-7,0.66752726,0.00008013162,0.0011825102,0.045759343,0.023030503,0.032703187],"study_design_scores_gemma":[0.00022293947,0.000016303768,0.14809956,0.000070987,0.00002488596,0.0000018445111,0.8014282,0.00018540304,0.00010840257,0.007240583,0.042388964,0.00021192747],"about_ca_topic_score_codex":0.0048374385,"about_ca_topic_score_gemma":0.0041832607,"teacher_disagreement_score":0.13390096,"about_ca_system_score_codex":0.000416148,"about_ca_system_score_gemma":0.0036490576,"threshold_uncertainty_score":0.99917763},"labels":[],"label_agreement":null},{"id":"W3188171252","doi":"10.1007/s10459-021-10063-w","title":"Implicit and inferred: on the philosophical positions informing assessment science","year":2021,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; St. Michael's Hospital; The Wilson Centre; Centre for Global Health Research; University of Toronto; University Health Network","funders":"","keywords":"Philosophical methodology; Competence (human resources); Epistemology; Construct (python library); Philosophical analysis; Psychology; Computer science; Social psychology; Philosophy","score_opus":0.037830304246417173,"score_gpt":0.4821125215118375,"score_spread":0.4442822172654203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188171252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50957084,0.0023488698,0.00013287248,0.2739532,0.0020045848,0.00070387544,0.000002386714,0.000043691445,0.21123968],"genre_scores_gemma":[0.99006605,0.0031892657,0.002073497,0.004316402,0.00019531784,0.00006546511,0.0000020209757,0.000002540834,0.000089414505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99803066,0.00015450279,0.0002771127,0.0003372712,0.00077739777,0.0004230404],"domain_scores_gemma":[0.9989452,0.00048388078,0.00013883485,0.00015163103,0.00014075782,0.00013970777],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0029191936,0.000082448605,0.00010667423,0.00018353447,0.0027765282,0.00029022375,0.00036520677,0.000027886223,0.000055228636],"category_scores_gemma":[0.000412814,0.00006381593,0.000017500888,0.0019997514,0.0014679787,0.0013033844,0.00007916734,0.00017711047,0.0000057022708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010801356,0.00009135872,0.06341044,0.000009997088,5.670005e-7,2.1019713e-7,0.004207106,0.000036665766,0.00002569094,0.90819794,0.000046958015,0.023971993],"study_design_scores_gemma":[0.00026455362,0.00030967096,0.53055525,0.00042940595,0.000005161822,0.000008614384,0.09548578,0.00053619954,0.00007247364,0.31271815,0.059250027,0.00036468054],"about_ca_topic_score_codex":0.00050722173,"about_ca_topic_score_gemma":0.0010135196,"teacher_disagreement_score":0.5954798,"about_ca_system_score_codex":0.00036905627,"about_ca_system_score_gemma":0.005246609,"threshold_uncertainty_score":0.99852175},"labels":[],"label_agreement":null},{"id":"W3191701502","doi":"10.1080/0142159x.2021.1957088","title":"Ottawa 2020 consensus statement for programmatic assessment – 1. Agreement on the principles","year":2021,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":115,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Operationalization; Medical education; Curriculum; Program evaluation; Engineering ethics; Medicine; Psychology; Political science; Pedagogy; Engineering","score_opus":0.07826089378203037,"score_gpt":0.4097405264132591,"score_spread":0.3314796326312287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191701502","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30004635,0.00021359773,0.0012425532,0.3118043,0.0013286188,0.0027951265,0.000007051676,0.00015383914,0.38240856],"genre_scores_gemma":[0.91428787,0.00013500948,0.003159609,0.0022663635,0.0012430045,0.0009615988,0.000041498868,0.00002814251,0.07787691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966165,0.0005358532,0.00038740563,0.00028724282,0.0017236278,0.00044936297],"domain_scores_gemma":[0.99882644,0.00047476622,0.0001154181,0.00024054525,0.00011501037,0.00022779434],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038662232,0.00013559399,0.00019038541,0.00001616631,0.00049480033,0.00013592647,0.00034312945,0.000096789154,0.01101056],"category_scores_gemma":[0.0012537378,0.00008767218,0.00012056719,0.00017288527,0.0002732927,0.000023912049,0.00009959526,0.00024992652,0.000084318046],"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":[0.00003706308,0.0025796012,0.0900499,0.00009598891,0.0005817222,0.00013435516,0.015326238,0.000006110052,0.00003554557,0.4634986,0.38222587,0.045429017],"study_design_scores_gemma":[0.0007923783,0.00012293055,0.0054211677,0.00006623169,0.000046309746,6.656558e-7,0.018213948,0.0010463803,0.000020123163,0.0012366252,0.9728657,0.00016753351],"about_ca_topic_score_codex":0.00010479881,"about_ca_topic_score_gemma":0.0010801699,"teacher_disagreement_score":0.6142415,"about_ca_system_score_codex":0.0002461123,"about_ca_system_score_gemma":0.0007199071,"threshold_uncertainty_score":0.9898935},"labels":[],"label_agreement":null},{"id":"W3191913029","doi":"10.20343/teachlearninqu.9.2.18","title":"Can Relational Feed-Forward Enhance Students’ Cognitive and Affective Responses to Assessment?","year":2021,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Psychology; Thematic analysis; Rubric; Cognition; Qualitative research; Medical education; Pedagogy","score_opus":0.04183766046924296,"score_gpt":0.41995587850686356,"score_spread":0.3781182180376206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191913029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97318333,0.00017550065,0.0038400393,0.013883931,0.00081208895,0.00024376113,0.0000023972286,0.000076237244,0.0077826893],"genre_scores_gemma":[0.983549,0.00014532516,0.001241016,0.0006956871,0.0012543396,0.000013966275,0.000005024452,0.000025815167,0.013069851],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.993638,0.0038821655,0.0003091843,0.00034269004,0.001330618,0.0004973373],"domain_scores_gemma":[0.9966996,0.0023555944,0.00027656794,0.00011641666,0.00029702683,0.0002548514],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0065467255,0.00019952668,0.0002556574,0.0001369657,0.0047743325,0.00093654764,0.00039555033,0.00009664582,0.00023242824],"category_scores_gemma":[0.0035907154,0.0001498389,0.00011026405,0.0002973021,0.00031901538,0.0003813319,0.00029710034,0.002053977,0.000030388164],"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":[0.00015404439,0.00014872442,0.7500564,0.0000043907353,0.00031463822,0.00009229093,0.22494608,0.00012992909,0.00069723354,0.006102548,0.0013413903,0.016012358],"study_design_scores_gemma":[0.0006606859,0.00021467997,0.79298276,0.00024316445,0.00011596286,0.00006863777,0.18455239,0.000025357436,0.00004402659,0.0008735427,0.019923646,0.00029513068],"about_ca_topic_score_codex":0.0001616173,"about_ca_topic_score_gemma":0.00019279763,"teacher_disagreement_score":0.04292641,"about_ca_system_score_codex":0.00036293457,"about_ca_system_score_gemma":0.0005545235,"threshold_uncertainty_score":0.9965213},"labels":[],"label_agreement":null},{"id":"W3192331548","doi":"10.5430/wjel.v11n2p107","title":"The Effects of Formative Evaluation on Students' Achievement in English for Specific Purposes (A Case Study of the Preparatory Year Students at Umm- Al-Qura University)","year":2021,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Mathematics education; Medical education; Control (management); Psychology; Pedagogy; Medicine; Computer science","score_opus":0.016403695714600586,"score_gpt":0.33835593444764445,"score_spread":0.32195223873304385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192331548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99376434,0.00042361856,0.0000010524443,0.000032282074,0.0014796411,0.0012222269,0.0000047937383,0.000005083141,0.0030669344],"genre_scores_gemma":[0.9985072,0.000119609016,0.000016755102,0.000021941718,0.00022772801,0.000008132779,9.727805e-7,0.000007651621,0.001090022],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99686086,0.0009006793,0.00041291508,0.00013088068,0.0015077534,0.00018693724],"domain_scores_gemma":[0.9971831,0.00097026525,0.0005796812,0.00021993867,0.0009972606,0.000049765684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024433874,0.000108649365,0.0002457956,0.00015985088,0.0003083264,0.00007054098,0.0006348163,0.00003110533,0.000028191862],"category_scores_gemma":[0.0010720124,0.00007536095,0.00014613397,0.0005980991,0.00009036,0.00022074071,0.00020865444,0.0001876509,4.1993476e-7],"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":[0.0003752584,0.0024672865,0.2761261,0.000033564724,0.00037634,0.00024774982,0.71603066,0.000063662126,0.0001986549,0.00061684666,0.0023902303,0.0010736649],"study_design_scores_gemma":[0.005483486,0.00055139425,0.093215965,0.00019092832,0.00018310016,0.0000010680011,0.886833,0.000001925141,0.00079862523,0.000014073844,0.012618903,0.00010754015],"about_ca_topic_score_codex":0.000060251547,"about_ca_topic_score_gemma":0.006884085,"teacher_disagreement_score":0.1829101,"about_ca_system_score_codex":0.00041118608,"about_ca_system_score_gemma":0.00013150011,"threshold_uncertainty_score":0.38414812},"labels":[],"label_agreement":null},{"id":"W3194429716","doi":"10.1007/978-981-16-3603-5_4","title":"Global ESOL Assessment Practices: The Washback Effect and Automated Testing in China","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Yorkville University","funders":"","keywords":"Language assessment; German; China; Foreign language; Test (biology); Language education; Computer science; Language industry; Mathematics education; Pedagogy; Comprehension approach; Psychology; Political science; Linguistics","score_opus":0.038857434390824924,"score_gpt":0.39103532223587484,"score_spread":0.3521778878450499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194429716","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039448226,0.00045483603,0.000007412649,0.0014624599,0.000387084,0.00084121875,0.000006421629,0.0002758672,0.9926199],"genre_scores_gemma":[0.23471291,0.0013172618,0.0033381328,0.0005672557,0.0011317054,0.00009096236,0.00006569008,0.00008110275,0.758695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9977234,0.000290689,0.00033248815,0.0004819016,0.00079310127,0.0003784424],"domain_scores_gemma":[0.9978336,0.0012138359,0.0005177681,0.00025016518,0.00008960051,0.00009500724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016925157,0.00031860435,0.00041900267,0.00004883023,0.00047499067,0.000542494,0.000377028,0.00031186387,0.00077086024],"category_scores_gemma":[0.00050341786,0.00022094027,0.00008823051,0.00019754934,0.00024436548,0.00022117882,0.0002766702,0.0004154204,0.00002666139],"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":[0.00002661552,0.000111671,0.31159827,0.00014924884,0.00038484274,0.00024158545,0.0030812814,0.000011949215,0.000008999306,0.648923,0.009687291,0.025775291],"study_design_scores_gemma":[0.0027606585,0.0006105349,0.688629,0.0016022566,0.00077535305,0.000033535212,0.0074654743,0.004085657,0.0000018494167,0.010661411,0.28120217,0.0021721078],"about_ca_topic_score_codex":0.003317518,"about_ca_topic_score_gemma":0.008595009,"teacher_disagreement_score":0.63826156,"about_ca_system_score_codex":0.00036866125,"about_ca_system_score_gemma":0.0004963941,"threshold_uncertainty_score":0.9009683},"labels":[],"label_agreement":null},{"id":"W3197741744","doi":"10.4018/978-1-7998-8275-6.ch012","title":"Beyond High-Stakes Assessment","year":2021,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Accreditation; Summative assessment; Certification; Medical education; Function (biology); Psychology; Standardized test; Measure (data warehouse); Mathematics education; Political science; Medicine; Computer science; Formative assessment","score_opus":0.027403880283262506,"score_gpt":0.3657024686300425,"score_spread":0.33829858834678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197741744","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034413932,0.03308549,0.0000015248967,0.005864109,0.01076987,0.00047816275,0.0000078161265,0.00005434871,0.9493945],"genre_scores_gemma":[0.0019397511,0.027538063,0.004739937,0.0012982872,0.0006228993,0.00018533118,0.00031561233,0.00003508094,0.963325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997751,0.0000942407,0.00051637366,0.00053225766,0.00077909516,0.000327009],"domain_scores_gemma":[0.9990202,0.00016100757,0.00028694767,0.00017003831,0.00021558706,0.00014622853],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034312406,0.0003579312,0.0004008677,0.00019152179,0.0006758177,0.0001250305,0.00023465902,0.0003122787,0.011058233],"category_scores_gemma":[0.000011182139,0.00034659353,0.000048994203,0.000087286695,0.00032018436,0.0013199776,0.00014653786,0.00041135532,0.000040190247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018840274,0.00011878927,0.003752,0.00009044585,0.000034304183,0.0000052089063,0.0038586985,3.4167587e-7,0.0000030984295,0.9688464,0.006425873,0.01684601],"study_design_scores_gemma":[0.00018504301,0.0000155226,0.028133579,0.0005996768,0.000015616124,8.456249e-7,0.0025021082,2.4042203e-8,0.000006971489,0.03789541,0.9302124,0.00043284273],"about_ca_topic_score_codex":0.000017538616,"about_ca_topic_score_gemma":0.00047007637,"teacher_disagreement_score":0.930951,"about_ca_system_score_codex":0.0003923756,"about_ca_system_score_gemma":0.0033644012,"threshold_uncertainty_score":0.9998986},"labels":[],"label_agreement":null},{"id":"W3200087034","doi":"10.5539/ies.v14n10p65","title":"Digital Assessment Literacy: The Need of Online Assessment Literacy and Online Assessment Literate Educators","year":2021,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Literacy; Medical education; Digital literacy; Needs assessment; Psychology; Information literacy; Professional development; Mathematics education; Pedagogy; Sociology; Medicine","score_opus":0.041525946898013893,"score_gpt":0.48765904690363954,"score_spread":0.44613310000562567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200087034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89864224,0.0026903069,0.0002371303,0.061952032,0.0072736414,0.00040674215,0.00024297935,0.000054944492,0.028499965],"genre_scores_gemma":[0.9675868,0.0028769702,0.011422339,0.0011418175,0.0011623026,0.00009750419,0.0005464194,0.000020287447,0.015145547],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99714303,0.00028631437,0.00073267816,0.00045313485,0.0010935438,0.00029132495],"domain_scores_gemma":[0.99505395,0.00076067785,0.00044942446,0.0002942061,0.0033217676,0.000119948345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006415252,0.0002616928,0.00036577665,0.00020420818,0.0005096436,0.000874028,0.00045202524,0.000056859215,0.00027235734],"category_scores_gemma":[0.0004124427,0.00020904401,0.00014516426,0.0005284889,0.00037057357,0.001076564,0.00037134907,0.00030050447,0.000005213379],"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":[0.000029928922,0.007462815,0.59260005,0.00010878794,0.0018890447,0.000010627175,0.07359598,0.000016494072,0.0003355981,0.10053113,0.014249172,0.20917039],"study_design_scores_gemma":[0.00058615516,0.00007510831,0.5510993,0.00026576122,0.000097647586,0.0000064852184,0.14824837,0.0001711351,0.000023039796,0.0039729513,0.29514292,0.0003111319],"about_ca_topic_score_codex":0.00014147379,"about_ca_topic_score_gemma":0.0001241443,"teacher_disagreement_score":0.28089374,"about_ca_system_score_codex":0.00052349764,"about_ca_system_score_gemma":0.002322041,"threshold_uncertainty_score":0.85245675},"labels":[],"label_agreement":null},{"id":"W3202203794","doi":"","title":"An Integrated Design and Appraisal Framework for Ethical Writing Assessment","year":2016,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"General partnership; Engineering ethics; Management science; Critical appraisal; Sociology; Psychology; Engineering; Political science; Medicine","score_opus":0.037488699228800985,"score_gpt":0.35270298762733926,"score_spread":0.31521428839853827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202203794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21678048,0.00009749033,0.74786276,0.01781574,0.00055674935,0.0015216748,0.0010386906,0.0010798788,0.013246554],"genre_scores_gemma":[0.89017034,0.00003629653,0.10807529,0.0006900048,0.0004810619,0.000084066014,0.000092517446,0.000057590423,0.00031285224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751663,0.00041116914,0.0003796974,0.00052233075,0.0005438784,0.0006262867],"domain_scores_gemma":[0.9956484,0.0034538037,0.00012620082,0.00023060387,0.00007921147,0.00046178352],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012218341,0.00025391494,0.0002710241,0.00010263015,0.00058540225,0.0024741862,0.00052645133,0.0005080459,0.00040726157],"category_scores_gemma":[0.0013969959,0.00018523671,0.00010779668,0.00032068844,0.0003791248,0.0035749257,0.00011901335,0.0005821553,0.0001264102],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026334682,0.00031504684,0.40095726,0.000028408655,0.000081471815,0.000012321699,0.00056743727,0.0000012955886,0.00040217288,0.5007104,0.0029720485,0.09368878],"study_design_scores_gemma":[0.0026192132,0.0008633507,0.043998532,0.0006300276,0.00007741144,0.0000039909255,0.004549649,0.0003355446,0.0006478556,0.30235976,0.64232403,0.0015906171],"about_ca_topic_score_codex":0.000004888153,"about_ca_topic_score_gemma":0.000002243837,"teacher_disagreement_score":0.67338985,"about_ca_system_score_codex":0.000058869573,"about_ca_system_score_gemma":0.0003401655,"threshold_uncertainty_score":0.9985613},"labels":[],"label_agreement":null},{"id":"W3202681787","doi":"10.1111/bjet.13169","title":"COVID‐19 as the tipping point for integrating e‐assessment in higher education practices","year":2021,"lang":"en","type":"article","venue":"British Journal of Educational Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Tipping point (physics); Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Higher education; Medicine; Virology; Economics; Engineering; Economic growth","score_opus":0.0578890967993076,"score_gpt":0.4468809123947186,"score_spread":0.388991815595411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202681787","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19961968,0.0052839234,0.000111128684,0.75924987,0.002465698,0.00033838802,0.0000029359987,0.000015365744,0.032913003],"genre_scores_gemma":[0.9792018,0.0010252786,0.010377475,0.002317798,0.001082071,0.00008468591,0.000009872285,0.0000088137085,0.005892235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987925,0.00017190637,0.00039292578,0.00014400556,0.00030677303,0.0001918558],"domain_scores_gemma":[0.99741226,0.0010316652,0.0007574284,0.00008470682,0.0006265666,0.00008734094],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013471066,0.00006575776,0.00014511464,0.00018011485,0.00046950197,0.00020218373,0.00036647875,0.00010875229,0.001762991],"category_scores_gemma":[0.0075031775,0.00006580407,0.00007066727,0.0005734078,0.00017410533,0.00032893635,0.000043469056,0.00039876706,0.000004226457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010853217,0.0006000108,0.048963606,0.000015789085,0.0000540003,0.000014281247,0.002002438,0.0000047360345,0.0002849862,0.9090035,0.019961137,0.019084675],"study_design_scores_gemma":[0.00055005186,0.00007333575,0.05576666,0.00023400439,0.000034078195,0.0006618462,0.105753094,0.0000040279524,0.000031835887,0.36962375,0.467113,0.0001543347],"about_ca_topic_score_codex":0.0006658109,"about_ca_topic_score_gemma":0.0020354844,"teacher_disagreement_score":0.7795821,"about_ca_system_score_codex":0.0005136135,"about_ca_system_score_gemma":0.00985722,"threshold_uncertainty_score":0.99914956},"labels":[],"label_agreement":null},{"id":"W3204027159","doi":"","title":"Implications of Standardized Testing in Teacher Education: A Look at Perceptions, Experiences and Impacts on Teacher Candidates","year":2020,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Standardized test; Certification; Psychology; Teacher education; Medical education; Perception; Teacher preparation; Test (biology); Mathematics education; Accreditation; Government (linguistics); Pedagogy; Medicine; Political science","score_opus":0.0457849572758282,"score_gpt":0.38077216744960946,"score_spread":0.33498721017378125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204027159","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85778826,0.000083958796,0.000011280169,0.004661556,0.00002716468,0.00022488908,0.0000021759809,0.000030835003,0.13716987],"genre_scores_gemma":[0.99682736,0.000046994748,0.00055484683,0.00027343107,0.000109307395,0.00006239511,0.0000034879265,0.0000050109334,0.0021171342],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991949,0.00008433705,0.00017202423,0.00018808142,0.00020370398,0.00015695686],"domain_scores_gemma":[0.99957615,0.00010499765,0.00006450331,0.00007953053,0.000055781544,0.00011905098],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024342955,0.000075664786,0.00012637055,0.000045287004,0.00023489809,0.0000523621,0.00012125238,0.000042573985,0.0019427139],"category_scores_gemma":[0.00029646943,0.00006444959,0.00002238438,0.00032621733,0.00017503396,0.00014669208,0.00004456706,0.00006642309,0.000013247365],"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":[0.00002129951,0.00009167097,0.86569506,0.0000038422963,0.0000043094624,9.505177e-8,0.12538502,4.6350056e-7,0.0009828099,0.001117929,0.0033302964,0.0033672303],"study_design_scores_gemma":[0.00031119955,0.00009680842,0.71493644,0.000024698813,0.00000929431,2.677705e-7,0.28148088,0.000029601393,0.00007170364,0.00013387109,0.0027838757,0.0001213698],"about_ca_topic_score_codex":0.0013828573,"about_ca_topic_score_gemma":0.001449393,"teacher_disagreement_score":0.15609586,"about_ca_system_score_codex":0.00011829768,"about_ca_system_score_gemma":0.00028817772,"threshold_uncertainty_score":0.9989697},"labels":[],"label_agreement":null},{"id":"W3209301443","doi":"10.5539/elt.v14n12p1","title":"Exploring Secondary School EFL Teachers’ Assessment Literacy in Practice: A Case Study in China","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Guangdong University of Foreign Studies","keywords":"Psychology; Internship; Literacy; Pedagogy; Medical education; Focus group; Mathematics education; Sociology; Medicine","score_opus":0.03903641093597413,"score_gpt":0.40236822463480165,"score_spread":0.3633318136988275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209301443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8889531,0.0003995528,0.000017264218,0.00024440716,0.0006548272,0.0005047865,0.0000020514701,0.00014118572,0.10908286],"genre_scores_gemma":[0.9950504,0.00004240041,0.0029118836,0.00012775487,0.00079212984,0.00013631347,0.000010974974,0.000030507998,0.0008976379],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9953452,0.00245926,0.0004629688,0.00053270574,0.00063636026,0.0005635004],"domain_scores_gemma":[0.9986652,0.00061671523,0.00013303923,0.00035797906,0.000059865673,0.00016720344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049674483,0.00021957174,0.0003216692,0.0002833591,0.00044772687,0.0006363516,0.00029269172,0.00008228742,0.00043374026],"category_scores_gemma":[0.003654695,0.00024197981,0.000077163015,0.0006268686,0.000034497647,0.003221328,0.00023251439,0.001978476,0.000011178586],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000575321,0.000756837,0.24372578,0.000006789345,0.000029654266,0.017652668,0.7113385,0.000009822041,0.000046352197,0.00027147835,0.000025997111,0.026130367],"study_design_scores_gemma":[0.0013975751,0.000044528366,0.08809906,0.00007896041,0.00002686824,0.00003792597,0.90747964,0.000022667904,0.0000061531623,0.000010376347,0.0025346603,0.0002615674],"about_ca_topic_score_codex":0.02420998,"about_ca_topic_score_gemma":0.01933582,"teacher_disagreement_score":0.19614115,"about_ca_system_score_codex":0.00069835974,"about_ca_system_score_gemma":0.0004529108,"threshold_uncertainty_score":0.99855876},"labels":[],"label_agreement":null},{"id":"W3210068963","doi":"10.1080/0969594x.2021.1988510","title":"Formative assessment, growth mindset, and achievement: examining their relations in the East and the West","year":2021,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mindset; Formative assessment; Psychology; Reading (process); Mainland China; Academic achievement; Pedagogy; Mathematics education; China; Political science; Computer science","score_opus":0.07796939436320567,"score_gpt":0.42193192942447144,"score_spread":0.3439625350612658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210068963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51677626,0.00065425487,0.00011644991,0.16626662,0.00021188702,0.00076819584,0.000008700095,0.000015016951,0.3151826],"genre_scores_gemma":[0.99040806,0.003560904,0.0019259823,0.0028958663,0.00021405215,0.00019888469,0.00002652764,0.000008007668,0.00076170365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99643284,0.0022921714,0.0003665297,0.00027048984,0.00035883792,0.00027910524],"domain_scores_gemma":[0.9934272,0.0058898195,0.00029142798,0.00019223773,0.00013139687,0.00006790744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004968341,0.0001533237,0.0001754987,0.00015254256,0.0008857095,0.00057652243,0.00020252728,0.000075328884,0.00003403229],"category_scores_gemma":[0.0016985696,0.000106408115,0.000021660237,0.0007078957,0.00036852385,0.0014114715,0.00016335557,0.00045077046,0.0000019566064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018804996,0.00029174722,0.12295666,0.000013066437,0.000028740207,0.0000012137617,0.16448733,0.0000019629288,0.000008965343,0.70885235,0.00009091223,0.003248253],"study_design_scores_gemma":[0.00069542165,0.000022938051,0.55200946,0.00003515187,0.000035019937,0.000012976049,0.40428564,0.00007671639,0.0000010663888,0.0060067377,0.0367156,0.000103260805],"about_ca_topic_score_codex":0.0027644853,"about_ca_topic_score_gemma":0.0037524144,"teacher_disagreement_score":0.7028456,"about_ca_system_score_codex":0.00017798628,"about_ca_system_score_gemma":0.0014827205,"threshold_uncertainty_score":0.68122506},"labels":[],"label_agreement":null},{"id":"W3210142070","doi":"10.1016/j.jslw.2021.100850","title":"What works may hurt: The negative side of feedback in second language writing","year":2021,"lang":"en","type":"article","venue":"Journal of Second Language Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Negative feedback; Constructive; Quality (philosophy); Psychology; Corrective feedback; Peer feedback; Feedback loop; Positive feedback; Second language writing; Social psychology; Computer science; Second language; Mathematics education; Linguistics; Computer security","score_opus":0.01804869953246795,"score_gpt":0.33177635910815306,"score_spread":0.3137276595756851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210142070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94916785,0.011681706,0.000008375044,0.0012143331,0.000442895,0.0001306075,0.0000057945767,0.000010898909,0.03733755],"genre_scores_gemma":[0.9949793,0.00046391576,0.0007091709,0.0006040308,0.001070113,0.0000026089097,0.0000032017601,0.000020379193,0.0021472473],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9973853,0.00048531653,0.0008777487,0.00018485988,0.00062154897,0.00044521352],"domain_scores_gemma":[0.99725527,0.0014009728,0.000769328,0.00017245168,0.0002950777,0.00010687472],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025802753,0.00016535052,0.00043616557,0.000154873,0.00026544734,0.0006130465,0.00044949254,0.00013014984,0.004915409],"category_scores_gemma":[0.00061087025,0.00013609868,0.00022111175,0.00060686114,0.00018546337,0.0015572062,0.00012194089,0.0007552979,0.000009563178],"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":[0.000089992456,0.0002931425,0.036800317,0.00022048326,0.00033531725,0.0023644129,0.7838211,0.000040497216,0.048465393,0.0015536293,0.0010581336,0.1249576],"study_design_scores_gemma":[0.0009327623,0.00003360275,0.023088822,0.0013224942,0.00003222717,0.000044744673,0.96771014,0.000013131324,0.0059760725,0.00014491638,0.0005328788,0.00016818797],"about_ca_topic_score_codex":0.0001958351,"about_ca_topic_score_gemma":0.008804001,"teacher_disagreement_score":0.18388908,"about_ca_system_score_codex":0.0001245241,"about_ca_system_score_gemma":0.00028492953,"threshold_uncertainty_score":0.9959942},"labels":[],"label_agreement":null},{"id":"W3211638126","doi":"10.1097/acm.0000000000004507","title":"Written-Based Progress Testing: A Scoping Review.","year":2022,"lang":"en","type":"article","venue":"PubMed","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada; Université de Sherbrooke","funders":"","keywords":"PsycINFO; Facilitator; CINAHL; MEDLINE; Formative assessment; Test (biology); Medical education; Psychology; Medicine; Nursing; Social psychology; Mathematics education; Psychological intervention","score_opus":0.09513950111257642,"score_gpt":0.3651457225609909,"score_spread":0.2700062214484145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211638126","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09789324,0.076431714,0.00006932704,0.10258171,0.0045340005,0.030473042,0.000025306124,0.0019814905,0.6860102],"genre_scores_gemma":[0.98044294,0.00019177879,0.0004451284,0.0027064134,0.00031973675,0.013848745,0.000007650474,0.000016288639,0.002021344],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983465,0.00023045167,0.00016390269,0.00019058652,0.0006517951,0.0004167363],"domain_scores_gemma":[0.999478,0.00014377237,0.00010014364,0.00012487131,0.000055107485,0.000098135315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001599018,0.00006993707,0.00013622877,0.000045637054,0.00082624116,0.000068261055,0.00034414962,0.00001591088,0.00029185452],"category_scores_gemma":[0.00035536938,0.00007304364,0.000052302967,0.00066365505,0.00013594991,0.00007669933,0.00010233145,0.00011372916,0.000009901041],"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":[0.00002110778,0.00037998497,0.6394505,0.0009729712,0.000032491367,0.000035059318,0.0015468082,0.000011829502,0.0000023537273,0.00254912,0.02261332,0.33238447],"study_design_scores_gemma":[0.0019177177,0.00011700112,0.78279513,0.0035114982,0.0001723437,0.0000027619844,0.00406486,0.000103241,0.00002216898,0.0006184748,0.20555028,0.001124516],"about_ca_topic_score_codex":0.00008084717,"about_ca_topic_score_gemma":0.000047499725,"teacher_disagreement_score":0.8825497,"about_ca_system_score_codex":0.00012679429,"about_ca_system_score_gemma":0.00018965699,"threshold_uncertainty_score":0.63548625},"labels":[],"label_agreement":null},{"id":"W3212616294","doi":"","title":"Ontario Elementary School Teachers' Approaches to Mathematics Assessment for Diverse Students","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Pedagogy; Mathematics; Psychology","score_opus":0.03906997615594648,"score_gpt":0.28939211954308985,"score_spread":0.25032214338714337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212616294","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6796334,0.000026100375,0.0005904253,0.023397932,0.00197599,0.0052437345,0.00017681773,0.0004260678,0.28852957],"genre_scores_gemma":[0.016588336,0.00013853377,0.037683014,0.00019722355,0.00032452377,0.000028433618,0.00231735,0.0000695109,0.94265306],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9967611,0.00021731302,0.00028823098,0.00079130486,0.0012709717,0.0006710898],"domain_scores_gemma":[0.9984542,0.00016771462,0.0003253065,0.00043287146,0.00009690428,0.0005229646],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025623114,0.00047346685,0.0006030852,0.000384804,0.0010513575,0.00058008655,0.0014640628,0.00042845335,0.0039606076],"category_scores_gemma":[0.000035842135,0.00057945185,0.00039149646,0.00055904745,0.0000704035,0.0013049304,0.0004407413,0.00057112577,0.000088155386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020990975,0.001288745,0.34263545,0.00024369809,0.0011412033,0.00009940492,0.1315615,0.000009857959,0.0000034212676,0.01359706,0.5084843,0.00072545256],"study_design_scores_gemma":[0.001003459,0.00013585905,0.07299073,0.0002214043,0.0005062688,2.5639551e-8,0.49813795,8.1890494e-7,0.000045241453,0.00028597843,0.42591617,0.00075609295],"about_ca_topic_score_codex":0.07770885,"about_ca_topic_score_gemma":0.1230054,"teacher_disagreement_score":0.66304505,"about_ca_system_score_codex":0.001495724,"about_ca_system_score_gemma":0.00225071,"threshold_uncertainty_score":0.9996657},"labels":[],"label_agreement":null},{"id":"W3213817778","doi":"","title":"Conrad, Dianne; Openo, Jason. Assessment strategies for online learning. Engagement and authenticity. Edmonton: Athabasca University Press, 2018, ISBN:978-1-77199-233-6","year":2021,"lang":"es","type":"article","venue":"Revista Latinoamericana de Difusión Científica","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Media studies; Sociology","score_opus":0.03236000520398399,"score_gpt":0.32440344464953874,"score_spread":0.2920434394455548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213817778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8945049,0.0074928207,0.008367537,0.008219818,0.0010326023,0.0040774313,0.0015856447,0.00038972864,0.07432949],"genre_scores_gemma":[0.959558,0.014210126,0.0073841903,0.00032023728,0.0006268403,0.000038085807,0.00042190385,0.00008473873,0.017355876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99395806,0.0015288424,0.000720901,0.0013495403,0.0011333096,0.001309335],"domain_scores_gemma":[0.99652064,0.0009125633,0.00081776915,0.00064151705,0.00049546873,0.0006120685],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014825378,0.0006540235,0.0010740331,0.00014865043,0.0018775314,0.0019343891,0.000900401,0.0002567614,0.00065934745],"category_scores_gemma":[0.00037501927,0.0007245624,0.00043250562,0.0010041485,0.0008386458,0.00063249393,0.00081242545,0.00074778026,0.000014529883],"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":[0.0006238754,0.006976897,0.23512816,0.0034675742,0.0032592264,0.0006964702,0.06046683,0.0003691388,0.003959586,0.5549456,0.062081035,0.06802559],"study_design_scores_gemma":[0.0016373436,0.00040693145,0.10560323,0.00031588777,0.00069560984,0.000004114872,0.08185439,0.0034727952,0.000016397122,0.000050292463,0.8051124,0.0008305871],"about_ca_topic_score_codex":0.0028661098,"about_ca_topic_score_gemma":0.00046468835,"teacher_disagreement_score":0.7430314,"about_ca_system_score_codex":0.00070372835,"about_ca_system_score_gemma":0.0016351192,"threshold_uncertainty_score":0.99952054},"labels":[],"label_agreement":null},{"id":"W3214027731","doi":"10.1177/02655322211052680","title":"Investigating and optimizing score dependability of a local ITA speaking test across language groups: A generalizability theory approach","year":2021,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalizability theory; Dependability; Language proficiency; Psychology; Variance (accounting); Test (biology); Construct (python library); Formative assessment; Computer science; Mathematics education; Developmental psychology; Accounting","score_opus":0.050868985531210546,"score_gpt":0.3497865942429446,"score_spread":0.29891760871173406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214027731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98038435,0.0011528842,0.0047810245,0.000044148735,0.00006582489,0.00023256343,0.00001666114,0.00015781727,0.01316473],"genre_scores_gemma":[0.93098235,0.0000042540373,0.06854533,0.00010991435,0.00022123879,0.00001201781,0.000015683407,0.000021010947,0.00008821429],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99761295,0.00050648104,0.00039708952,0.0005083492,0.00044740277,0.00052771973],"domain_scores_gemma":[0.9972788,0.0018545347,0.00022308495,0.00032554808,0.00016898093,0.00014902363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029051993,0.00019110511,0.00033547494,0.000031750697,0.0005742435,0.0001790089,0.00026772174,0.00011366411,0.00006458023],"category_scores_gemma":[0.0068359906,0.00018702577,0.000076177195,0.0006511075,0.0007264764,0.00027953964,0.00038376372,0.00026989277,0.0000015083446],"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":[0.000004317801,0.00015638063,0.6197887,0.00023000389,0.000026692574,0.000048284066,0.32065213,0.000079439444,0.027888648,0.0017110135,0.000004185023,0.02941021],"study_design_scores_gemma":[0.0006748703,0.000045657373,0.09744235,0.00025980826,0.000060857717,0.000024148412,0.8915778,0.003956292,0.004598945,0.00089438155,0.000008816892,0.00045611832],"about_ca_topic_score_codex":0.0031399147,"about_ca_topic_score_gemma":0.0015628922,"teacher_disagreement_score":0.57092565,"about_ca_system_score_codex":0.00010112506,"about_ca_system_score_gemma":0.00016792513,"threshold_uncertainty_score":0.8183813},"labels":[],"label_agreement":null},{"id":"W3215227414","doi":"10.5539/elt.v14n12p183","title":"Teachers’ Practice and Perceptions of Self-Assessment and Peer Assessment of Presentation Skills","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; Peer assessment; Psychology; Assessment for learning; Medical education; Presentation (obstetrics); Pedagogy; Self-assessment; Mathematics education; Medicine; Formative assessment","score_opus":0.009395595803848704,"score_gpt":0.38553344987276483,"score_spread":0.37613785406891614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215227414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92169017,0.00019886404,0.0004966457,0.00048628403,0.00016511098,0.00018577065,0.000006900681,0.00005328027,0.07671698],"genre_scores_gemma":[0.95835274,0.000160662,0.04022657,0.00004249464,0.00019496781,0.000009492821,0.00002077626,0.000010227995,0.0009820366],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99800503,0.0007275786,0.00024232679,0.00021793127,0.00063733326,0.00016978575],"domain_scores_gemma":[0.9987508,0.00062126573,0.00018149056,0.00014843422,0.00022436948,0.00007363854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001972783,0.00009786477,0.0001940906,0.00006559208,0.00026706126,0.00010739669,0.00009800157,0.0000716084,0.00014505313],"category_scores_gemma":[0.0008223043,0.00010034494,0.000044008037,0.00012620595,0.00009170843,0.0005459306,0.00010746336,0.0002972243,3.2992187e-7],"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":[0.0000015113542,0.0003306581,0.27218652,0.000024308125,0.00007659155,0.0000069010634,0.7088447,0.0000027061708,0.002469927,0.011507403,0.00016672097,0.0043820427],"study_design_scores_gemma":[0.0004324921,0.00003395484,0.27591032,0.000031616444,0.00010278033,0.0000014162785,0.72164685,0.000048583068,0.00006031072,0.000039912873,0.0015906541,0.0001011526],"about_ca_topic_score_codex":0.00083944545,"about_ca_topic_score_gemma":0.00023178461,"teacher_disagreement_score":0.07573494,"about_ca_system_score_codex":0.00010478177,"about_ca_system_score_gemma":0.00019351253,"threshold_uncertainty_score":0.4091948},"labels":[],"label_agreement":null},{"id":"W3216763624","doi":"10.37213/cjal.2021.31242","title":"Is Less Really More? The Case for Comprehensive Written Corrective Feedback","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Corrective feedback; Exploit; Focus (optics); Second-language acquisition; Psychology; Cognitive psychology; Computer science; Empirical research; Mathematics education; Linguistics; Epistemology","score_opus":0.05410565985707475,"score_gpt":0.3385950120407823,"score_spread":0.2844893521837075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216763624","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27100176,0.0018918981,0.0016112668,0.015745945,0.01663637,0.0017778106,0.00048527637,0.000053793457,0.6907959],"genre_scores_gemma":[0.99220747,0.00005765935,0.0019599176,0.0019274825,0.0031077587,0.000005916221,0.0000058534783,0.000019763807,0.0007081932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988055,0.000049800652,0.0003329823,0.00014959727,0.00025976557,0.0004023086],"domain_scores_gemma":[0.996424,0.00055132323,0.00026808924,0.00015819933,0.0021221577,0.0004762171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041815988,0.00012841071,0.00025552264,0.00008657621,0.0009759835,0.00022842716,0.00034422326,0.00010451309,0.00008520194],"category_scores_gemma":[0.00092684256,0.00011064677,0.00013157929,0.00029055966,0.00035269922,0.000017357484,0.000019813515,0.00028842845,0.000007096222],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016147026,0.00008539018,0.004792496,0.000059218975,0.00070617074,0.010411218,0.22092402,0.00021391519,0.00006110201,0.3849705,0.36592975,0.011684756],"study_design_scores_gemma":[0.00069366937,0.000044432363,0.0016414892,0.00003542005,0.00019320902,0.00018735707,0.21993805,0.00006890605,0.00008719376,0.0045803427,0.77231055,0.00021938523],"about_ca_topic_score_codex":0.007919341,"about_ca_topic_score_gemma":0.10687901,"teacher_disagreement_score":0.7212057,"about_ca_system_score_codex":0.00026561585,"about_ca_system_score_gemma":0.0033906128,"threshold_uncertainty_score":0.998687},"labels":[],"label_agreement":null},{"id":"W326428004","doi":"10.55016/ojs/jet.v26i1.52246","title":"The Decima Research English Curriculum","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Curriculum; Psychology; Pedagogy; Mathematics education; Sociology","score_opus":0.06980221479026665,"score_gpt":0.4835671468002403,"score_spread":0.41376493200997366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W326428004","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4371149,0.0012202705,0.000013697526,0.04848006,0.009401107,0.00016304573,9.245521e-7,0.000006825071,0.50359917],"genre_scores_gemma":[0.9409888,0.0005960361,0.0017126923,0.00012157198,0.030275825,0.0000059138474,5.839623e-7,0.0000076208767,0.02629098],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978173,0.0003679976,0.00026220502,0.00007627495,0.0011972284,0.0002790249],"domain_scores_gemma":[0.9948036,0.0016572595,0.00018119231,0.00010487304,0.0031315708,0.00012150129],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0045656213,0.000049875325,0.00007930971,0.000096730175,0.0016216263,0.0002595824,0.0006294063,0.000042817603,0.00089149777],"category_scores_gemma":[0.002580715,0.000032000808,0.000077712684,0.00057176786,0.0006423776,0.00029274344,0.00004392383,0.0002707116,0.00013271176],"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":[0.000015142769,0.00015729765,0.04910006,8.4244374e-7,0.000028465385,4.8581734e-7,0.010739954,1.4708526e-7,0.000017715458,0.5394546,0.39905247,0.0014328478],"study_design_scores_gemma":[0.000110215864,0.00006904672,0.038467333,0.000018051549,0.0000066065727,0.0000018875731,0.023305994,9.315417e-7,0.000025452322,0.017640714,0.9203093,0.00004449043],"about_ca_topic_score_codex":0.00007075487,"about_ca_topic_score_gemma":0.00026110365,"teacher_disagreement_score":0.52181387,"about_ca_system_score_codex":0.00016685494,"about_ca_system_score_gemma":0.0011635341,"threshold_uncertainty_score":0.99967813},"labels":[],"label_agreement":null},{"id":"W339483823","doi":"10.12794/metadc271904","title":"The Politics of Grading: a Comparative Study of High School English Teachers' Personal Beliefs, Self-reported Systems, and Actual Practices","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de l’Éducation, Gouvernement de l’Ontario; University of Toronto; Harvard University","keywords":"Grading (engineering); Mathematics education; Psychology; Politics; Medical education; Pedagogy; Political science; Engineering; Medicine","score_opus":0.05246443031952186,"score_gpt":0.38897096461860875,"score_spread":0.3365065342990869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W339483823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96207815,0.00058987126,2.825241e-7,0.00003776168,0.00079003465,0.0015238554,0.0000074894365,0.000048953152,0.03492358],"genre_scores_gemma":[0.9693812,0.00023596683,0.000043338423,0.0000033647138,0.00035967957,0.0000744447,0.00005758559,0.000013172575,0.029831264],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99718964,0.0005053683,0.0006220547,0.0002966759,0.0011060492,0.00028019765],"domain_scores_gemma":[0.995583,0.0010208066,0.002088093,0.0001704108,0.0010102488,0.00012744681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009491199,0.00023224352,0.00054459536,0.00010136964,0.00070208276,0.0002888266,0.00033668106,0.00021034697,0.000095623625],"category_scores_gemma":[0.0007336472,0.00016437598,0.000062524276,0.00021987405,0.00016205676,0.00033849632,0.000035756504,0.00033422044,0.000003499788],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003834896,0.0008322741,0.0664856,0.000081386985,0.0019014628,0.0000013647624,0.91013294,3.2050067e-7,0.000026152431,0.01524511,0.005219295,0.000035724115],"study_design_scores_gemma":[0.00050991535,0.0002649902,0.0827177,0.000050970408,0.0004918715,2.4497422e-7,0.9137813,0.000014751155,0.0000120268605,0.000038335747,0.0019506041,0.00016731479],"about_ca_topic_score_codex":0.033566155,"about_ca_topic_score_gemma":0.009079869,"teacher_disagreement_score":0.024486285,"about_ca_system_score_codex":0.000103957565,"about_ca_system_score_gemma":0.00054716406,"threshold_uncertainty_score":0.9728694},"labels":[],"label_agreement":null},{"id":"W36778657","doi":"10.1557/s43578-022-00764-2","title":"On-line formative assessment item banking and learning support","year":2001,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Formative assessment; Process (computing); Computer science; Curriculum; The Internet; Variation (astronomy); Line (geometry); Psychology; Medical education; Knowledge management; Mathematics education; Pedagogy; World Wide Web; Medicine","score_opus":0.04230765488828795,"score_gpt":0.3899345329517583,"score_spread":0.3476268780634703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W36778657","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37638706,0.0000064058563,0.001398329,0.0010323138,0.000117795375,0.0001131073,2.30494e-7,0.000075114614,0.62086964],"genre_scores_gemma":[0.9767238,0.000140134,0.0007230834,0.00038411064,0.00012521821,0.0000072817456,0.000004638488,0.000005748863,0.021886025],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989638,0.0001107198,0.00013412301,0.0001414989,0.00038885695,0.00026101823],"domain_scores_gemma":[0.99943465,0.0003329228,0.000058579408,0.00005288662,0.000043954715,0.00007700773],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007939747,0.00008341356,0.00011481994,0.00005723048,0.00067871576,0.00014001154,0.00010224084,0.000044747743,0.0030610885],"category_scores_gemma":[0.00006758955,0.00007089322,0.00003050652,0.00016502876,0.00007332544,0.00028903282,0.00005030057,0.00018142523,0.00006136399],"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":[0.000032173153,0.00018146003,0.5250089,0.0000085029415,0.00007167481,0.0000266347,0.060183797,0.00006778664,0.000057695455,0.3678266,0.0052178022,0.041316923],"study_design_scores_gemma":[0.0028594267,0.0014721979,0.30732104,0.000087388275,0.00007225544,0.0000073218234,0.22774376,0.00588107,0.00006434606,0.012790537,0.44066948,0.0010311742],"about_ca_topic_score_codex":0.0001981045,"about_ca_topic_score_gemma":0.00025123797,"teacher_disagreement_score":0.60033673,"about_ca_system_score_codex":0.000070768656,"about_ca_system_score_gemma":0.000055230797,"threshold_uncertainty_score":0.99785024},"labels":[],"label_agreement":null},{"id":"W37481711","doi":"10.1093/rheumatology/kead362","title":"Self-Assessment in the Middle School Science Classroom","year":2014,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; Arthritis Society; Mayo Clinic","keywords":"Mathematics education; Diversity (politics); Psychology; Set (abstract data type); Pedagogy; Self-assessment; Science education; Student achievement; Academic achievement; Computer science; Sociology","score_opus":0.032105416556750185,"score_gpt":0.3473892525693282,"score_spread":0.315283836012578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37481711","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31107572,0.000009489186,0.00023672485,0.003946247,0.0002553025,0.00025178885,1.0985397e-7,0.00006872527,0.6841559],"genre_scores_gemma":[0.99388874,0.000027666754,0.0036698102,0.000954409,0.0002214713,0.000024672428,3.3725144e-7,0.0000035275514,0.0012093665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9979933,0.00021830863,0.00014692964,0.00022592052,0.0010011224,0.0004144341],"domain_scores_gemma":[0.9993733,0.00019599948,0.00004162396,0.00022637259,0.00006511352,0.00009759265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004146416,0.00007662727,0.00008884011,0.00009693829,0.000723711,0.0003747823,0.0009769339,0.00003898699,0.0003973226],"category_scores_gemma":[0.00010252882,0.000050137645,0.00003476208,0.00091549876,0.0002834358,0.0003782357,0.00008012802,0.00016924398,0.00020293449],"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":[0.0000017118344,0.00017343677,0.41288581,0.0000033558897,0.0000039470483,9.661771e-7,0.013827585,0.0000014817291,0.0001022797,0.5691655,0.0020823865,0.001751473],"study_design_scores_gemma":[0.0005646894,0.00007460457,0.7676999,0.00001223219,0.000011002195,3.7327214e-7,0.08819138,0.0008610598,0.000021548845,0.0064698355,0.1358619,0.00023148776],"about_ca_topic_score_codex":0.0009772399,"about_ca_topic_score_gemma":0.002881434,"teacher_disagreement_score":0.6829465,"about_ca_system_score_codex":0.00023639713,"about_ca_system_score_gemma":0.00052292313,"threshold_uncertainty_score":0.55662733},"labels":[],"label_agreement":null},{"id":"W4200080833","doi":"10.35542/osf.io/fmgv8","title":"A Short History of Grading Practices at Dalhousie University (1901-2021)","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Grading (engineering); Grading scale; Value (mathematics); Point (geometry); Psychology; Mathematics education; Statistics; Mathematics; Medicine; Engineering","score_opus":0.08511183768631214,"score_gpt":0.3450227982369392,"score_spread":0.25991096055062707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200080833","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30969098,0.0006709379,0.000059356225,0.0005064263,0.0020938623,0.00023168096,0.00000399546,0.00005636652,0.6866864],"genre_scores_gemma":[0.81801283,0.002036043,0.0012070419,0.000034006778,0.0002786019,0.0000019487863,0.00003155227,0.000011868511,0.17838614],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814856,0.0002948083,0.00019482062,0.00044583713,0.0006675876,0.00024840684],"domain_scores_gemma":[0.9986839,0.00024170222,0.00046178405,0.00031856602,0.00018925758,0.00010477385],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007096037,0.00015914754,0.00033816605,0.00011499474,0.00020094107,0.000049119022,0.00060259324,0.00027333345,0.0035462363],"category_scores_gemma":[0.00016585788,0.00018182209,0.00021428226,0.00015835762,0.0002796711,0.00025313874,0.0012588485,0.00032555987,0.000016982714],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012942342,0.0007445581,0.6416844,0.00038027344,0.0010803707,0.00032697283,0.23703025,0.000033285625,0.0013830995,0.017163467,0.091846794,0.008197123],"study_design_scores_gemma":[0.00025457013,0.000025448431,0.07382685,0.00015250019,0.00039439715,8.227427e-7,0.11134041,0.000057558093,0.000051137846,0.000093428665,0.813177,0.00062591094],"about_ca_topic_score_codex":0.010497558,"about_ca_topic_score_gemma":0.016154576,"teacher_disagreement_score":0.72133017,"about_ca_system_score_codex":0.0020518163,"about_ca_system_score_gemma":0.0012681087,"threshold_uncertainty_score":0.99736464},"labels":[],"label_agreement":null},{"id":"W4200186911","doi":"10.21083/ajote.v10i2.6762","title":"Analysis of Item Writing Flaws in a Communications Skills Test in a Ghanaian University","year":2021,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Multiple choice; Multitude; Quality (philosophy); First language; Mathematics education; Descriptive statistics; Item analysis; Social psychology; Statistics; Linguistics; Psychometrics; Developmental psychology; Mathematics","score_opus":0.025276382341985728,"score_gpt":0.35590290993779317,"score_spread":0.33062652759580746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200186911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97282296,0.0002320448,0.000012687134,0.003706182,0.00005363308,0.000044962653,0.0000013681191,0.0000022371544,0.023123931],"genre_scores_gemma":[0.9978925,0.00018715048,0.0010931764,0.00002078416,0.000042698328,5.0601574e-7,0.0000040143377,0.0000023870682,0.0007567627],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989279,0.000403413,0.00029614507,0.00006809891,0.00020207264,0.00010237685],"domain_scores_gemma":[0.9988256,0.00039985153,0.00032000305,0.0001567583,0.00024610688,0.000051678435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001005265,0.000041640098,0.00018732376,0.0005291498,0.00007537656,0.000023125793,0.00033444917,0.00003511,0.00010049153],"category_scores_gemma":[0.0004932235,0.00004753165,0.0000920325,0.0025509333,0.00008430732,0.00020289008,0.000038156406,0.00016742824,7.9633605e-7],"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":[0.000002256686,0.0008699153,0.953757,0.0000017445326,0.000050558705,0.0000021334822,0.040709168,0.000005569251,0.00012580423,0.0010574573,0.000081258004,0.0033371677],"study_design_scores_gemma":[0.0001189066,0.000010204815,0.7421145,0.000038948256,0.00011315192,4.0205066e-7,0.255466,0.000026929069,0.0000054687002,0.00005550029,0.0020129676,0.000036998455],"about_ca_topic_score_codex":0.0015164663,"about_ca_topic_score_gemma":0.014405768,"teacher_disagreement_score":0.21475686,"about_ca_system_score_codex":0.00033851108,"about_ca_system_score_gemma":0.00084735797,"threshold_uncertainty_score":0.8038757},"labels":[],"label_agreement":null},{"id":"W4200222103","doi":"10.14221/ajte.2021v46n10.1","title":"The Role of Individual Preferences in the Efficacy of Written Corrective Feedback in an English for Academic Purposes Writing Course","year":2021,"lang":"en","type":"article","venue":"˜The œAustralian journal of teacher education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capilano University","funders":"","keywords":"Corrective feedback; Psychology; Mathematics education; Qualitative research; Test (biology); Qualitative property; Control (management); English as a foreign language; Treatment and control groups; Medical education; Computer science; Medicine","score_opus":0.05189781943817671,"score_gpt":0.3935110894213582,"score_spread":0.3416132699831815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200222103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951665,0.0006887704,0.0000013822622,0.002220365,0.0004996332,0.0003576467,0.0000038141332,0.0000024388837,0.0010594692],"genre_scores_gemma":[0.99871844,0.00009472485,0.00009725574,0.000031753883,0.00071790034,0.000020173191,0.0000047966846,0.0000059435174,0.000309017],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99774945,0.0008478369,0.0005529931,0.00010707689,0.00052778993,0.00021483678],"domain_scores_gemma":[0.99785984,0.0008773212,0.0006223967,0.00012566564,0.0004709826,0.00004382645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039678165,0.000088877954,0.00018017426,0.000070670445,0.0001844023,0.00011462838,0.0008321324,0.00008941424,0.000027396603],"category_scores_gemma":[0.00037342793,0.00005411964,0.00008692325,0.0004228251,0.00023290388,0.0003301936,0.000023547398,0.00051582203,3.8929738e-7],"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":[0.000057247045,0.0005967791,0.67298096,0.0000069371913,0.000038992683,3.3790613e-7,0.274497,0.000014170861,0.00020134442,0.0010750402,0.0011295542,0.049401615],"study_design_scores_gemma":[0.00024004029,0.00006301012,0.5284528,0.0000726858,0.000045161596,0.0000014950275,0.4683336,0.0000018010365,0.00013365097,0.0012844686,0.0013310743,0.000040219813],"about_ca_topic_score_codex":0.00019220142,"about_ca_topic_score_gemma":0.0014209311,"teacher_disagreement_score":0.19383661,"about_ca_system_score_codex":0.00006955619,"about_ca_system_score_gemma":0.00088761107,"threshold_uncertainty_score":0.22410186},"labels":[],"label_agreement":null},{"id":"W4205154527","doi":"10.1097/acm.0000000000004507","title":"Written-Based Progress Testing: A Scoping Review","year":2021,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada; Université de Sherbrooke","funders":"","keywords":"Facilitator; Formative assessment; Test (biology); Inclusion (mineral); Consistency (knowledge bases); Thematic analysis; MEDLINE; Data extraction","score_opus":0.14112124408067425,"score_gpt":0.46820543343452536,"score_spread":0.3270841893538511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205154527","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0155075,0.50343704,0.0003286262,0.30883393,0.0016641655,0.0023312224,0.0000015172938,0.00050044176,0.16739558],"genre_scores_gemma":[0.7477843,0.1454131,0.0034474055,0.07659221,0.009358838,0.00042243768,0.00008070895,0.00008210897,0.016818909],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.9980575,0.00021446905,0.00036147516,0.0002641389,0.0007545416,0.00034786676],"domain_scores_gemma":[0.9987917,0.0005051514,0.00014584819,0.00016533068,0.00022552328,0.00016646938],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015808567,0.00011054337,0.00031661187,0.000040234092,0.00024844674,0.000010850296,0.00029721213,0.00011711454,0.0011086435],"category_scores_gemma":[0.003268892,0.00009172235,0.00003269186,0.0008528719,0.0005052378,0.00008497213,0.00004675278,0.00035445404,0.000052736432],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022451855,0.0000881931,0.62062156,0.011473485,0.00010783374,0.00036272878,0.02280844,0.000001444968,0.0016343391,0.023262005,0.24142048,0.07819704],"study_design_scores_gemma":[0.0047828685,0.000348676,0.019030677,0.713478,0.0007793867,0.000026182468,0.021606317,0.00016234058,0.00047811598,0.0031306462,0.23482665,0.0013500758],"about_ca_topic_score_codex":0.00006543074,"about_ca_topic_score_gemma":0.000030082698,"teacher_disagreement_score":0.7322768,"about_ca_system_score_codex":0.00005223002,"about_ca_system_score_gemma":0.000648756,"threshold_uncertainty_score":0.9998045},"labels":[],"label_agreement":null},{"id":"W4205625260","doi":"10.20343/teachlearninqu.10.3","title":"Instructors’ Perspectives of Challenges and Barriers to Providing Effective Feedback","year":2022,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capilano University; University of Calgary","funders":"Social Sciences and Humanities Research Council of Canada; Killam Trusts","keywords":"Context (archaeology); Thematic analysis; Workload; Class (philosophy); Focus group; Medical education; Coronavirus disease 2019 (COVID-19); Process (computing); Psychology; Computer science; Qualitative research; Medicine; Sociology","score_opus":0.031140960563814667,"score_gpt":0.34022756603078774,"score_spread":0.3090866054669731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205625260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98465836,0.0016731285,0.000072096416,0.0060625677,0.0007423395,0.00034269158,6.054491e-7,0.000061349245,0.0063868864],"genre_scores_gemma":[0.99786854,0.00039268524,0.00028193995,0.00008207141,0.0007474587,0.000020501671,2.8303333e-7,0.000023095154,0.0005834123],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99547964,0.002835938,0.00024307254,0.00024797488,0.00080576824,0.00038760845],"domain_scores_gemma":[0.9986375,0.0006163563,0.00030464292,0.000117947435,0.00007812657,0.00024545245],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0062517626,0.00015373265,0.00024813958,0.00019254515,0.0055681225,0.00016254731,0.0005350014,0.00004268315,0.00021299848],"category_scores_gemma":[0.001936366,0.00011242407,0.000102846934,0.00018338846,0.0003623595,0.0002767863,0.00036682998,0.0017543553,0.0000028643758],"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":[0.000073624,0.000031067142,0.020895097,0.000007201536,0.00010509365,0.0000055423607,0.92416084,0.00050890003,0.00056333473,0.010253624,0.00020604672,0.04318962],"study_design_scores_gemma":[0.00036581978,0.00039999443,0.034901783,0.000047320722,0.000037549296,0.000031668027,0.9311816,0.000030608735,0.000014175932,0.0006009058,0.032221597,0.00016694097],"about_ca_topic_score_codex":0.00015474946,"about_ca_topic_score_gemma":0.000024250961,"teacher_disagreement_score":0.043022677,"about_ca_system_score_codex":0.00035960504,"about_ca_system_score_gemma":0.00018734296,"threshold_uncertainty_score":0.99572647},"labels":[],"label_agreement":null},{"id":"W4206800665","doi":"10.5206/cieeci.v50i1.14133","title":"Grading in a Dilemmatic Space : An Exploratory Cross-cultural Analysis of Mathematics and Language Secondary Teachers","year":2021,"lang":"en","type":"article","venue":"Comparative and International Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Negotiation; Mathematics education; Exploratory research; Psychology; Pedagogy; Sociology; Social science; Engineering","score_opus":0.09320390665256642,"score_gpt":0.4722633425067662,"score_spread":0.37905943585419977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206800665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9882831,0.00083082303,0.000045634177,0.00016512114,0.00013780539,0.000060070597,0.0000040321725,0.000005209374,0.010468211],"genre_scores_gemma":[0.997763,0.00007156981,0.0011065685,0.000026935155,0.00004198594,0.000010813074,0.00007133869,0.0000017605654,0.000906045],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9995033,0.000062267005,0.0001382655,0.000112335554,0.00012629699,0.000057520847],"domain_scores_gemma":[0.9995524,0.000066654466,0.00008199595,0.00004643115,0.00021775249,0.0000347346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015468788,0.000050343802,0.00012912287,0.00013268893,0.000074197524,0.00012011249,0.00006518766,0.00002225628,0.00014797304],"category_scores_gemma":[0.00006293132,0.00004899988,0.000024046858,0.00026533817,0.00012046848,0.0005295875,0.000022462778,0.000053683674,0.000001025404],"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":[0.0000028587272,0.0001671962,0.23170848,0.000011314774,0.00012084348,3.5170396e-7,0.74687034,0.000009439375,0.0011572165,0.018314073,0.00009685467,0.0015410278],"study_design_scores_gemma":[0.0001306534,0.000009428059,0.32474768,0.000022641772,0.000048065438,2.3536181e-7,0.67322123,0.0006224752,0.00023545747,0.00038924933,0.00051280204,0.000060085844],"about_ca_topic_score_codex":0.00020236886,"about_ca_topic_score_gemma":0.0021175037,"teacher_disagreement_score":0.0930392,"about_ca_system_score_codex":0.00006147323,"about_ca_system_score_gemma":0.00013644372,"threshold_uncertainty_score":0.1998157},"labels":[],"label_agreement":null},{"id":"W4207047314","doi":"10.1093/oxfordhb/9780199841332.013.28","title":"Classroom Assessment as a Source of Motivational Messages","year":2021,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Summative assessment; Extant taxon; Psychology; Task (project management); Theme (computing); Field (mathematics); Event (particle physics); Formative assessment; Mathematics education; Computer science; Engineering","score_opus":0.030881876982471478,"score_gpt":0.28154660866295145,"score_spread":0.25066473168048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207047314","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059777364,0.000057894584,0.00038291412,0.00011517303,0.0002073476,0.0003216766,0.000029332496,0.00006742135,0.99822044],"genre_scores_gemma":[0.0060011544,0.00045503993,0.0005803905,0.00003970152,0.00017138559,8.568268e-7,0.000050275143,0.000025489122,0.9926757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99807966,0.0000987823,0.00021364793,0.00038354067,0.0009587738,0.00026561605],"domain_scores_gemma":[0.99872214,0.00019876302,0.00036387975,0.00027804685,0.00030828943,0.0001289097],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023516959,0.00024921767,0.00040341457,0.00014464058,0.0004166011,0.00006732993,0.00058317103,0.0003850203,0.00076326256],"category_scores_gemma":[0.000016641905,0.00030411265,0.00027472322,0.000019692843,0.000413253,0.00012092622,0.0003840375,0.00036124748,0.0000013214166],"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":[0.00002423312,0.000028883287,0.00047578992,0.000029057761,0.00026245852,0.000034484725,0.001384381,0.0000040702844,0.000017915061,0.9936202,0.0020465392,0.0020719862],"study_design_scores_gemma":[0.00043330717,0.000040639043,0.00040608837,0.00013788596,0.00017409532,5.5482803e-7,0.0024065312,0.000005267831,0.000021474136,0.0013179849,0.9947711,0.00028504015],"about_ca_topic_score_codex":0.00051677186,"about_ca_topic_score_gemma":0.00017312657,"teacher_disagreement_score":0.9927246,"about_ca_system_score_codex":0.00029583854,"about_ca_system_score_gemma":0.00071361905,"threshold_uncertainty_score":0.9999411},"labels":[],"label_agreement":null},{"id":"W4210351234","doi":"10.1364/etop.2021.f1b.1","title":"Fostering flow and feedback in the classroom: increasing the successful implementation of active learning instruction","year":2021,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; John Abbott College; Vanier College; Dawson College","funders":"","keywords":"Orchestration; Facilitation; Computer science; Active learning (machine learning); Mathematics education; Flow (mathematics); Multimedia; Knowledge management; Psychology; Artificial intelligence","score_opus":0.034210946651620396,"score_gpt":0.36427669572487414,"score_spread":0.33006574907325376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210351234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710264,0.000030254552,0.000069333524,0.0014228682,0.000080702026,0.00014364884,6.413342e-7,0.000009423187,0.027216703],"genre_scores_gemma":[0.9993366,0.00012005514,0.00031311446,0.00005621938,0.000076170225,0.000007087232,0.000003502312,0.0000030720628,0.00008418786],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9988852,0.00048248126,0.0001378602,0.00010792984,0.00025480863,0.00013167996],"domain_scores_gemma":[0.9995336,0.00026686024,0.00007494675,0.000056961704,0.000054181957,0.000013471152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078049675,0.000051131028,0.000073966876,0.00002982638,0.00036674796,0.00012225832,0.00010538334,0.000029414588,0.00017608589],"category_scores_gemma":[0.000066031476,0.000033520046,0.000022558477,0.00031795158,0.00008839265,0.0002898071,0.000118439544,0.00011620474,9.546751e-7],"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":[0.00002347939,0.000022379814,0.551917,0.000008708731,0.000021880542,0.0000016747713,0.07782139,0.000016875896,0.0014928122,0.004015288,0.000026222031,0.36463228],"study_design_scores_gemma":[0.00032077386,0.000013840892,0.49445245,0.000009442892,0.000009946625,0.0000017419379,0.5034981,0.00007578933,0.0005545488,0.00049292395,0.0005299138,0.000040535706],"about_ca_topic_score_codex":0.004751535,"about_ca_topic_score_gemma":0.01454958,"teacher_disagreement_score":0.4256767,"about_ca_system_score_codex":0.00004260267,"about_ca_system_score_gemma":0.000062915904,"threshold_uncertainty_score":0.81190073},"labels":[],"label_agreement":null},{"id":"W4210444891","doi":"10.18357/otessac.2021.1.1.44","title":"Comparison of English Teacher Feedback and Automated Writing Feedback on the Quality of English Language Learners’ Essay Revision","year":2021,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ell; Quality (philosophy); Class (philosophy); Mathematics education; Psychology; English as a foreign language; English language; Strengths and weaknesses; Peer feedback; Computer science; Teaching method; Artificial intelligence; Social psychology","score_opus":0.07025106336337318,"score_gpt":0.4276535230342052,"score_spread":0.357402459670832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210444891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97903365,0.0006938278,0.0000039102665,0.009197756,0.00033215096,0.00042079395,0.000006341391,0.00007365971,0.010237895],"genre_scores_gemma":[0.9975781,0.00074321096,0.00026707983,0.00023626935,0.00010717525,0.000027292066,0.000014127851,0.000007682487,0.0010190604],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9970848,0.0013747031,0.0005432169,0.00029350098,0.00046635387,0.00023741151],"domain_scores_gemma":[0.9961035,0.0013518186,0.0007292323,0.00029095373,0.0014866074,0.000037842812],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0068696616,0.00013012272,0.00037265272,0.000048832604,0.0005489407,0.0002761452,0.000578154,0.00039020347,0.000120952674],"category_scores_gemma":[0.0124689145,0.00010437636,0.00006473619,0.00082888326,0.00040232413,0.00037548496,0.00025224724,0.00076343725,0.000002480107],"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":[0.000010438046,0.00025321316,0.7091421,0.000024393694,0.000047134236,4.221015e-8,0.2248911,0.0000011653007,0.00056417607,0.060004983,0.0009200809,0.0041411733],"study_design_scores_gemma":[0.00046226027,0.000026556296,0.26054206,0.00018777582,0.000029834448,5.263163e-8,0.7339497,0.000060441438,0.0010448201,0.0018506034,0.0017090745,0.00013676466],"about_ca_topic_score_codex":0.00025890282,"about_ca_topic_score_gemma":0.00034381196,"teacher_disagreement_score":0.50905865,"about_ca_system_score_codex":0.00022704985,"about_ca_system_score_gemma":0.00060107943,"threshold_uncertainty_score":0.9958495},"labels":[],"label_agreement":null},{"id":"W4210921245","doi":"10.24124/2018/59229","title":"Analysis of portfolio-based language assessment (PBLA) guidelines for new immigrant language instruction in Canada: An action plan for teachers and administrators","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Division of Graduate Education","keywords":"Summative assessment; Formative assessment; Portfolio; Context (archaeology); Medical education; Computer science; Mathematics education; Medicine; Psychology","score_opus":0.0627993727201416,"score_gpt":0.44013063660281404,"score_spread":0.37733126388267246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210921245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965883,0.000072708455,0.0003524106,0.00014932068,0.0005096841,0.0008735191,0.00014932292,0.000024850558,0.0012798916],"genre_scores_gemma":[0.9861757,0.000037797887,0.0054737744,0.00006943904,0.00037427025,0.00009638268,0.004512864,0.000024018835,0.0032357513],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9983029,0.000058723283,0.00054353155,0.00036546218,0.00046767638,0.00026173025],"domain_scores_gemma":[0.9988965,0.00009940006,0.0004504552,0.00015521944,0.00026565828,0.00013277575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059866183,0.00021134676,0.00048513841,0.00046494542,0.00015184571,0.000060335715,0.00017828267,0.00020732357,0.00017384432],"category_scores_gemma":[0.000121264384,0.00020362143,0.00014612994,0.0005328012,0.000033643766,0.00015470614,0.0000051465663,0.000089193985,8.490158e-8],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017187679,0.00047808568,0.6000203,0.000618915,0.0036322977,0.0000123537075,0.1363705,0.00015394315,0.004716608,0.002281054,0.023093158,0.22690403],"study_design_scores_gemma":[0.0013503691,0.0002127799,0.262141,0.000055430635,0.0012716905,8.930354e-8,0.7298385,0.00201247,0.00065418886,0.000020430587,0.0020603486,0.00038274084],"about_ca_topic_score_codex":0.9477487,"about_ca_topic_score_gemma":0.9991202,"teacher_disagreement_score":0.59346795,"about_ca_system_score_codex":0.0005116628,"about_ca_system_score_gemma":0.0042181807,"threshold_uncertainty_score":0.8303441},"labels":[],"label_agreement":null},{"id":"W4212780504","doi":"10.1080/13611267.2022.2030186","title":"Towards a better understanding of an academic success center in an EMI context","year":2022,"lang":"en","type":"article","venue":"Mentoring & Tutoring Partnership in Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Context (archaeology); Mathematics education; Reading (process); Computer science; Point (geometry); Academic year; Psychology; Pedagogy; Mathematics","score_opus":0.13657375738084648,"score_gpt":0.41073488157990506,"score_spread":0.2741611241990586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212780504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.977561,0.00008403585,0.000030364652,0.00026525598,0.0007796837,0.00026151648,9.045979e-7,0.00009217542,0.020925049],"genre_scores_gemma":[0.99697846,0.00001785575,0.00007943052,0.000044610086,0.00037347767,0.00008070442,0.000010475695,0.000030777574,0.0023841935],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99609905,0.0011337793,0.0004993053,0.00045872922,0.001014855,0.0007942831],"domain_scores_gemma":[0.9992369,0.00016220163,0.00022840135,0.00018633486,0.000027559096,0.0001586373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041050944,0.00019029013,0.0003223921,0.00041329637,0.000608761,0.00012959767,0.0006353581,0.00010509786,0.00024209851],"category_scores_gemma":[0.00012732968,0.00023379002,0.00006512328,0.000761436,0.00011578823,0.0008342281,0.00023851809,0.0011608684,0.0000026779123],"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":[0.00005336449,0.000100627425,0.80882096,0.000017880662,0.000009644561,0.000017724684,0.18106198,0.0013850651,0.0004899844,0.0066317394,0.0000060852703,0.0014049523],"study_design_scores_gemma":[0.0043660374,0.00066751684,0.3244753,0.00052423833,0.000039737308,0.0000027592346,0.592907,0.0013487411,0.00068556675,0.0014430833,0.072351664,0.0011883584],"about_ca_topic_score_codex":0.001813905,"about_ca_topic_score_gemma":0.0010886729,"teacher_disagreement_score":0.48434567,"about_ca_system_score_codex":0.0018600624,"about_ca_system_score_gemma":0.00014146938,"threshold_uncertainty_score":0.95336807},"labels":[],"label_agreement":null},{"id":"W4213156228","doi":"10.5430/ijhe.v11n3p158","title":"Pedagogical Strategies Used to Enact Formative Assessment in Science Classrooms: Physical Sciences Teachers' Perspectives","year":2022,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Science education; Pedagogy; Mathematics education; Qualitative research; Professional development; Sociology; Psychology; Social science","score_opus":0.0775854320361169,"score_gpt":0.5047785421790595,"score_spread":0.4271931101429426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213156228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95801306,0.00007287407,0.00007573693,0.012264424,0.0023198784,0.00013808599,0.000002027215,0.000009382252,0.027104562],"genre_scores_gemma":[0.9967578,0.000009899934,0.0006628744,0.00016354733,0.00082524,0.0000235576,0.0000011267168,0.000003999279,0.0015519665],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9969144,0.00022273698,0.00027639486,0.0001813588,0.002188662,0.00021648096],"domain_scores_gemma":[0.9989396,0.0001487567,0.00027376862,0.000055791814,0.00048279093,0.00009934343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017108558,0.000085997744,0.00013306273,0.000610174,0.000525353,0.00042269542,0.0010839212,0.000017210668,0.0008298503],"category_scores_gemma":[0.000074616895,0.00007683811,0.000073333256,0.0007711223,0.00040759885,0.0015602118,0.00013925433,0.00032815235,0.0000061687065],"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":[0.000027073012,0.001154017,0.029615719,7.593804e-7,0.00002666259,0.0000038771454,0.7449243,0.0005030272,0.0011743417,0.21914844,0.0009171646,0.002504594],"study_design_scores_gemma":[0.00027445,0.00022315783,0.18200168,0.000016882284,0.0000072147423,0.000003920282,0.78752285,0.000022852286,0.000022740733,0.006341043,0.023459496,0.00010369848],"about_ca_topic_score_codex":0.00027510093,"about_ca_topic_score_gemma":0.0000657132,"teacher_disagreement_score":0.2128074,"about_ca_system_score_codex":0.0018563087,"about_ca_system_score_gemma":0.004004058,"threshold_uncertainty_score":0.9086279},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4214555837","doi":"10.5206/cjsotl-rcacea.2017.1.1","title":"Tools and Questions: An Introduction to Volume 8, Issue 1","year":2017,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sociology; Psychology","score_opus":0.06214295486918278,"score_gpt":0.38785865685816706,"score_spread":0.32571570198898425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214555837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9018853,0.00041693202,0.0001903041,0.09500371,0.00079877814,0.00020776983,0.0000025479499,0.0000095497635,0.0014851253],"genre_scores_gemma":[0.9896286,0.000032786204,0.0005804347,0.00013536753,0.0019708588,0.0000036084928,7.1233575e-7,0.0000072555717,0.0076403725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878323,0.00064479973,0.000106846535,0.00009739778,0.00014988569,0.00021786153],"domain_scores_gemma":[0.9991312,0.0002258553,0.00013576292,0.00015559173,0.00008707762,0.00026451237],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010388295,0.000060070226,0.0000841833,0.000061715604,0.022493135,0.0022757638,0.00042764744,0.000044196062,0.000041496038],"category_scores_gemma":[0.006909173,0.000039991202,0.000030086296,0.000026728398,0.00024131963,0.0007105227,0.000022280192,0.001069861,0.000002493392],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051108585,0.000011484472,0.3152237,0.000012161071,0.00010325262,0.000002485684,0.12680823,0.00040351046,0.00025535253,0.046634678,0.003971954,0.5065221],"study_design_scores_gemma":[0.00015170313,0.00011935633,0.33412114,0.000043688262,0.00005149065,0.000013908249,0.023228109,0.00007804768,0.0000025720606,0.0023363011,0.63975674,0.00009695955],"about_ca_topic_score_codex":0.02854538,"about_ca_topic_score_gemma":0.074333794,"teacher_disagreement_score":0.63578475,"about_ca_system_score_codex":0.000058096783,"about_ca_system_score_gemma":0.00016048684,"threshold_uncertainty_score":0.99876},"labels":[],"label_agreement":null},{"id":"W4214612186","doi":"10.52358/mm.vi9.244","title":"Évaluer des compétences : une articulation cubique","year":2022,"lang":"fr","type":"article","venue":"Médiations et médiatisations","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Valuation (finance); Library science; Philosophy; Computer science; Business","score_opus":0.06017867497735572,"score_gpt":0.35317604974977257,"score_spread":0.29299737477241683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214612186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43448725,0.007954171,0.024462236,0.16800818,0.008517335,0.0025153677,0.00091356336,0.00057097815,0.35257092],"genre_scores_gemma":[0.9339959,0.00080592843,0.010836229,0.0015777631,0.0005407134,0.00061267574,0.0003756016,0.00004107134,0.05121413],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9955818,0.0016707301,0.00061520597,0.00044327544,0.0010859302,0.000603057],"domain_scores_gemma":[0.9980473,0.00081735884,0.00036669,0.00032700493,0.00024640074,0.00019522478],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014892416,0.00026242062,0.00027426626,0.00029609972,0.0053011826,0.00027465474,0.00042175746,0.00011440954,0.012768468],"category_scores_gemma":[0.00020952897,0.0003355802,0.00021385847,0.0031556927,0.0007354997,0.0009855869,0.00021375489,0.0004532411,0.00041657573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062326903,0.00079045835,0.10553376,0.000018273062,0.00013545349,0.0000047510243,0.059806816,0.048104867,0.00005236476,0.7442919,0.029087223,0.012167911],"study_design_scores_gemma":[0.00068345753,0.00013179815,0.46579552,0.000025540046,0.00023984164,0.0000054823636,0.03105159,0.011129297,0.00000713297,0.063715495,0.42667073,0.00054413103],"about_ca_topic_score_codex":0.010392213,"about_ca_topic_score_gemma":0.006679001,"teacher_disagreement_score":0.6805764,"about_ca_system_score_codex":0.00093764585,"about_ca_system_score_gemma":0.0008133829,"threshold_uncertainty_score":0.99990964},"labels":[],"label_agreement":null},{"id":"W4220932421","doi":"10.22158/selt.v10n2p27","title":"Formative Assessment is a Scaffold for ELs to Reach ZPD’s Second Layer: A Literature Review Study","year":2022,"lang":"en","type":"review","venue":"Studies in English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Formative assessment; Zone of proximal development; Mathematics education; Function (biology); Process (computing); Scaffold; Computer science; sort; Psychology; Assessment for learning; Pedagogy","score_opus":0.09516354740164225,"score_gpt":0.4958929418848868,"score_spread":0.40072939448324457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220932421","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014082721,0.9553575,0.000006291781,0.00012480702,0.001756398,0.009361805,0.00033720414,0.0001827313,0.03273245],"genre_scores_gemma":[0.00017779788,0.98566014,0.00086659694,0.0009566246,0.0012677511,0.0057469974,0.00015225993,0.00008759696,0.005084259],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99326646,0.0024538497,0.0012404674,0.0009909406,0.0011401736,0.00090807717],"domain_scores_gemma":[0.99679464,0.0015791687,0.00062749506,0.0006711313,0.00017840049,0.00014917548],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.009168842,0.0007645173,0.0030130437,0.00050324097,0.0013982947,0.00029514031,0.0013183429,0.00019772125,0.0004511322],"category_scores_gemma":[0.0026767142,0.00064415496,0.0007198629,0.0012758712,0.00009070586,0.00049330597,0.0010978176,0.0017268147,0.00000802299],"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":[0.0000035617575,0.00019395154,0.00002372902,0.016401125,0.0005850643,0.00005484849,0.6568386,5.7486023e-8,2.538307e-8,0.00030739713,0.028120844,0.2974708],"study_design_scores_gemma":[0.00028021482,0.00015967617,0.0000024974345,0.023760075,0.00047308079,0.000001075074,0.3474576,1.7494747e-7,1.8064299e-8,0.0000137876905,0.6274139,0.00043786358],"about_ca_topic_score_codex":0.0002004244,"about_ca_topic_score_gemma":0.0016208615,"teacher_disagreement_score":0.5992931,"about_ca_system_score_codex":0.0017328907,"about_ca_system_score_gemma":0.00031553154,"threshold_uncertainty_score":0.9999018},"labels":[],"label_agreement":null},{"id":"W4221071532","doi":"10.51357/jei.v3i1.182","title":"Examining Online Course Evaluations and the Quality of Student Feedback","year":2022,"lang":"en","type":"article","venue":"Journal of Educational Informatics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Constructive; Quality (philosophy); Online course; Usability; Coronavirus disease 2019 (COVID-19); Data collection; Computer science; Psychology; Medical education; Mathematics education; Medicine; Sociology","score_opus":0.1478109579851624,"score_gpt":0.49933037932117824,"score_spread":0.3515194213360159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221071532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805751,0.00027967966,0.000031302177,0.011027624,0.0005830989,0.00015572856,0.00001251607,0.0000014164978,0.007333571],"genre_scores_gemma":[0.9970619,0.00010265325,0.0016572834,0.00030580853,0.0002436038,0.000006168891,0.0000068979975,0.0000023122195,0.00061335735],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9976494,0.00029438635,0.0007763832,0.000023966451,0.001167923,0.000087988854],"domain_scores_gemma":[0.9970185,0.0013559178,0.0010692147,0.00007382853,0.0004326003,0.000049907936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047629625,0.00004803349,0.00015977747,0.00006718065,0.00050489453,0.000047886646,0.00030239447,0.000014733709,0.000625535],"category_scores_gemma":[0.00042499046,0.00003498817,0.00005662232,0.00020855955,0.00027264073,0.000268519,0.00008550923,0.00018231783,0.0000014617184],"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":[0.00009863913,0.0013848154,0.3291992,0.000035052588,0.00025714596,1.224169e-7,0.4365051,0.0015001383,0.000010855479,0.21896653,0.009890553,0.002151847],"study_design_scores_gemma":[0.00096412306,0.00006074012,0.5797577,0.000009526723,0.000064456246,0.0000034423563,0.4134924,0.0001061312,4.6822294e-7,0.002789756,0.002704034,0.00004718395],"about_ca_topic_score_codex":0.00004491138,"about_ca_topic_score_gemma":0.000037895385,"teacher_disagreement_score":0.2505585,"about_ca_system_score_codex":0.00010324191,"about_ca_system_score_gemma":0.0009312652,"threshold_uncertainty_score":0.6849169},"labels":[],"label_agreement":null},{"id":"W4226190183","doi":"10.1504/ijlc.2022.119506","title":"Education quality comparing between official measurement scale and inter-counterparts' perception: a new horizon for learning assessment","year":2021,"lang":"en","type":"article","venue":"International Journal of Learning and Change","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Horizon; Scale (ratio); Perception; Quality (philosophy); Psychology; Item response theory; Mathematics education; Computer science; Psychometrics; Geography; Mathematics; Cartography","score_opus":0.14183940712578774,"score_gpt":0.44760455393451576,"score_spread":0.305765146808728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226190183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9810965,0.0005336743,0.009444161,0.0051732077,0.0012739619,0.00012214016,0.0000012426461,0.00001639628,0.0023386905],"genre_scores_gemma":[0.99383515,0.0004171148,0.0012621846,0.00005174645,0.0036166518,0.000005593194,0.000009916591,0.000007224003,0.0007944239],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99852276,0.0002187196,0.00030396,0.00013619997,0.0006883036,0.00013003196],"domain_scores_gemma":[0.9986474,0.0001107801,0.0003150207,0.000025840034,0.00079086324,0.00011010941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014609765,0.00008291752,0.0001919404,0.00009516808,0.00027484365,0.0002809701,0.00011603908,0.00005119305,0.000071658586],"category_scores_gemma":[0.00020316847,0.00008459386,0.00007364778,0.000058324906,0.000047436944,0.0002772204,0.000058319634,0.00025936755,0.0000011533239],"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":[0.000060938233,0.000082929124,0.76306665,0.000014498041,0.00011438032,0.0000016516619,0.021591324,0.000004189563,0.00038054466,0.00043681826,0.00027637958,0.21396972],"study_design_scores_gemma":[0.0014984779,0.00043863102,0.728616,0.00052043475,0.00011670969,0.000015747852,0.092250414,0.00019509615,0.000042255542,0.0004451322,0.17561528,0.00024582172],"about_ca_topic_score_codex":0.00039842704,"about_ca_topic_score_gemma":0.0005508434,"teacher_disagreement_score":0.2137239,"about_ca_system_score_codex":0.00023880773,"about_ca_system_score_gemma":0.00034281687,"threshold_uncertainty_score":0.3449638},"labels":[],"label_agreement":null},{"id":"W4226402501","doi":"10.32038/ltrq.2021.25.02","title":"Teachers’ Beliefs and Practice about Written Corrective Feedback: A Case Study in a French as a Foreign Language Program","year":2021,"lang":"en","type":"article","venue":"Language Teaching Research Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Corrective feedback; Situated; Foreign language; English as a foreign language; Psychology; Class (philosophy); Pedagogy; Peer feedback; Second language writing; Mathematics education; Medical education; Second language; Computer science; Medicine; Linguistics","score_opus":0.04800438437751356,"score_gpt":0.4747548318168341,"score_spread":0.42675044743932056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226402501","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9039741,0.0012139061,0.00001337262,0.00078520837,0.00008720861,0.00182742,0.0000055780183,0.00018148255,0.09191171],"genre_scores_gemma":[0.9919407,0.000019874813,0.001448652,0.00010700602,0.00039831473,0.00036995675,0.000013650887,0.000036481273,0.005665414],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98971343,0.0064536897,0.00036071215,0.00077407964,0.0015227527,0.0011753318],"domain_scores_gemma":[0.9961674,0.00267433,0.000105434,0.00047625587,0.00026036278,0.00031619327],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.011556851,0.00024393936,0.00035985728,0.0003757142,0.0012428164,0.0010390583,0.0004107325,0.0001688303,0.00019032764],"category_scores_gemma":[0.0041345595,0.00023877791,0.00007583916,0.000996169,0.0003255133,0.00078143325,0.00018464393,0.0018889243,0.000061492814],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035893423,0.0016192133,0.03130455,0.000012997881,0.00007401268,0.024380052,0.7794793,1.1201889e-7,0.00019039326,0.00062782556,0.00031332727,0.16196229],"study_design_scores_gemma":[0.0014743094,0.0015226923,0.024399651,0.000086553286,0.00003199475,0.0005565785,0.9705389,0.000027383914,0.000004462276,0.00015913718,0.00093073986,0.0002675979],"about_ca_topic_score_codex":0.20690426,"about_ca_topic_score_gemma":0.14226301,"teacher_disagreement_score":0.19105956,"about_ca_system_score_codex":0.0003677238,"about_ca_system_score_gemma":0.0005001955,"threshold_uncertainty_score":0.999998},"labels":[],"label_agreement":null},{"id":"W4230383360","doi":"10.5465/amle.9.4.zqr652","title":"Improving the Effectiveness of Students in Groups With a Centralized Peer Evaluation System","year":2010,"lang":"en","type":"article","venue":"Academy of Management Learning and Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Peer feedback; Peer evaluation; Peer assessment; Peer group; Computer science; Qualitative research; Psychology; Peer effects; Higher education; Mathematics education; Medical education; Multimedia; Knowledge management; Social psychology; Sociology","score_opus":0.015076458740300377,"score_gpt":0.3634936882704143,"score_spread":0.3484172295301139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230383360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99227315,0.00005815582,0.000034686534,0.00030493675,0.00015218995,0.00071421807,8.211596e-8,0.000011529853,0.0064510577],"genre_scores_gemma":[0.9992816,0.00003915497,0.00012913169,0.0000071467903,0.00004565331,0.00007291554,0.0000026753905,0.0000042133456,0.00041750216],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984219,0.0005412372,0.00013799177,0.0001281812,0.0006556617,0.00011504973],"domain_scores_gemma":[0.9995463,0.0001681787,0.00015921924,0.000039348557,0.00006596109,0.00002102005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063707195,0.000055316214,0.00009554633,0.000084625484,0.00015031033,0.000035732446,0.0001503371,0.00004649127,0.000011243667],"category_scores_gemma":[0.00009849131,0.00004114657,0.000014937825,0.00021392686,0.00008255113,0.00012119744,0.00003726776,0.00017556247,8.966092e-7],"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":[0.00008204437,0.00010875992,0.94526976,0.00026877964,0.000041178442,4.6323454e-8,0.0079090465,0.00004208068,0.00051409757,0.025453938,0.000025963773,0.02028433],"study_design_scores_gemma":[0.0005921937,0.000022538894,0.95505685,0.00016344107,0.00007862079,1.1728161e-7,0.042833354,0.00013924959,0.00006477841,0.00012700388,0.0008689617,0.000052881347],"about_ca_topic_score_codex":0.00048168033,"about_ca_topic_score_gemma":0.00003591938,"teacher_disagreement_score":0.034924306,"about_ca_system_score_codex":0.000049396007,"about_ca_system_score_gemma":0.000036710022,"threshold_uncertainty_score":0.2207977},"labels":[],"label_agreement":null},{"id":"W4233654530","doi":"10.33137/incite.1.28913","title":"This Is a Test","year":2018,"lang":"en","type":"article","venue":"in cite journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Poetry; Word (group theory); Linguistics; History; Computer science; Psychology; Literature; Art; Philosophy; Biology; Ecology","score_opus":0.041965805483094615,"score_gpt":0.39616559617924996,"score_spread":0.35419979069615537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233654530","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35827333,0.000098740435,0.000023490868,0.0069467463,0.0009787101,0.0000591771,9.73299e-7,0.000017275235,0.63360155],"genre_scores_gemma":[0.9776101,0.00020755967,0.00041401762,0.0008669169,0.0024089029,9.20285e-7,8.25614e-8,0.000004468143,0.018487025],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991889,0.00004736955,0.00013211997,0.000068399386,0.00034265753,0.00022053799],"domain_scores_gemma":[0.99962825,0.000101012556,0.000060191327,0.00004998369,0.00008462301,0.0000759153],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00071258796,0.000043754106,0.000066681365,0.00008064387,0.00035452668,0.00017705052,0.0002169326,0.000046451914,0.008531361],"category_scores_gemma":[0.00014837853,0.000038064227,0.00003789389,0.00025969496,0.0001400643,0.00020619344,0.000022640372,0.00016777386,0.0005933723],"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":[0.0000058124065,0.00006280568,0.82461035,6.456278e-7,0.0000073857354,0.000018466482,0.041108318,2.6607422e-8,0.00018096183,0.00075231417,0.12738384,0.005869072],"study_design_scores_gemma":[0.0004996966,0.000111870155,0.18423098,0.000044952343,0.000007452375,0.00001044923,0.004496299,0.000023137878,0.000062967905,0.0035519237,0.8068248,0.00013546803],"about_ca_topic_score_codex":0.00022551439,"about_ca_topic_score_gemma":0.00062707433,"teacher_disagreement_score":0.679441,"about_ca_system_score_codex":0.00008284281,"about_ca_system_score_gemma":0.00010341195,"threshold_uncertainty_score":0.99237496},"labels":[],"label_agreement":null},{"id":"W4239004152","doi":"10.37514/atd-b.2016.0933.3.2","title":"Epilogue","year":2016,"lang":"en","type":"book-chapter","venue":"The WAC Clearinghouse; University Press of Colorado eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Philosophy","score_opus":0.040058663557430124,"score_gpt":0.2596215988172264,"score_spread":0.21956293525979628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239004152","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014752363,0.000054015018,0.0000192423,0.0005011077,0.00031907897,0.0005583752,0.00004046052,0.00016684862,0.99686563],"genre_scores_gemma":[0.12063923,0.00028179042,0.000031323274,0.000034295124,0.0002443639,5.857821e-7,0.0000017838954,0.00004081774,0.8787258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983121,0.00012823196,0.00021576897,0.00032295345,0.00065836956,0.00036257715],"domain_scores_gemma":[0.99842316,0.0003563732,0.0004075192,0.00051662436,0.00017446965,0.00012187718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004965765,0.0002617306,0.00042290564,0.00012205313,0.00070745894,0.000051649222,0.0015298635,0.0003828643,0.00025604898],"category_scores_gemma":[0.000020964351,0.00021556366,0.00026850094,0.000019585921,0.001420028,0.0001083588,0.00063064514,0.000370906,0.000078574485],"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":[0.0001613595,0.000014643055,0.000073235926,0.000016834854,0.00019465764,0.000018202942,0.0033193808,9.934985e-7,0.000026830294,0.98882973,0.004010454,0.0033336955],"study_design_scores_gemma":[0.0004821811,0.0000785952,0.000267518,0.00014043498,0.00021330445,4.6346327e-7,0.00094463205,0.0000010047636,0.000028293804,0.005135083,0.99240595,0.00030254538],"about_ca_topic_score_codex":0.00074279396,"about_ca_topic_score_gemma":0.0006188462,"teacher_disagreement_score":0.9883955,"about_ca_system_score_codex":0.00021475494,"about_ca_system_score_gemma":0.00021447794,"threshold_uncertainty_score":0.8790431},"labels":[],"label_agreement":null},{"id":"W4239409743","doi":"10.4018/9781591407324.ch020","title":"Effects of Anonymity and Accountability During Online Peer Assessment","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Anonymity; Accountability; Internet privacy; Computer science; Psychology; Computer security; Political science; Law","score_opus":0.025561739298318783,"score_gpt":0.33107803161382754,"score_spread":0.30551629231550875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239409743","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123695225,0.00018916564,0.000008420643,0.000041970074,0.00044534242,0.0006744109,0.00008634895,0.000067094494,0.87479204],"genre_scores_gemma":[0.9205778,0.00005545239,0.00036657846,0.0000515597,0.00036355073,0.000011278989,0.0000046786586,0.00002286875,0.07854622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9977971,0.000066189576,0.00036596842,0.0004566624,0.0009711313,0.0003429909],"domain_scores_gemma":[0.99886256,0.00011651715,0.00030592096,0.00027953656,0.00026944588,0.00016600997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042588188,0.00032744568,0.0005440776,0.00004694437,0.00024314,0.000067072,0.00035901554,0.00041638478,0.00014585545],"category_scores_gemma":[0.00004779229,0.00032196296,0.0001798058,0.000020914405,0.00049607374,0.00008790215,0.00027829627,0.00028403237,0.000011682051],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054374694,0.000097613396,0.017126178,0.00024914448,0.00017413568,0.000021936174,0.0014356573,3.348422e-8,0.00007598235,0.9783034,0.0002688802,0.0021926963],"study_design_scores_gemma":[0.002285478,0.00026917233,0.5995153,0.00064458157,0.0007088293,0.0000044657,0.0008740143,0.0000011899873,0.00016860783,0.36824134,0.025941899,0.0013451161],"about_ca_topic_score_codex":0.0019095269,"about_ca_topic_score_gemma":0.0026041865,"teacher_disagreement_score":0.79688257,"about_ca_system_score_codex":0.00036846206,"about_ca_system_score_gemma":0.00031972173,"threshold_uncertainty_score":0.9999232},"labels":[],"label_agreement":null},{"id":"W4239550360","doi":"10.37514/atd-b.2016.0933.1.3","title":"Introduction","year":2016,"lang":"en","type":"book-chapter","venue":"The WAC Clearinghouse; University Press of Colorado eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Geology","score_opus":0.026302958385079643,"score_gpt":0.2468246126396398,"score_spread":0.22052165425456016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239550360","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013395209,0.000036752834,0.000020836449,0.0015216082,0.0005235956,0.0004746624,0.000017071436,0.00015411877,0.99591184],"genre_scores_gemma":[0.052461214,0.0002466597,0.000029102983,0.000019204479,0.0010021608,4.94494e-7,0.0000017585606,0.000034202007,0.9462052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985391,0.00010736366,0.00018398151,0.00031213913,0.00057907257,0.00027836466],"domain_scores_gemma":[0.9987436,0.00017031054,0.00036357745,0.00045779295,0.00017994813,0.000084793304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045817927,0.00021158748,0.0003269332,0.0001160439,0.00063059333,0.000047787096,0.0010040842,0.0003055005,0.0003646254],"category_scores_gemma":[0.000020422764,0.00017677492,0.00019994393,0.000019520683,0.0010847481,0.000122081,0.00041008482,0.00032081216,0.000068601956],"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":[0.00017570572,0.000012433986,0.00002800729,0.000014694076,0.00016064088,0.000006304548,0.0027988788,0.0000016096436,0.000052084746,0.97958505,0.01284972,0.0043148478],"study_design_scores_gemma":[0.00033154554,0.00006118385,0.00014719839,0.000060026283,0.00018178004,4.581293e-7,0.0008498076,8.8005623e-7,0.000042056254,0.002739966,0.99536425,0.00022087691],"about_ca_topic_score_codex":0.00042215097,"about_ca_topic_score_gemma":0.00031126448,"teacher_disagreement_score":0.9825145,"about_ca_system_score_codex":0.00023255702,"about_ca_system_score_gemma":0.00015069098,"threshold_uncertainty_score":0.72086716},"labels":[],"label_agreement":null},{"id":"W4239565827","doi":"10.24124/2013/bpgub1571","title":"Inquiry for deep learning for all learners","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia; University of British Columbia","funders":"","keywords":"Formative assessment; Pedagogy; Resource (disambiguation); The arts; Point (geometry); Mathematics education; Reflection (computer programming); Language arts; English language; Psychology; Computer science; Visual arts; Art","score_opus":0.06086780292602795,"score_gpt":0.4159079277008984,"score_spread":0.35504012477487046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239565827","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17110264,0.0007052209,0.0054373476,0.0010603105,0.009832687,0.00725988,0.0000039609595,0.0005582751,0.80403966],"genre_scores_gemma":[0.098496854,0.0003766908,0.0035974593,0.00020497564,0.0019756882,0.0011713483,0.0016978261,0.000069074995,0.8924101],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99874485,0.000046161153,0.00020328486,0.00029169672,0.0003065622,0.00040744393],"domain_scores_gemma":[0.9991127,0.00034488767,0.00017305299,0.00007717174,0.00020953293,0.00008264799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044257662,0.00016767666,0.00023209571,0.000086759894,0.0005256786,0.00021314895,0.00028707052,0.0003438626,0.00086752226],"category_scores_gemma":[0.0002702044,0.00016066758,0.00021005336,0.000084713574,0.0000477404,0.0001741705,0.000010412888,0.0001555753,0.00010692314],"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":[0.00033095956,0.0001854825,0.00468045,0.0005165094,0.0006794336,6.507194e-7,0.48837,0.000053444335,0.00055512454,0.16149175,0.20114404,0.14199215],"study_design_scores_gemma":[0.00052554527,0.00011733173,0.001317307,0.000026101961,0.000115987415,1.7657088e-8,0.40225607,0.00022761589,0.00003841194,0.0015148736,0.59347737,0.0003833594],"about_ca_topic_score_codex":0.00061309244,"about_ca_topic_score_gemma":0.0041436963,"teacher_disagreement_score":0.39233333,"about_ca_system_score_codex":0.00007852279,"about_ca_system_score_gemma":0.00011776402,"threshold_uncertainty_score":0.94987607},"labels":[],"label_agreement":null},{"id":"W4239768617","doi":"10.1007/978-94-6209-028-6_2","title":"Breakthrough","year":2012,"lang":"en","type":"book-chapter","venue":"SensePublishers eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Work (physics); Political science; Literacy; Public administration; Library science; Sociology; Media studies; Engineering; Law","score_opus":0.043099086111957674,"score_gpt":0.3064134650660748,"score_spread":0.26331437895411713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239768617","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003624692,0.0004941651,0.00000580122,0.00063711574,0.0025024677,0.00047047206,0.000013767883,0.00032225854,0.99551773],"genre_scores_gemma":[0.0044926307,0.00009068697,0.000210352,0.00061839726,0.0033901213,0.000008903272,0.000038049628,0.00010113544,0.9910497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973003,0.000064000895,0.00034775783,0.00044236312,0.001097508,0.00074805523],"domain_scores_gemma":[0.9985776,0.0001335585,0.00027678415,0.00045644864,0.00021132619,0.00034431263],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006978041,0.0004076578,0.00043965125,0.00018070819,0.00056814303,0.00061604497,0.00055513263,0.0007930357,0.0060296557],"category_scores_gemma":[0.00003975909,0.00042549075,0.00032746114,0.000026781054,0.0006859196,0.0004139383,0.0001540847,0.0005965031,0.0009740131],"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":[0.000009624443,0.000011213083,0.0000832341,0.000011438525,0.00014730527,0.000018156263,0.009687356,2.7016092e-8,0.0000043229634,0.7181644,0.23901251,0.032850433],"study_design_scores_gemma":[0.00020003611,0.00001798551,0.000048314567,0.000045214227,0.00011042484,0.0000020503244,0.0010631109,1.2929905e-7,0.0000022507368,0.017871656,0.98013616,0.00050268887],"about_ca_topic_score_codex":0.0005931429,"about_ca_topic_score_gemma":0.0008572486,"teacher_disagreement_score":0.7411236,"about_ca_system_score_codex":0.00028789957,"about_ca_system_score_gemma":0.00038385205,"threshold_uncertainty_score":0.9998197},"labels":[],"label_agreement":null},{"id":"W4241845040","doi":"10.1007/978-3-030-71363-8_26","title":"Giving Feedback on Others’ Writing","year":2021,"lang":"en","type":"book-chapter","venue":"Innovation and change in professional education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Conversation; Transformative learning; Rewriting; Action (physics); Computer science; Psychology; Human–computer interaction; Communication; Pedagogy","score_opus":0.09681976494152646,"score_gpt":0.41650593143806286,"score_spread":0.3196861664965364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241845040","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059528586,0.000655824,0.0000021310905,0.01337291,0.0060071605,0.000768509,0.0000088875195,0.00004843718,0.9196076],"genre_scores_gemma":[0.16971985,0.00038809585,0.00010766836,0.0035336001,0.0022602775,0.00011782769,0.00020657977,0.000030213403,0.8236359],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986367,0.00005856661,0.00035063399,0.0003029916,0.00047512056,0.0001759557],"domain_scores_gemma":[0.99912536,0.00011938097,0.00027531353,0.00010569461,0.000336909,0.000037348367],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006104015,0.00016627107,0.00017453388,0.00042779386,0.00031021886,0.00008880865,0.00010546052,0.00031705297,0.0018996976],"category_scores_gemma":[0.00008481427,0.00017578306,0.000027787093,0.00027557154,0.000079472,0.00020781868,0.000048810136,0.00038459033,0.000038363632],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009469587,0.000091954826,0.0040304344,0.00004635101,0.000009412249,0.0000012016415,0.017552346,3.291248e-8,0.000023971994,0.8955706,0.0044524567,0.078211784],"study_design_scores_gemma":[0.00047616716,0.000044304878,0.06587444,0.0047681956,0.000017363025,0.0000013019746,0.03679206,0.000007918615,0.000011621623,0.036337852,0.8550144,0.00065436325],"about_ca_topic_score_codex":0.0001762259,"about_ca_topic_score_gemma":0.00038117162,"teacher_disagreement_score":0.8592327,"about_ca_system_score_codex":0.00023416444,"about_ca_system_score_gemma":0.0006350288,"threshold_uncertainty_score":0.9990127},"labels":[],"label_agreement":null},{"id":"W4244193584","doi":"10.1037/e642622013-015","title":"What's in a quarter: Adjusting and re-engaging with course aspirations after mid-quarter feedback","year":2013,"lang":"en","type":"dataset","venue":"PsycEXTRA Dataset","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Course (navigation); Short course; History; Engineering; Medicine; Pediatrics","score_opus":0.0382086263038963,"score_gpt":0.34316675102373695,"score_spread":0.30495812471984063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244193584","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018104936,0.0009109306,0.000007706689,0.00257713,0.00080906635,0.00097397005,0.9926264,0.000042842596,0.00024141523],"genre_scores_gemma":[0.0031630122,0.0011671493,0.00025238283,0.0008507335,0.00065662747,0.0003404144,0.9934525,0.000028830726,0.00008837369],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964591,0.00042842096,0.00056045334,0.0008857654,0.00083607266,0.0008301909],"domain_scores_gemma":[0.99814945,0.0003084443,0.00031384482,0.0008641808,0.00008244184,0.0002816345],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010215484,0.00050734694,0.0005330992,0.00026880944,0.00053800904,0.001915143,0.00072944857,0.000360065,0.0021435223],"category_scores_gemma":[0.000054398522,0.00046134344,0.00006107141,0.00047602042,0.00044446005,0.0025277915,0.00015533842,0.0008636228,0.00052825414],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040160056,0.00019354612,0.0017250788,0.00008520934,0.00006633524,0.000082455066,0.0024436188,7.4080043e-7,0.0000011775908,0.000011387161,0.99478376,0.0005665322],"study_design_scores_gemma":[0.0009215655,0.00011131257,0.0059900023,0.0005556189,0.00023457278,0.000005893959,0.028466007,0.000009252943,3.127256e-7,0.000037754136,0.9629983,0.0006694615],"about_ca_topic_score_codex":0.004309411,"about_ca_topic_score_gemma":0.061017625,"teacher_disagreement_score":0.056708213,"about_ca_system_score_codex":0.000097144744,"about_ca_system_score_gemma":0.00023019093,"threshold_uncertainty_score":0.9997838},"labels":[],"label_agreement":null},{"id":"W4244696859","doi":"10.24124/2015/bpgub1662","title":"Formative assessment strategies used in the University of Northern British Columbia School of Education","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Northern British Columbia","keywords":"Formative assessment; Medical education; Knowledge survey; Psychology; Qualitative research; Phenomenology (philosophy); Pedagogy; Mathematics education; Summative assessment; Sociology; Medicine","score_opus":0.01935480869583143,"score_gpt":0.3475716144568128,"score_spread":0.32821680576098133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244696859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65879416,0.000034753823,0.0000053082567,0.000023262537,0.00017216007,0.00034558633,0.000007666723,0.0000064220053,0.34061068],"genre_scores_gemma":[0.98025465,0.000102846265,0.0001229789,0.000006178678,0.0000326719,0.0000039307247,0.00022102374,0.000004294464,0.019251449],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.998789,0.0002054499,0.00019239068,0.00010770681,0.00059469405,0.00011072928],"domain_scores_gemma":[0.9990532,0.000063526226,0.0003069506,0.000099335426,0.00044367535,0.0000333432],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006163317,0.00006189124,0.00019434847,0.000043566863,0.00015033442,0.00016936284,0.0003929729,0.00012580596,0.00092100573],"category_scores_gemma":[0.000027135653,0.00007925891,0.000060134887,0.000285602,0.00009118136,0.0003725118,0.000012093767,0.00014228869,0.00000641577],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025617117,0.00072668324,0.62895423,0.00015804556,0.000089009314,0.0000017880942,0.32693097,0.000005182491,0.000030993066,0.0026037036,0.03302385,0.007449905],"study_design_scores_gemma":[0.0001353638,0.000023228848,0.42493254,0.00006168462,0.000019833638,3.0158617e-8,0.57268536,0.0000014436266,4.3711884e-7,0.0013272957,0.00076061575,0.000052178828],"about_ca_topic_score_codex":0.39858586,"about_ca_topic_score_gemma":0.977179,"teacher_disagreement_score":0.57859313,"about_ca_system_score_codex":0.00019159875,"about_ca_system_score_gemma":0.003733985,"threshold_uncertainty_score":0.9999923},"labels":[],"label_agreement":null},{"id":"W4245142731","doi":"10.24124/2013/bpgub918","title":"Implementing rubrics as formative assessment in English writing classes in Japan.","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Heritage; Library and Archives Canada","funders":"Vancouver Island University; University of Northern British Columbia","keywords":"Rubric; Formative assessment; Action research; Interpersonal communication; Psychology; Pedagogy; Mathematics education; Social psychology","score_opus":0.02393801657956783,"score_gpt":0.39175912016037673,"score_spread":0.3678211035808089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245142731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5138777,0.000044763157,0.0000039765864,0.000067924215,0.00055759813,0.00062228495,0.0000021885733,0.00006364972,0.4847599],"genre_scores_gemma":[0.9744394,0.0004370362,0.0008471842,0.00010107246,0.00041721834,0.00028228972,0.00045800637,0.000034734785,0.022983104],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99635524,0.00025540427,0.000916449,0.00042709222,0.0010011981,0.0010446092],"domain_scores_gemma":[0.9984879,0.00046567587,0.00045513,0.0001525807,0.0003408593,0.00009789326],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020685955,0.00032256768,0.0004848019,0.00051248696,0.00043169394,0.000577804,0.0004927509,0.0003652301,0.0022295555],"category_scores_gemma":[0.0003072978,0.00033950058,0.00011874511,0.0008087204,0.00004473313,0.0010572232,0.00010427615,0.00076111226,0.00007367203],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014933647,0.00029614934,0.4938941,0.00017458544,0.000068981404,0.000009984944,0.3527775,0.0000031912007,0.0000972174,0.13236701,0.0032637941,0.017032534],"study_design_scores_gemma":[0.000515677,0.000034272292,0.23040165,0.00022843799,0.000017744875,5.6004662e-8,0.7596368,0.00006220338,0.00003312857,0.0010445409,0.0076243365,0.00040116464],"about_ca_topic_score_codex":0.016116519,"about_ca_topic_score_gemma":0.1341232,"teacher_disagreement_score":0.4617768,"about_ca_system_score_codex":0.00066884444,"about_ca_system_score_gemma":0.00070529606,"threshold_uncertainty_score":0.9999057},"labels":[],"label_agreement":null},{"id":"W4246205618","doi":"10.1787/epa-2006-5-en","title":"Improving Learning through Formative Assessment","year":2007,"lang":"en","type":"book-chapter","venue":"Education policy analysis","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; German; Equity (law); Quality (philosophy); Medical education; Pedagogy; Political science; Mathematics education; Psychology; Geography; Medicine","score_opus":0.046278301571159114,"score_gpt":0.43819529058630224,"score_spread":0.39191698901514316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246205618","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008405938,0.00019659924,0.0051877815,0.0018978334,0.00038973326,0.00024847244,0.00000671127,0.000092226765,0.99189657],"genre_scores_gemma":[0.04565209,0.00056417374,0.003316426,0.00071260764,0.0027898583,0.000024069079,0.000262234,0.00003412385,0.9466444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99776953,0.00009559603,0.00048299553,0.0003765658,0.000868929,0.00040636896],"domain_scores_gemma":[0.99829364,0.00019522621,0.00075474277,0.00027683936,0.00033555602,0.00014399948],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00091168936,0.00028085336,0.00046139315,0.0011452071,0.0009568844,0.00024979963,0.00035816192,0.0003229801,0.0030542826],"category_scores_gemma":[0.00013185159,0.00030108538,0.00051993894,0.0007840195,0.0001864247,0.00043438494,0.000078672536,0.0005322799,0.00020855636],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028629174,0.00006055172,0.0014853003,0.000015518974,0.0013591506,5.4447963e-7,0.039010912,0.000026843925,0.0000015976887,0.9226198,0.0031843814,0.032232508],"study_design_scores_gemma":[0.00010567768,0.000028485903,0.0018292427,0.00003688132,0.0021505803,1.854152e-7,0.024195725,0.00009852453,0.0000015695273,0.016072573,0.9549602,0.0005203],"about_ca_topic_score_codex":0.017846247,"about_ca_topic_score_gemma":0.0033576833,"teacher_disagreement_score":0.95177585,"about_ca_system_score_codex":0.0011923664,"about_ca_system_score_gemma":0.0023945307,"threshold_uncertainty_score":0.99994415},"labels":[],"label_agreement":null},{"id":"W4247519277","doi":"10.1007/978-3-030-16454-6","title":"Differentiated Teacher Evaluation and Professional Learning","year":2019,"lang":"en","type":"book","venue":"Palgrave studies on leadership and learning in teacher education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Professional development; Psychology; Professional learning community; Pedagogy; Medical education; Medicine","score_opus":0.1085604436891531,"score_gpt":0.4125393468333608,"score_spread":0.3039789031442077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247519277","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36914757,0.02506345,0.0000041798266,0.006911214,0.004347046,0.0030342466,0.0000012126061,0.00025505453,0.59123605],"genre_scores_gemma":[0.5064078,0.0007205718,0.000013873419,0.000088687666,0.00052622176,0.000097762866,0.00008528694,0.000030657266,0.49202916],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99565977,0.0020215716,0.00038050773,0.00065499876,0.00085871026,0.00042441668],"domain_scores_gemma":[0.9985134,0.0006109309,0.00041430717,0.00012751942,0.00024115936,0.000092700335],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003484193,0.00037692767,0.00048191645,0.00036954635,0.0007964295,0.00013284928,0.00014048777,0.0004705429,0.0002589954],"category_scores_gemma":[0.0014517367,0.00035686977,0.000069494796,0.00016003494,0.000378889,0.00007490661,0.000073451076,0.002196269,0.00005694762],"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":[0.00009077521,0.00027395796,0.37080333,0.00044580703,0.0003321294,0.0000011634351,0.50129426,0.00004359782,0.0000109233615,0.005875999,0.006855848,0.11397219],"study_design_scores_gemma":[0.0011796444,0.00026914448,0.23398255,0.0020454365,0.00035530134,7.7951046e-7,0.70892423,0.00029623642,9.3752135e-7,0.002891624,0.049182568,0.00087153516],"about_ca_topic_score_codex":0.00011246983,"about_ca_topic_score_gemma":0.00029568,"teacher_disagreement_score":0.20762996,"about_ca_system_score_codex":0.00066329894,"about_ca_system_score_gemma":0.00092800934,"threshold_uncertainty_score":0.9998883},"labels":[],"label_agreement":null},{"id":"W4249889919","doi":"10.24124/2001/bpgub1223","title":"Provinding [sic] authentic assessment for vocational programs","year":2001,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocational education; Psychology; Computer science; Pedagogy","score_opus":0.04395059877584961,"score_gpt":0.4216020254307026,"score_spread":0.37765142665485296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249889919","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023680544,0.000075043354,0.0012482336,0.0006515547,0.003122668,0.003692482,0.0000071502923,0.0002501415,0.96727216],"genre_scores_gemma":[0.1641728,0.00007969353,0.00770796,0.000052097395,0.0014349648,0.0014156125,0.0036752324,0.000051545496,0.8214101],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979211,0.000056118,0.00031438167,0.00038736805,0.0008608388,0.00046018363],"domain_scores_gemma":[0.99910337,0.000116988835,0.00025151423,0.00013539106,0.0002891712,0.00010358618],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00066047185,0.00021742583,0.00024497282,0.00013421832,0.0007848753,0.000404173,0.00038720702,0.0002768877,0.0010173332],"category_scores_gemma":[0.000054095744,0.0002091573,0.00019734558,0.00027533955,0.000055175104,0.00019788681,0.000014622914,0.00016473435,0.00004940195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007756135,0.0009792637,0.030412147,0.00032344426,0.0003838818,0.000003204247,0.03422473,6.4171684e-7,0.00007466808,0.6914566,0.016504021,0.22555985],"study_design_scores_gemma":[0.0019582387,0.00040786565,0.08967504,0.0004687956,0.0006721715,6.1530125e-7,0.23763879,0.00024811673,0.0000495595,0.03808704,0.628974,0.0018197568],"about_ca_topic_score_codex":0.0004007115,"about_ca_topic_score_gemma":0.0058636926,"teacher_disagreement_score":0.65336955,"about_ca_system_score_codex":0.00031390597,"about_ca_system_score_gemma":0.00095865194,"threshold_uncertainty_score":0.9998959},"labels":[],"label_agreement":null},{"id":"W4250420280","doi":"10.4018/9781591407324.ch010","title":"Self-Assessment During Online Discussion","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Computer science","score_opus":0.026535787720943914,"score_gpt":0.32138575955527415,"score_spread":0.29484997183433026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250420280","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011735306,0.00010372127,0.000013124844,0.00023611258,0.0011035868,0.00057283114,0.00007688195,0.0003801807,0.99634004],"genre_scores_gemma":[0.26123568,0.0001544491,0.0022930545,0.00017938498,0.002067377,0.00002377492,0.00001934858,0.00007835116,0.7339486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750185,0.000051668194,0.00040236666,0.0005437674,0.00095493335,0.0005453887],"domain_scores_gemma":[0.9989098,0.00001944213,0.00029588927,0.00038699096,0.00011106347,0.00027682332],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021527063,0.0004317742,0.00045566834,0.000068954854,0.0005934659,0.00014069435,0.0006377362,0.0005024314,0.0005639268],"category_scores_gemma":[0.000005234185,0.0003273019,0.00029561986,0.000026085232,0.00016527966,0.00009453361,0.00031749677,0.00037601826,0.0002548351],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017487242,0.000058535905,0.0011973133,0.000027917116,0.00012824705,0.00004600672,0.0014948238,5.1754796e-8,0.00000519985,0.99366665,0.0008020706,0.0025556989],"study_design_scores_gemma":[0.0013840013,0.00017663592,0.015765913,0.00056339963,0.00048222893,0.0000069636358,0.0015676414,0.0000028364354,0.00000863913,0.47067806,0.5076418,0.001721888],"about_ca_topic_score_codex":0.00037439817,"about_ca_topic_score_gemma":0.0017181118,"teacher_disagreement_score":0.52298856,"about_ca_system_score_codex":0.0010122539,"about_ca_system_score_gemma":0.0005575094,"threshold_uncertainty_score":0.9999179},"labels":[],"label_agreement":null},{"id":"W4254133157","doi":"10.4018/978-1-4666-0047-8.ch015","title":"Leveraging Technology to Promote Assessment for Learning in Higher Education","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Peer assessment; Higher education; Computer science; Process (computing); Institution; Engineering management; Mathematics education; Medical education; Engineering; Knowledge management; Psychology; Sociology; Political science; Medicine","score_opus":0.05092252813267043,"score_gpt":0.3644200365005259,"score_spread":0.31349750836785545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254133157","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095838925,0.00009405701,0.00013088236,0.0013065853,0.0012326086,0.0013051811,0.0000047548097,0.00017257666,0.99479496],"genre_scores_gemma":[0.3107278,0.000006328138,0.0039740596,0.00034040387,0.00057555444,0.00022886741,0.000005022908,0.000037824015,0.68410414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984506,0.000024603174,0.000292035,0.0004583256,0.00034556523,0.00042890644],"domain_scores_gemma":[0.99934757,0.000022635886,0.00018230025,0.00019027805,0.00014869726,0.000108526925],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003359787,0.00025471774,0.00032615018,0.00021863628,0.00025900413,0.00009191413,0.00041228568,0.00045269346,0.00023237123],"category_scores_gemma":[0.0000198122,0.00028349034,0.00010262442,0.00006084051,0.00008931341,0.000052775988,0.0001351784,0.00032131578,0.00007714525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011120002,0.00002180213,0.0019034173,0.000012640065,0.000028234383,0.0000024145697,0.0009833545,6.1808106e-7,0.0000101734795,0.9590104,0.0009484454,0.037067365],"study_design_scores_gemma":[0.00020107429,0.00009117235,0.0012800994,0.00019243232,0.00003327347,4.4425298e-7,0.00040594063,6.8825017e-7,0.000003393532,0.43109974,0.5663844,0.0003073779],"about_ca_topic_score_codex":0.000414628,"about_ca_topic_score_gemma":0.00053891813,"teacher_disagreement_score":0.5654359,"about_ca_system_score_codex":0.0009191152,"about_ca_system_score_gemma":0.00090608245,"threshold_uncertainty_score":0.99996173},"labels":[],"label_agreement":null},{"id":"W4255235667","doi":"10.20343/9.1.20","title":"Exploring the Emotional Responses of Undergraduate Students to Assessment Feedback: Implications for Instructors","year":2021,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"MacEwan University; Ohio State University; University of Gloucestershire; Purdue University; Monash University; Leeds Beckett University","keywords":"Psychology; Summative assessment; Peer feedback; Psychological resilience; Variety (cybernetics); Social psychology; Cognition; Negative feedback; Formative assessment; Medical education; Pedagogy","score_opus":0.17912409354407574,"score_gpt":0.44624243943902614,"score_spread":0.2671183458949504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255235667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93178153,0.000040293417,0.007162285,0.058161967,0.0014401588,0.00030084114,0.0000032498194,0.000048630973,0.0010610339],"genre_scores_gemma":[0.9922998,0.00016573582,0.0031905684,0.0002750478,0.0012075448,0.000046026988,0.000004714862,0.000025611045,0.002784932],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99605024,0.0018629134,0.00046876777,0.00023193334,0.0009495745,0.0004365484],"domain_scores_gemma":[0.99715513,0.0017309671,0.00036868828,0.0002589748,0.00034431435,0.00014193072],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0058633653,0.00015828332,0.00022058304,0.00012026761,0.0049663833,0.0005934593,0.0010001778,0.00004185488,0.00003917356],"category_scores_gemma":[0.0018185835,0.00009841958,0.00021278854,0.00036572025,0.00024326764,0.00038880648,0.00026202653,0.0010127528,0.000007627411],"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":[0.00012734573,0.00033170806,0.6802977,0.00001630673,0.00053571956,0.000005194866,0.1365667,0.0033208064,0.0039319587,0.12901285,0.003532376,0.042321347],"study_design_scores_gemma":[0.0004967331,0.00011556781,0.86937153,0.00012708262,0.00008410478,0.000024842066,0.07325613,0.000022182052,0.000044804183,0.0041815545,0.052099004,0.00017646588],"about_ca_topic_score_codex":0.00007312398,"about_ca_topic_score_gemma":0.000062208666,"teacher_disagreement_score":0.18907385,"about_ca_system_score_codex":0.00030210125,"about_ca_system_score_gemma":0.0005506782,"threshold_uncertainty_score":0.996329},"labels":[],"label_agreement":null},{"id":"W4256693308","doi":"10.15760/nwjte.2012.9.2.7","title":"Towards Balanced Assessment of Student Teaching Performance","year":2012,"lang":"en","type":"article","venue":"Northwest Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Summative assessment; Formative assessment; Context (archaeology); Knowledge survey; Process (computing); Medical education; Pedagogy; Mathematics education; Psychology; Computer science; Medicine","score_opus":0.0344671714649823,"score_gpt":0.4169282447697099,"score_spread":0.3824610733047276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256693308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9506296,0.00030700085,0.000111339905,0.0005127673,0.001973891,0.00012625386,5.37791e-7,0.000008767931,0.046329822],"genre_scores_gemma":[0.9936004,0.00017715195,0.003821383,0.000046577676,0.0016397196,0.0000056797076,0.0000034277443,0.00000896188,0.0006966431],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99818015,0.00024447418,0.0004494546,0.00007308231,0.0008047936,0.00024807098],"domain_scores_gemma":[0.9987763,0.00004412356,0.00063593994,0.00011763522,0.00027222311,0.00015378254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002556569,0.00009835221,0.00020921686,0.00013491049,0.00020918355,0.00004476038,0.0003344094,0.000060689777,0.00021346557],"category_scores_gemma":[0.00005706799,0.00008503296,0.0001009965,0.00014810028,0.000066592314,0.00079267035,0.00002986563,0.0003291148,0.000004446483],"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":[0.0000054896686,0.0011209666,0.94208115,0.000010754735,0.000034226327,9.6758384e-8,0.024814313,0.000004997924,0.00019782851,0.0020960534,0.00047918793,0.029154913],"study_design_scores_gemma":[0.00021765359,0.00008441656,0.9658754,0.00005409967,0.00005611499,0.0000025206887,0.020275999,0.0000031315517,0.000039383292,0.00002085672,0.013283058,0.00008735428],"about_ca_topic_score_codex":0.0004240842,"about_ca_topic_score_gemma":0.000087605134,"teacher_disagreement_score":0.04563318,"about_ca_system_score_codex":0.0003458275,"about_ca_system_score_gemma":0.0009299834,"threshold_uncertainty_score":0.34675434},"labels":[],"label_agreement":null},{"id":"W4281488678","doi":"10.1097/acm.0000000000004755","title":"Narrative Assessments in Higher Education: A Scoping Review to Identify Evidence-Based Quality Indicators","year":2022,"lang":"en","type":"review","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Narrative; Thematic analysis; Quality (philosophy); Narrative inquiry; Psychology; Medical education; Descriptive statistics; Computer science; Inclusion (mineral); Qualitative research; Medicine; Social psychology; Sociology; Linguistics; Statistics; Social science","score_opus":0.5162953262998812,"score_gpt":0.6455581755914443,"score_spread":0.12926284929156318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281488678","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020904063,0.97140235,0.000004146837,0.010806044,0.0029964948,0.005216211,0.0000030898832,0.000062625026,0.00948816],"genre_scores_gemma":[0.00004874822,0.98098373,0.000033626537,0.007888501,0.0016236666,0.0025018787,0.00010051366,0.00003915515,0.006780199],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904511,0.0036862493,0.0020184773,0.00089443935,0.0023575525,0.0005921561],"domain_scores_gemma":[0.99496746,0.002681751,0.0013690331,0.0005002153,0.0000803357,0.00040118338],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010367857,0.00048576246,0.0025330698,0.00087050186,0.00043575713,0.000031208867,0.0016978595,0.00045746693,0.023691928],"category_scores_gemma":[0.0028389255,0.00040769047,0.00023038582,0.0044473507,0.00028484387,0.00036564228,0.00027614864,0.0019131246,0.0001085648],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011135777,0.00007117417,0.001755874,0.095630415,0.00011441224,0.000011877697,0.02298835,1.0779177e-7,2.748319e-7,0.0035388544,0.071960256,0.8039173],"study_design_scores_gemma":[0.00010581096,0.000036967787,0.00019036783,0.41991016,0.00025397545,2.9454804e-7,0.00353986,9.899573e-9,1.1094561e-8,0.000036481168,0.57568437,0.00024172346],"about_ca_topic_score_codex":0.0007634539,"about_ca_topic_score_gemma":0.00008340447,"teacher_disagreement_score":0.80367553,"about_ca_system_score_codex":0.0016397862,"about_ca_system_score_gemma":0.006244651,"threshold_uncertainty_score":0.9998375},"labels":[],"label_agreement":null},{"id":"W4282946125","doi":"10.52214/jmetc.v13i1.8984","title":"Peer Feedback in the Mathematics Classroom","year":2022,"lang":"en","type":"article","venue":"Journal of Mathematics Education at Teachers College","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; St. Francis Xavier University","funders":"","keywords":"Peer feedback; Mathematics education; Point (geometry); Psychology; Pedagogy; Mathematics","score_opus":0.03812704026720599,"score_gpt":0.3495190702609642,"score_spread":0.3113920299937582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282946125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8683629,0.0002419714,0.000079100435,0.028535977,0.0013765391,0.0006336197,0.0000074211553,0.00001584754,0.10074664],"genre_scores_gemma":[0.92475986,0.00004828646,0.010222549,0.0006144219,0.0004208443,0.00006283168,0.0000033973668,0.000023834149,0.06384394],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9965681,0.00044153645,0.00068275706,0.00009990486,0.0019584862,0.0002492561],"domain_scores_gemma":[0.9980904,0.0005849402,0.0007484267,0.00022123207,0.00026969358,0.000085331965],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00650257,0.00012425006,0.0002543551,0.00022817292,0.0007235121,0.00009164838,0.00090389745,0.000047012312,0.0015445722],"category_scores_gemma":[0.0006418325,0.00009685046,0.00015960664,0.000659741,0.00009786767,0.000183554,0.000099898236,0.0004907262,0.000036784368],"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":[0.00000992231,0.0026948901,0.0057684123,0.000026336716,0.000045842688,0.0000101751075,0.57314265,0.000024474366,0.00005090617,0.060132876,0.3576908,0.00040272952],"study_design_scores_gemma":[0.00042714225,0.00005594264,0.002856142,0.000027005199,0.000050929702,0.00006347526,0.760929,0.000051402196,0.0000042470506,0.0086822165,0.22672966,0.00012282956],"about_ca_topic_score_codex":0.0000342964,"about_ca_topic_score_gemma":0.00018309087,"teacher_disagreement_score":0.18778637,"about_ca_system_score_codex":0.0011009646,"about_ca_system_score_gemma":0.0009687531,"threshold_uncertainty_score":0.99936813},"labels":[],"label_agreement":null},{"id":"W4283698056","doi":"10.1007/s11092-022-09389-9","title":"Mapping the constellation of assessment discourses: a scoping review study on assessment competence, literacy, capability, and identity","year":2022,"lang":"en","type":"review","venue":"Educational Assessment Evaluation and Accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Memorial University of Newfoundland","funders":"","keywords":"Competence (human resources); Operationalization; Construct (python library); Authentic assessment; Literacy; Rubric; Pedagogy; Identity (music); Psychology; Engineering ethics; Sociology; Epistemology; Social psychology; Computer science; Engineering","score_opus":0.19602477827829456,"score_gpt":0.5663204934521253,"score_spread":0.37029571517383075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283698056","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006654717,0.9474011,0.0000959048,0.0027519553,0.00170517,0.022965105,0.000119422024,0.000047145077,0.018259477],"genre_scores_gemma":[0.04627483,0.9500688,0.00048941374,0.00018947564,0.00032326902,0.0021338286,0.00043012755,0.000029187437,0.00006109835],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98495024,0.0075763287,0.0018803665,0.0011431129,0.0040557683,0.00039418635],"domain_scores_gemma":[0.991549,0.005041269,0.001760233,0.00080450735,0.00069364806,0.00015131474],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026448311,0.00055633433,0.0015899268,0.00029970732,0.0018484618,0.0006231524,0.0007120628,0.00013223491,0.0047709853],"category_scores_gemma":[0.00051713263,0.0004339578,0.00032415526,0.001160552,0.0006946883,0.0010531697,0.0004963881,0.00080059166,0.0000039112506],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073141982,0.005064021,0.22775,0.038322926,0.0005448615,6.639996e-7,0.009985577,0.000009465075,4.66841e-7,0.020005343,0.00045767863,0.69785166],"study_design_scores_gemma":[0.0014302853,0.00046287652,0.7079127,0.07314509,0.003811967,0.0000073525034,0.0634001,0.00031660774,2.6675508e-8,0.0049321265,0.1431074,0.0014734727],"about_ca_topic_score_codex":0.00063796237,"about_ca_topic_score_gemma":0.00046514627,"teacher_disagreement_score":0.69637823,"about_ca_system_score_codex":0.0019554193,"about_ca_system_score_gemma":0.008670215,"threshold_uncertainty_score":0.99981123},"labels":[],"label_agreement":null},{"id":"W4283730835","doi":"10.1080/0142159x.2022.2083489","title":"Technology enhanced assessment: Ottawa consensus statement and recommendations","year":2022,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute for Health and Care Research","keywords":"Coronavirus disease 2019 (COVID-19); Medical education; Engineering ethics; Health technology; Computer science; Knowledge management; Health care; Engineering management; Political science; Medicine; Engineering","score_opus":0.027043108996454637,"score_gpt":0.3946262649641411,"score_spread":0.3675831559676865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283730835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4580026,0.00020752798,0.0004998726,0.19040617,0.0008910815,0.00045416987,0.000006798676,0.0002442662,0.3492875],"genre_scores_gemma":[0.9819305,0.00010425551,0.0006898683,0.00040720223,0.00011237824,0.00015415483,0.000014110483,0.000008481949,0.016579026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809927,0.0003838335,0.00023059984,0.00021532031,0.00078989763,0.0002810862],"domain_scores_gemma":[0.99955136,0.0000879435,0.000076048156,0.000110365414,0.00003064574,0.00014364623],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018220054,0.000076537304,0.00012988647,0.000095529285,0.00088845316,0.00003059387,0.00024791714,0.00007361512,0.0329323],"category_scores_gemma":[0.0002549646,0.000076044154,0.000025483465,0.00032710965,0.00036564784,0.00003386441,0.0002411417,0.00043009,0.000018296336],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019812676,0.0012102532,0.25863907,0.000012758656,0.00022118851,0.00005584752,0.024209617,0.0000017157536,0.00021959301,0.18794537,0.301891,0.22557381],"study_design_scores_gemma":[0.00071036175,0.00008234351,0.0022997805,0.0000064216983,0.000016245518,0.0000016714395,0.044248898,0.00015630094,0.0000058613664,0.003080739,0.94925165,0.00013974559],"about_ca_topic_score_codex":0.00020203396,"about_ca_topic_score_gemma":0.0003039205,"teacher_disagreement_score":0.6473606,"about_ca_system_score_codex":0.00018729769,"about_ca_system_score_gemma":0.00026814654,"threshold_uncertainty_score":0.9679517},"labels":[],"label_agreement":null},{"id":"W4283754310","doi":"10.21083/ajote.v11i1.6880","title":"The Use of Peers in Assessment for Learning: A Case Study of Trainee Teachers at Bindura University of Science Education (BUSE), Zimbabwe","year":2022,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer assessment; Psychology; Sincerity; Medical education; Population; Curriculum; Qualitative property; Mathematics education; Pedagogy; Social psychology; Medicine; Statistics","score_opus":0.06151002741819684,"score_gpt":0.3750338498474102,"score_spread":0.31352382242921334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283754310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99739957,0.00005102254,0.000023518398,0.0009803044,0.00039757325,0.00045013975,0.0000016124892,0.0000025510153,0.0006936999],"genre_scores_gemma":[0.9971447,0.000017768427,0.0007064404,0.000004965939,0.00004361549,0.00000582772,0.000001189704,0.0000054410475,0.0020700807],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9981018,0.00055112,0.000367988,0.00012008754,0.000704636,0.00015438319],"domain_scores_gemma":[0.998018,0.00031610808,0.0010013173,0.0001248812,0.00047088234,0.00006876078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033211475,0.00006741779,0.00017494262,0.00033671805,0.00070890493,0.00002487394,0.00042691236,0.000021023741,0.00004724985],"category_scores_gemma":[0.00034766184,0.00006184555,0.000077726494,0.0009330874,0.00042914104,0.00031388263,0.00006819081,0.00023287538,6.80875e-8],"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":[0.00009347081,0.0032990489,0.52942485,0.0000075138746,0.000045624703,0.0000024544995,0.44726604,0.00048507357,0.0010556971,0.0005753009,0.0013724292,0.016372526],"study_design_scores_gemma":[0.000473889,0.0005261615,0.11342783,0.0000115848725,0.000063062085,0.000009328497,0.8757204,0.000038111484,0.0000094286315,0.00003207644,0.009633237,0.00005489123],"about_ca_topic_score_codex":0.0044426494,"about_ca_topic_score_gemma":0.0014975187,"teacher_disagreement_score":0.42845437,"about_ca_system_score_codex":0.0009586451,"about_ca_system_score_gemma":0.0044405353,"threshold_uncertainty_score":0.7877319},"labels":[],"label_agreement":null},{"id":"W4283778139","doi":"10.1117/12.2635510","title":"Fostering flow and feedback in the classroom: increasing the successful implementation of active learning instruction","year":2022,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; John Abbott College; Vanier College; Dawson College","funders":"","keywords":"Orchestration; Facilitation; Active learning (machine learning); Computer science; Mathematics education; Flow (mathematics); Knowledge management; Multimedia; Psychology; Artificial intelligence","score_opus":0.03253108966307457,"score_gpt":0.356015431635151,"score_spread":0.32348434197207643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283778139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798542,0.000016485392,0.000029285018,0.0012012696,0.00009543793,0.0002506032,0.0000013733256,0.000011328427,0.018539988],"genre_scores_gemma":[0.9996409,0.00003330197,0.00011220109,0.000059558886,0.000053810836,0.000028420938,0.000003558859,0.0000033705228,0.000064921165],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99860144,0.0006744386,0.0001347561,0.00010026724,0.0003555404,0.00013355927],"domain_scores_gemma":[0.99958533,0.00023719197,0.000094977884,0.00005090372,0.000020425365,0.000011186809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013228375,0.000048720372,0.00006591433,0.00004940478,0.0009121873,0.00007508845,0.00017353924,0.000014485589,0.0003609522],"category_scores_gemma":[0.000027686652,0.00003326503,0.00002087782,0.0003366687,0.000081449274,0.00023513312,0.00024151066,0.0001682787,4.622434e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056848847,0.000027630418,0.549652,0.000005268326,0.000018764244,7.2722725e-7,0.13692386,0.00012215757,0.00052716985,0.0040121195,0.000051407555,0.3086021],"study_design_scores_gemma":[0.00033310513,0.000038254973,0.3667851,0.0000022725878,0.000007808608,0.0000013557857,0.6309617,0.00015903417,0.000050508635,0.00045752872,0.0011630832,0.000040237883],"about_ca_topic_score_codex":0.009626238,"about_ca_topic_score_gemma":0.0056126295,"teacher_disagreement_score":0.49403787,"about_ca_system_score_codex":0.00008287068,"about_ca_system_score_gemma":0.000041678133,"threshold_uncertainty_score":0.99696875},"labels":[],"label_agreement":null},{"id":"W4284711440","doi":"10.1108/qae-02-2022-0048","title":"Assuring online assessment quality: the case of unproctored online assessment","year":2022,"lang":"en","type":"article","venue":"Quality Assurance in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Quality (philosophy); Quality assessment; Originality; Psychology; Alternative assessment; Online assessment; Higher education; Medical education; Mathematics education; Marketing; Social psychology; Political science; Formative assessment; Medicine; Business","score_opus":0.08445615915997876,"score_gpt":0.4978529657096593,"score_spread":0.4133968065496806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284711440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787797,0.00022359876,0.00016156999,0.012366142,0.0018393524,0.00084314,0.00014808531,0.000052647505,0.005585767],"genre_scores_gemma":[0.99400616,0.00011495878,0.0036403213,0.00041731456,0.00042030963,0.00026099756,0.00019810296,0.000017769024,0.00092404976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935477,0.0033745212,0.0010700691,0.0004374459,0.0011562317,0.00041404046],"domain_scores_gemma":[0.9970511,0.0013005661,0.00076250476,0.000529255,0.00026899655,0.00008755889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077026314,0.00019205212,0.00040471734,0.00016325021,0.00096625456,0.00009397459,0.00063926505,0.000074376876,0.0004052298],"category_scores_gemma":[0.00039865557,0.00018156147,0.00013830389,0.0011210537,0.00021923942,0.00033030933,0.00018006965,0.0006019047,0.0000015652599],"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":[0.00006155827,0.008963269,0.7506404,0.00018673194,0.00011208248,0.00002203057,0.06700507,0.001234673,0.0007957598,0.10905865,0.0015788825,0.060340885],"study_design_scores_gemma":[0.00045490204,0.000052391668,0.64012235,0.00003221283,0.00002364593,0.0000049062655,0.3466822,0.00023559251,0.000009275086,0.0017356784,0.010414537,0.00023233019],"about_ca_topic_score_codex":0.037396092,"about_ca_topic_score_gemma":0.046258204,"teacher_disagreement_score":0.27967712,"about_ca_system_score_codex":0.0012230405,"about_ca_system_score_gemma":0.0024530513,"threshold_uncertainty_score":0.9711451},"labels":[],"label_agreement":null},{"id":"W4285051177","doi":"10.56498/21202092","title":"Genre-based Rubric for Peer Feedback","year":2020,"lang":"en","type":"article","venue":"Modern Journal of Studies in English Language Teaching and Literature","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Rubric; Argumentative; Peer feedback; Computer science; Peer assessment; Peer evaluation; Psychology; Mathematics education; Higher education; Linguistics; Political science","score_opus":0.038451028981926975,"score_gpt":0.3611125235187574,"score_spread":0.3226614945368304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285051177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9453518,0.0431748,0.0011221261,0.005762529,0.0008442263,0.0002445435,0.000014659971,0.000048874284,0.0034364494],"genre_scores_gemma":[0.9921784,0.00027050253,0.004105629,0.00081068056,0.001998651,0.000004582994,0.0000036754802,0.000013451819,0.00061443355],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99864817,0.00025466518,0.0002901884,0.00015782358,0.00040812892,0.00024101371],"domain_scores_gemma":[0.9989195,0.00040425605,0.00016823449,0.000061008835,0.00033735728,0.00010965716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018057955,0.00013825131,0.00032741396,0.00009542295,0.00033900424,0.00018631163,0.00021611199,0.00008988587,0.0000054957345],"category_scores_gemma":[0.002682264,0.000108591084,0.00011093601,0.00016157553,0.00010424009,0.00028275224,0.000041575757,0.00070541166,2.3487895e-7],"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":[0.00010028848,0.00004424292,0.0029821477,0.000101446196,0.00008040654,0.00007245557,0.9858985,0.00006624078,0.00007972565,0.0004787975,0.0037919933,0.0063037397],"study_design_scores_gemma":[0.0037921036,0.0003997386,0.0009177023,0.0008677508,0.00011967847,0.0000057526204,0.94265914,0.00087612704,0.000027242027,0.0005922399,0.04932033,0.0004221799],"about_ca_topic_score_codex":0.000010516014,"about_ca_topic_score_gemma":0.000022986238,"teacher_disagreement_score":0.0468266,"about_ca_system_score_codex":0.00005832669,"about_ca_system_score_gemma":0.000044862416,"threshold_uncertainty_score":0.4428216},"labels":[],"label_agreement":null},{"id":"W4285677805","doi":"10.18733/cpi29639","title":"All that Glitters is not Gold: Culturally responsive online assessment and pedagogy in uncertain times","year":2022,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Psychology; Pedagogy","score_opus":0.5267311310912989,"score_gpt":0.5478395655922317,"score_spread":0.021108434500932804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285677805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9643075,0.0006355717,0.0000018197406,0.030642116,0.00035450148,0.00034862568,0.000044875258,0.00005403222,0.0036109504],"genre_scores_gemma":[0.9777259,0.0013674956,0.00034438295,0.0056514433,0.0003724304,0.000055313332,0.00009473562,0.000009366983,0.014378937],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99753624,0.00053186575,0.0002757752,0.0005056015,0.0006683854,0.00048212163],"domain_scores_gemma":[0.9992578,0.0002522264,0.00010677208,0.00011210025,0.000066647095,0.00020443423],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005839303,0.000234484,0.00032419382,0.000074222364,0.00061883876,0.00020918035,0.00029267202,0.00010885869,0.0013810038],"category_scores_gemma":[0.000045923523,0.00016902898,0.000084295534,0.00024147576,0.0005646267,0.000354536,0.00042419683,0.0004453557,0.0000072448943],"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":[0.0007232767,0.00062254706,0.18581735,0.000045653967,0.0001612984,0.00024530126,0.71410507,0.000030571104,0.002941392,0.029327946,0.051168624,0.014810977],"study_design_scores_gemma":[0.0009807294,0.00023237128,0.24438979,0.000016585216,0.000035902205,0.000012747858,0.48061118,0.000071686445,0.000010904639,0.0006203363,0.27260476,0.00041300626],"about_ca_topic_score_codex":0.0013428719,"about_ca_topic_score_gemma":0.00048184898,"teacher_disagreement_score":0.23349388,"about_ca_system_score_codex":0.00019246811,"about_ca_system_score_gemma":0.00011037454,"threshold_uncertainty_score":0.99953187},"labels":[],"label_agreement":null},{"id":"W4285723393","doi":"10.7202/1089053ar","title":"Toward the Consolidation of a Sociology of Classroom Assessment: A Narrative Review of the French-Language Literature","year":2020,"lang":"fr","type":"review","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Consolidation (business); Excellence; Sociology; Narrative; Presentation (obstetrics); Engineering ethics; Social science; Pedagogy; Political science; Linguistics; Engineering","score_opus":0.09067218176414672,"score_gpt":0.46036097831665657,"score_spread":0.36968879655250986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285723393","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026828283,0.94054663,0.00042973546,0.04389989,0.0020646288,0.0036098817,0.00016011212,0.000013752429,0.006592523],"genre_scores_gemma":[0.146533,0.8505978,0.00046962974,0.00046167057,0.00032438044,0.00019795411,0.00067433185,0.00002125083,0.0007199679],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9759598,0.020490766,0.0015828507,0.0004127965,0.0013387707,0.00021506503],"domain_scores_gemma":[0.9922209,0.002250934,0.0037786742,0.0004951703,0.0012113935,0.000042926567],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013703961,0.00036265276,0.0013400842,0.000096937314,0.00020419514,0.00002960382,0.0008424209,0.00043342184,0.000921316],"category_scores_gemma":[0.0026777047,0.00022660573,0.0006753737,0.0015811182,0.0009157089,0.00026142917,0.00012529473,0.0006968744,0.000012988837],"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":[0.0000038533713,0.00017849523,0.0006285824,0.020277388,0.0003758527,1.9657094e-7,0.91807544,0.0000035205655,0.00007273692,0.014773336,0.005474309,0.04013627],"study_design_scores_gemma":[0.001522036,0.0006631542,0.13141252,0.1945923,0.009198402,0.000012006617,0.27743524,0.0002976216,0.0001302198,0.00745483,0.37604308,0.0012385881],"about_ca_topic_score_codex":0.00016288366,"about_ca_topic_score_gemma":0.00011989755,"teacher_disagreement_score":0.6406402,"about_ca_system_score_codex":0.0004093268,"about_ca_system_score_gemma":0.0043928134,"threshold_uncertainty_score":0.99999195},"labels":[],"label_agreement":null},{"id":"W4286213965","doi":"10.5296/ijssr.v10i2.19889","title":"Secondary School EFL Teachers’ Formative Assessment Practices and Their Impact on Learning","year":2022,"lang":"en","type":"article","venue":"International Journal of Social Science Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Formative assessment; Summative assessment; Psychology; Mathematics education; Strengths and weaknesses; Test (biology); Peer assessment; Medical education; The Internet; Pedagogy; Medicine; Computer science; Social psychology","score_opus":0.10155170101928927,"score_gpt":0.5545968960672434,"score_spread":0.4530451950479541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286213965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8594934,0.00005315889,0.000019260235,0.007221342,0.0005076513,0.00012601752,0.0000054510083,0.0000080069585,0.13256572],"genre_scores_gemma":[0.9982755,0.00010988302,0.00007371229,0.00008511892,0.0006865016,0.0000082206725,0.0000010882507,0.0000051674415,0.0007547853],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99381566,0.0010492696,0.0002545835,0.00016320439,0.0043071206,0.00041017798],"domain_scores_gemma":[0.9972456,0.0008014022,0.0005809661,0.000043006,0.0011228137,0.00020618376],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017634215,0.0000831714,0.00013995779,0.0006117315,0.0035042025,0.00080956373,0.0013015906,0.00003113279,0.0015648621],"category_scores_gemma":[0.001493681,0.0000615111,0.00009919223,0.0007643268,0.0009512434,0.0015665645,0.0004879401,0.0016930583,0.000008225255],"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":[0.00055070675,0.0008378242,0.2220493,0.0000053138842,0.00047348638,0.00009500572,0.5263829,0.00014736873,0.009763683,0.050112467,0.0074667674,0.18211512],"study_design_scores_gemma":[0.00075302983,0.0008694461,0.41627908,0.000019641573,0.0000056334384,0.000018611716,0.5240498,0.0001396499,0.000081040664,0.003224187,0.05442129,0.00013854587],"about_ca_topic_score_codex":0.0003707531,"about_ca_topic_score_gemma":0.000021146781,"teacher_disagreement_score":0.19422978,"about_ca_system_score_codex":0.0022520248,"about_ca_system_score_gemma":0.0030430858,"threshold_uncertainty_score":0.99934787},"labels":[],"label_agreement":null},{"id":"W4286390209","doi":"10.7202/1090461ar","title":"L’évaluation continue pour apprendre : enjeux de la pluralité des feedbacks entre pairs dans un cours universitaire","year":2021,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.0497611882047252,"score_gpt":0.3633203714747588,"score_spread":0.3135591832700336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286390209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8934623,0.0019599115,0.008043318,0.04051207,0.002183831,0.0005719973,0.000035835896,0.00012609827,0.053104624],"genre_scores_gemma":[0.95085096,0.0015974258,0.0061387424,0.00019920224,0.0006318577,0.000034257413,0.000526009,0.000040044397,0.039981484],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9835117,0.013674164,0.00048324783,0.00058022863,0.0012088545,0.0005418371],"domain_scores_gemma":[0.9964426,0.0016046265,0.00039050446,0.0003219583,0.0010622721,0.00017804513],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013542525,0.00033569304,0.00032527454,0.00013045532,0.00080893125,0.00034126072,0.0003361313,0.00048184243,0.00371443],"category_scores_gemma":[0.0015236684,0.00041164315,0.00022824675,0.0010231014,0.0004583429,0.00097240886,0.00008165034,0.00038534647,0.00019835631],"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":[0.000023988876,0.00064986077,0.17290036,0.000091045906,0.00025009626,0.000013931106,0.7102117,0.001419061,0.0018277171,0.024492323,0.013189558,0.07493038],"study_design_scores_gemma":[0.0012434178,0.000051655043,0.70146585,0.00024359916,0.00058397546,0.000014223865,0.27010104,0.0023018864,0.0009943816,0.015304163,0.007270588,0.00042520696],"about_ca_topic_score_codex":0.00080884015,"about_ca_topic_score_gemma":0.0019410249,"teacher_disagreement_score":0.52856547,"about_ca_system_score_codex":0.0017283286,"about_ca_system_score_gemma":0.0041317777,"threshold_uncertainty_score":0.9998335},"labels":[],"label_agreement":null},{"id":"W4287658006","doi":"","title":"Guidelines for Generating Effective Feedback from E-Assessments","year":2020,"lang":"en","type":"article","venue":"DergiPark (Istanbul University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Psychology","score_opus":0.08930957328236618,"score_gpt":0.36593272620510414,"score_spread":0.276623152922738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287658006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7041585,0.00029790544,0.0793507,0.018187638,0.001466593,0.0028141926,0.00024597926,0.0006464041,0.19283208],"genre_scores_gemma":[0.92153573,0.0002301974,0.057341766,0.0033679549,0.002621158,0.00001682937,0.00015513344,0.00005738071,0.014673873],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984271,0.00017950995,0.00019542855,0.00044559798,0.00038044376,0.0003718989],"domain_scores_gemma":[0.9986549,0.00039058746,0.00014422975,0.00013515555,0.00043757434,0.00023757799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023407098,0.00017747252,0.00025294165,0.00007538811,0.0008230861,0.00014815768,0.00049093727,0.00011431232,0.00026880915],"category_scores_gemma":[0.0003304603,0.00020551811,0.00015636809,0.0005391945,0.00011856581,0.00038300361,0.00012226813,0.000113765804,0.000052601306],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024000886,0.000610804,0.095727526,0.0001604027,0.0021385348,0.00036860854,0.0984058,0.001411406,0.018446092,0.20374815,0.5318459,0.044736646],"study_design_scores_gemma":[0.0020232105,0.00014410459,0.0023336338,0.000028368355,0.00014523313,9.24975e-8,0.044629004,0.002151908,0.00023282644,0.00039364066,0.94748944,0.00042854794],"about_ca_topic_score_codex":0.0009405559,"about_ca_topic_score_gemma":0.0007746932,"teacher_disagreement_score":0.41564348,"about_ca_system_score_codex":0.00022880464,"about_ca_system_score_gemma":0.00017787408,"threshold_uncertainty_score":0.8380785},"labels":[],"label_agreement":null},{"id":"W4291926400","doi":"10.5539/elt.v15n9p9","title":"The Impact of Peer Feedback on Chinese EFL Junior High School Students’ Writing Performance","year":2022,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Formative assessment; Psychology; Corrective feedback; Mathematics education; Class (philosophy); Grammar; Pedagogy; Computer science","score_opus":0.010141569157979632,"score_gpt":0.3475321059387549,"score_spread":0.33739053678077524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291926400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94553494,0.0001463586,0.0000021416456,0.0001785644,0.0007017016,0.00031124518,0.000014263671,0.0001288306,0.05298192],"genre_scores_gemma":[0.99082875,0.000021058908,0.000066406225,0.00005877083,0.0011250059,0.000039933006,0.000018015042,0.000026464191,0.007815594],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966137,0.00069087,0.000300944,0.00024549905,0.001668213,0.00048078882],"domain_scores_gemma":[0.9987336,0.000540504,0.00020057193,0.00033100988,0.00008156359,0.0001127498],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004650026,0.0001837215,0.00021874248,0.000098629964,0.002799391,0.0003003295,0.0011244884,0.000043849144,0.0008400927],"category_scores_gemma":[0.0014443762,0.00013024991,0.00017931602,0.0003382444,0.000099044184,0.00030825328,0.0003844982,0.0009721968,0.00001894529],"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":[0.0000674956,0.00021724067,0.6779767,0.0000066480493,0.00009368728,0.000009056747,0.3113701,0.00044560354,0.00020235642,0.0011183429,0.00205085,0.006441886],"study_design_scores_gemma":[0.0011275575,0.0003093376,0.51153123,0.00003617705,0.000023642051,8.485286e-7,0.483789,0.00010442032,0.000020724068,0.00004020132,0.0027012196,0.00031562508],"about_ca_topic_score_codex":0.002892071,"about_ca_topic_score_gemma":0.00012404186,"teacher_disagreement_score":0.17241889,"about_ca_system_score_codex":0.00040179232,"about_ca_system_score_gemma":0.0001104732,"threshold_uncertainty_score":0.99849886},"labels":[],"label_agreement":null},{"id":"W4292230213","doi":"10.32329/uad.992521","title":"Curriculum Evaluation in Higher Education: Examples from Australia, Canada, The United Kingdom, and the United StatesCurriculum Evaluation in Higher Education: Comparative Analysis of Some Practices from Australia, Canada, the United Kingdom, and the United States","year":2021,"lang":"en","type":"article","venue":"DergiPark (Istanbul University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Kingdom; Curriculum; Political science; Public administration; Library science; Law; Computer science","score_opus":0.1556669228352931,"score_gpt":0.37538849787615597,"score_spread":0.21972157504086287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292230213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97613627,0.0003702907,0.0000027006618,0.020688364,0.0006418993,0.0011716062,0.00014318382,0.0000139050035,0.000831785],"genre_scores_gemma":[0.9925375,0.00019080818,0.000031152285,0.0006892037,0.000145865,0.000039819337,0.0031936355,0.000010752445,0.0031612653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9906578,0.006211978,0.0005809656,0.0005519863,0.0015780102,0.00041924464],"domain_scores_gemma":[0.99267524,0.0038584904,0.0010644932,0.0005337159,0.00173145,0.00013660909],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002262568,0.00033894583,0.0005324342,0.0008499474,0.0009910158,0.00036731627,0.0007445046,0.00013568118,0.0015768037],"category_scores_gemma":[0.00040151988,0.00022214968,0.00008576965,0.01069749,0.0010392857,0.0005017713,0.00016219262,0.00050146354,0.000001062102],"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":[0.0006650231,0.00076331914,0.56528085,0.00003214106,0.0036225915,0.000027672506,0.06578532,0.027792854,0.000020619462,0.31977278,0.016126147,0.00011070976],"study_design_scores_gemma":[0.00295995,0.000014082034,0.5455624,0.00008298609,0.0028850168,3.9103645e-7,0.20994478,0.009253332,0.0000067296864,0.0018347932,0.22711407,0.0003414667],"about_ca_topic_score_codex":0.99876994,"about_ca_topic_score_gemma":0.9966951,"teacher_disagreement_score":0.31793797,"about_ca_system_score_codex":0.0014460263,"about_ca_system_score_gemma":0.0041674105,"threshold_uncertainty_score":0.9993359},"labels":[],"label_agreement":null},{"id":"W4292772413","doi":"10.3102/1443120","title":"Large-Scale Assessment in Mathematics: The Relationship Between Teachers' Views and Classroom Practice","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Mathematics education; Computer science; Mathematics; Geography","score_opus":0.031363479234160864,"score_gpt":0.354898228618803,"score_spread":0.3235347493846421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292772413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8710303,0.000130553,0.0000044789863,0.008308626,0.00013904585,0.0006997657,0.0000055060714,0.000022650027,0.11965912],"genre_scores_gemma":[0.99287266,0.000033703876,0.0028697024,0.000105075116,0.00018416531,0.000016815811,8.305278e-7,0.000013926905,0.0039031063],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983355,0.000098968965,0.00039425518,0.00022219491,0.00062118546,0.0003279392],"domain_scores_gemma":[0.9976606,0.0015053276,0.00048139176,0.00010964932,0.00019710591,0.000045945657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055147163,0.00012795259,0.00023635528,0.00005534241,0.00042888167,0.00014954241,0.0005233316,0.00010795989,0.000019680081],"category_scores_gemma":[0.0015992684,0.00008222744,0.00006783188,0.00036962345,0.00015063761,0.00074352854,0.00026671856,0.00045821772,0.00002356988],"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":[0.0000037432692,0.000050523253,0.8608474,0.00002955544,0.000013449828,3.0253595e-8,0.12167478,6.6653195e-7,0.00012495536,0.016067604,0.0010996097,0.00008766546],"study_design_scores_gemma":[0.0003874661,0.000032984157,0.63455623,0.000248541,0.000060520986,5.445266e-7,0.34797686,0.000037289326,0.000031302174,0.0041876207,0.012340967,0.00013964699],"about_ca_topic_score_codex":0.00022897842,"about_ca_topic_score_gemma":0.00011126783,"teacher_disagreement_score":0.22630209,"about_ca_system_score_codex":0.000092096976,"about_ca_system_score_gemma":0.000066960914,"threshold_uncertainty_score":0.33531377},"labels":[],"label_agreement":null},{"id":"W4292841507","doi":"10.3102/1430052","title":"Fairness of Teachers' Grading Practices and Decisions in Canadian and Chinese Secondary Schools","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Computer science; Mathematics education; Psychology; Engineering","score_opus":0.011611069291201292,"score_gpt":0.31345446260978127,"score_spread":0.30184339331857996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292841507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9641874,0.00031313044,4.8634483e-8,0.0017819885,0.00014352438,0.0003179194,0.0000081226135,0.0000079847005,0.033239886],"genre_scores_gemma":[0.99881375,0.00014386042,0.0003398824,0.000036155572,0.000061379396,0.0000035691505,3.6650127e-7,0.000008215435,0.0005928337],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99895954,0.00002723097,0.00023891116,0.00019743263,0.00029092532,0.00028597462],"domain_scores_gemma":[0.99896556,0.0002895499,0.0004062664,0.0000521046,0.0001700184,0.000116484116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017894254,0.00010045348,0.00021325226,0.00014619503,0.0002204697,0.00009585666,0.00031142947,0.00008189047,0.000016739561],"category_scores_gemma":[0.0021709288,0.00007595835,0.00003295916,0.0003562674,0.00011930627,0.00084591535,0.00014951816,0.00026043205,0.000002211165],"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":[0.000009089468,0.000011704663,0.96226573,0.000020043435,0.000011337776,1.10190186e-7,0.032438815,3.7356202e-7,0.0026750178,0.0014647606,0.00027010273,0.0008328871],"study_design_scores_gemma":[0.0003763842,0.000031145824,0.9082271,0.0003154603,0.000016660082,0.0000013021265,0.0877865,0.000024046994,0.00017791592,0.0011299289,0.0017816947,0.00013189844],"about_ca_topic_score_codex":0.16453886,"about_ca_topic_score_gemma":0.05528561,"teacher_disagreement_score":0.10925324,"about_ca_system_score_codex":0.000056254532,"about_ca_system_score_gemma":0.00019422764,"threshold_uncertainty_score":0.961953},"labels":[],"label_agreement":null},{"id":"W4292847067","doi":"10.3102/1446397","title":"Building Preservice Elementary Teachers' Capacity in Authentic Assessment Through Problem-Based Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Computer science; Psychology","score_opus":0.01866985797117298,"score_gpt":0.309482046371426,"score_spread":0.290812188400253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292847067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94349784,0.00005076702,0.000013453315,0.0016781962,0.0002891285,0.0009804358,0.0000042122438,0.00007300538,0.05341296],"genre_scores_gemma":[0.9800016,0.000012563835,0.018309724,0.00013890886,0.00015186371,0.000033149438,0.0000017239144,0.000025928592,0.0013245031],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973774,0.000107049666,0.0004894067,0.00040876734,0.0009925799,0.00062480883],"domain_scores_gemma":[0.99883574,0.00019436002,0.00050343823,0.000112657384,0.00029342342,0.000060378105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028936442,0.00021490456,0.0003232238,0.00009887163,0.00044677628,0.00014951591,0.0009457465,0.00012295679,0.00011811518],"category_scores_gemma":[0.00021347155,0.00018098297,0.00013588493,0.00061861426,0.00013258935,0.00095004775,0.00033850377,0.00057971396,0.000015662778],"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":[0.000020816977,0.00013941144,0.9218539,0.0001397393,0.000037208247,1.5644322e-7,0.05001868,0.00026995936,0.020556033,0.0061305887,0.00060237834,0.00023112414],"study_design_scores_gemma":[0.00717734,0.00075069815,0.5580963,0.0053851698,0.00035846318,0.000001991052,0.3255544,0.0034971295,0.024404712,0.014855093,0.05754487,0.0023738726],"about_ca_topic_score_codex":0.0053240233,"about_ca_topic_score_gemma":0.00019781603,"teacher_disagreement_score":0.36375764,"about_ca_system_score_codex":0.00029646186,"about_ca_system_score_gemma":0.00013432726,"threshold_uncertainty_score":0.8048366},"labels":[],"label_agreement":null},{"id":"W4293420146","doi":"10.1111/medu.14932","title":"‘For the most part it works’: Exploring how authors navigate peer review feedback","year":2022,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Western University","funders":"","keywords":"Credibility; Context (archaeology); Autonomy; Process (computing); Peer feedback; Peer review; Consistency (knowledge bases); Psychology; Grounded theory; Social psychology; Knowledge management; Public relations; Computer science; Qualitative research; Pedagogy; Sociology; Political science","score_opus":0.10468164831843134,"score_gpt":0.4169217140655558,"score_spread":0.31224006574712443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293420146","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045826244,0.0063697207,0.00011797984,0.9705709,0.010177636,0.0009117374,0.000003682367,0.000057302772,0.0072083967],"genre_scores_gemma":[0.33730972,0.079004034,0.00084428256,0.13755503,0.01676914,0.01765448,0.0006902541,0.000110941124,0.4100621],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971546,0.0002469855,0.00018239697,0.00019751131,0.0019426002,0.00027590053],"domain_scores_gemma":[0.99904835,0.00032690255,0.000100215744,0.00017534045,0.00020713675,0.00014203806],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0045856233,0.00008383604,0.00012815207,0.000023001377,0.0013394075,0.00013177394,0.00053826935,0.000042682084,0.0049699484],"category_scores_gemma":[0.003472939,0.000064445485,0.00007576984,0.000542322,0.00013487069,0.0002126934,0.0000984061,0.00031484096,0.000034380355],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036637687,0.00008803058,0.0006571836,0.000033158867,0.000011985912,2.581134e-7,0.007628005,8.344803e-7,3.8729186e-7,0.0017545511,0.88926744,0.10055449],"study_design_scores_gemma":[0.00009955624,0.000014960172,0.00068371766,0.00028717323,0.00003926648,3.844945e-7,0.04243908,0.000032887292,5.732858e-7,0.00015739139,0.9561599,0.00008510792],"about_ca_topic_score_codex":0.00020849801,"about_ca_topic_score_gemma":0.000103024824,"teacher_disagreement_score":0.83301586,"about_ca_system_score_codex":0.00017363828,"about_ca_system_score_gemma":0.0012023221,"threshold_uncertainty_score":0.9999607},"labels":[],"label_agreement":null},{"id":"W4297236988","doi":"10.5430/wjel.v12n8p49","title":"Review of Formative Assessment Practices: Primary Evidence on Relationship with Self-efficacy and Self-esteem","year":2022,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Self-efficacy; Mathematics education; Variation (astronomy); Self-esteem; Knowledge survey; Social psychology; Summative assessment","score_opus":0.035515425108625806,"score_gpt":0.3701219538905678,"score_spread":0.33460652878194197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297236988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6567549,0.086659916,0.000057362773,0.004175961,0.0011800996,0.001607564,0.000013263337,0.00012647819,0.24942446],"genre_scores_gemma":[0.981519,0.011882297,0.0048239906,0.0008424626,0.00039043877,0.000015812238,0.0000029781218,0.0000131664965,0.0005098929],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753517,0.0007319713,0.0004348949,0.00011883187,0.0010113451,0.00016779517],"domain_scores_gemma":[0.9960063,0.001680945,0.001675424,0.00014318281,0.00040146726,0.00009268749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035076824,0.000106813815,0.0002925893,0.00017679532,0.00035741052,0.000058829963,0.0003119313,0.000018984183,0.00020641011],"category_scores_gemma":[0.0012298948,0.000084527666,0.000068056106,0.0006546487,0.000057259746,0.0008437572,0.00008415162,0.0005341438,9.015227e-7],"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":[0.0004921742,0.004755268,0.14552194,0.0036931406,0.00078244956,0.00021294852,0.7891261,0.00005723048,0.000039195857,0.025298007,0.023836933,0.0061846045],"study_design_scores_gemma":[0.0035203162,0.0032808734,0.23785242,0.014784087,0.0011076299,0.000031020594,0.21255162,0.000009278008,0.000018543937,0.000083846615,0.5261523,0.0006080558],"about_ca_topic_score_codex":0.000026836118,"about_ca_topic_score_gemma":0.000057472753,"teacher_disagreement_score":0.5765745,"about_ca_system_score_codex":0.0003130153,"about_ca_system_score_gemma":0.0004421945,"threshold_uncertainty_score":0.34469384},"labels":[],"label_agreement":null},{"id":"W4301180890","doi":"10.21203/rs.3.rs-1942986/v2","title":"Improving the Effectiveness of Teacher Assessment in Higher Education: A Case Study of Professors’ Perceptions in Morocco","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec en Outaouais","funders":"","keywords":"Apprehension; Strengths and weaknesses; Perception; Psychology; Higher education; Anxiety; Medical education; Process (computing); Pedagogy; Political science; Medicine; Social psychology","score_opus":0.15942425412388184,"score_gpt":0.5378363459027331,"score_spread":0.37841209177885127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301180890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9783014,0.00016503393,0.0000011006543,0.0003582681,0.0004302798,0.005461713,0.000010177189,0.000012735302,0.015259283],"genre_scores_gemma":[0.99415153,0.00003709738,0.000031555024,0.000002440664,0.00014372756,0.003629404,0.000013844273,0.000018978042,0.001971443],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9852986,0.011490537,0.0004667923,0.00047910225,0.0018374466,0.00042753958],"domain_scores_gemma":[0.9972425,0.0015139647,0.00018478636,0.00058498286,0.0004141602,0.000059593407],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015119224,0.00015764359,0.00038948123,0.00060680846,0.00046535712,0.00007940545,0.00081572577,0.00016098493,0.0016663704],"category_scores_gemma":[0.0002492016,0.00013159578,0.00009745209,0.001358413,0.00027732246,0.00010879244,0.0015657361,0.0021652381,0.0000016599671],"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":[0.00006023522,0.004646079,0.9063409,0.0006541286,0.00004058251,0.00006567526,0.08418496,0.00016747613,0.00007238639,0.0028547344,0.000049341506,0.0008635064],"study_design_scores_gemma":[0.00035728165,0.00014511646,0.5746845,0.00020201932,0.0000105437,5.1527604e-7,0.42418393,0.00002040152,8.739867e-7,0.00025663926,0.00006125774,0.00007691051],"about_ca_topic_score_codex":0.1386965,"about_ca_topic_score_gemma":0.029096698,"teacher_disagreement_score":0.339999,"about_ca_system_score_codex":0.0014295061,"about_ca_system_score_gemma":0.0029917287,"threshold_uncertainty_score":0.99924624},"labels":[],"label_agreement":null},{"id":"W4303833150","doi":"10.3390/logistics6040070","title":"Student-Centered Curriculum Design and Evaluation in Logistics Management","year":2022,"lang":"en","type":"article","venue":"Logistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Curriculum; Constructive; Plan (archaeology); Logistics management; Conceptual framework; Engineering ethics; Computer science; Mathematics education; Knowledge management; Sociology; Engineering management; Process management; Pedagogy; Engineering; Psychology; Process (computing)","score_opus":0.10667085788631406,"score_gpt":0.40068361902944344,"score_spread":0.29401276114312935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303833150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37370068,0.0022292437,0.24298914,0.0037607711,0.008094894,0.010603852,0.000058175712,0.00043541807,0.35812783],"genre_scores_gemma":[0.995495,0.00027167914,0.0031900909,0.00011453055,0.000073142335,0.00012362466,0.00001572308,0.0000072132234,0.0007089484],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99789613,0.00054099644,0.00019515601,0.00022177957,0.0008803216,0.00026559312],"domain_scores_gemma":[0.99958056,0.00011712401,0.00007774606,0.00012004017,0.000054660155,0.000049878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020199602,0.00008924116,0.000114777446,0.00009487935,0.00044540982,0.00008507151,0.00027035055,0.00003066543,0.0003043794],"category_scores_gemma":[0.00009736486,0.000097455486,0.000019879175,0.00030115072,0.00013207963,0.00004912256,0.0002707289,0.00013133376,0.000009984572],"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":[0.000053137042,0.001446042,0.58548087,0.000033168184,0.000096739524,0.00014327263,0.017470334,0.037352182,0.000010120743,0.3286406,0.010795261,0.018478286],"study_design_scores_gemma":[0.007015986,0.000668456,0.5133555,0.000050390354,0.00056148786,0.0000037992218,0.24373637,0.099782236,0.0000029926746,0.045101646,0.088465154,0.0012559796],"about_ca_topic_score_codex":0.00021973293,"about_ca_topic_score_gemma":0.00018460458,"teacher_disagreement_score":0.62179434,"about_ca_system_score_codex":0.000354508,"about_ca_system_score_gemma":0.000052597454,"threshold_uncertainty_score":0.39741194},"labels":[],"label_agreement":null},{"id":"W4304693611","doi":"10.1097/acm.0000000000005013","title":"The Case for Feedback-in-Practice as a Topic of Educational Scholarship","year":2022,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scholarship; Higher education; Sociology; Medical education; Psychology; Pedagogy; Medicine; Political science","score_opus":0.058813945386953254,"score_gpt":0.45603152081014,"score_spread":0.3972175754231867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304693611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65218866,0.003357502,0.000009566764,0.27293396,0.0015034238,0.00072515896,0.000003417511,0.000011117177,0.069267176],"genre_scores_gemma":[0.98594475,0.0005473157,0.000051330197,0.0015413427,0.0007314626,0.00014211122,0.0000043658633,0.0000049755895,0.011032338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986479,0.00030344495,0.0002586296,0.00012877151,0.00045712764,0.00020411228],"domain_scores_gemma":[0.9951165,0.0044854744,0.00015436376,0.0001036448,0.00008263376,0.000057434467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038774048,0.00005422624,0.00010834838,0.00005776504,0.0007392776,0.0000067359356,0.00037182556,0.000052844818,0.0007704158],"category_scores_gemma":[0.005228931,0.00004110112,0.000024761304,0.00033947156,0.0002140695,0.00014076123,0.00006808614,0.00048010438,0.0000066483212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001358332,0.00003663018,0.041807953,0.000013259489,0.00004307566,0.00002670009,0.062338546,0.0000032807127,0.00015955685,0.8626126,0.02654607,0.0062764785],"study_design_scores_gemma":[0.001178424,0.00016298327,0.006190894,0.000027387823,0.00006379219,0.00007730004,0.29670087,0.000011407498,0.000010057615,0.043499738,0.6519842,0.00009291523],"about_ca_topic_score_codex":0.001466174,"about_ca_topic_score_gemma":0.00025307437,"teacher_disagreement_score":0.8191129,"about_ca_system_score_codex":0.00013033053,"about_ca_system_score_gemma":0.00030188303,"threshold_uncertainty_score":0.8435513},"labels":[],"label_agreement":null},{"id":"W4308121603","doi":"10.3390/jrfm15110503","title":"Students’ Perception of the Use of a Rubric and Peer Reviews in an Online Learning Environment","year":2022,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; Peer assessment; Summative assessment; Grading (engineering); Likert scale; Writing assessment; Peer feedback; Psychology; Computer science; Mathematics education; Medical education; Formative assessment; Engineering; Medicine","score_opus":0.04913201276311174,"score_gpt":0.31686616042821814,"score_spread":0.2677341476651064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308121603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99896723,0.0003865295,0.00013055543,0.0001454017,0.00010439581,0.00021397011,0.0000036350202,7.744647e-7,0.000047528974],"genre_scores_gemma":[0.98047906,0.018195188,0.000587508,0.000031117946,0.00005394634,0.0000033807182,7.00012e-7,0.0000028232241,0.00064628455],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99854404,0.00037228598,0.00033314264,0.00007541201,0.0005909026,0.00008423817],"domain_scores_gemma":[0.99944615,0.000030966185,0.00041656103,0.00005772023,0.000022979377,0.000025604457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016087889,0.00005291822,0.00017898045,0.00009461034,0.0002068928,0.000021141654,0.00016644361,0.000016034624,0.00004973767],"category_scores_gemma":[0.0000645528,0.000039840706,0.00005427989,0.00015168874,0.00006694737,0.00013285804,0.0002111397,0.00018724438,1.3634053e-7],"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":[0.00004146139,0.00025259433,0.8903595,0.000013339056,0.000006231648,0.0000025811835,0.013393435,0.0002540568,0.00002221142,0.00025010397,0.00019451023,0.09520998],"study_design_scores_gemma":[0.00034902414,0.0001545504,0.8081271,0.000027312053,0.000044567958,3.6626588e-7,0.010708368,0.000013744225,1.6645615e-7,0.000080089696,0.18046033,0.000034387114],"about_ca_topic_score_codex":0.00019651407,"about_ca_topic_score_gemma":0.0002013089,"teacher_disagreement_score":0.18026581,"about_ca_system_score_codex":0.000059408732,"about_ca_system_score_gemma":0.000009909141,"threshold_uncertainty_score":0.16246568},"labels":[],"label_agreement":null},{"id":"W4308198949","doi":"10.1177/00224871221130742","title":"Teachers’ Conceptions of Fairness in Classroom Assessment: An Empirical Study","year":2022,"lang":"en","type":"article","venue":"Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Equity (law); Psychology; Dialectic; Pedagogy; Empirical research; Mathematics education; Social psychology; Epistemology; Political science","score_opus":0.05846958575669899,"score_gpt":0.4690927883659702,"score_spread":0.4106232026092712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308198949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895428,0.000071730974,0.000049016337,0.0021389395,0.0008953976,0.00025947957,0.0000011637889,0.0000072827584,0.007034179],"genre_scores_gemma":[0.99749106,0.000006996821,0.00047761263,0.000052751628,0.00037829444,0.000026884774,0.0000042474426,0.0000079110105,0.0015542364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99720806,0.0012451141,0.00048496714,0.0001171433,0.0007952916,0.00014941666],"domain_scores_gemma":[0.99906987,0.00007414046,0.00048179016,0.00012184025,0.0001654542,0.000086882865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027938196,0.00007434103,0.00020417022,0.00026070606,0.00025880616,0.000044304918,0.0003972868,0.000039490686,0.0009006505],"category_scores_gemma":[0.000077153265,0.000074005664,0.00007639734,0.00050657155,0.000072453295,0.00044271292,0.000048769274,0.0004892791,0.0000017125366],"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":[0.000012263059,0.0054629864,0.8329427,0.0000012214914,0.000018272058,0.000001146591,0.15469894,0.000037580503,0.00011291745,0.00037903612,0.002233023,0.004099875],"study_design_scores_gemma":[0.00035827173,0.0002709741,0.57782763,0.000004290984,0.000025488856,0.0000011636453,0.4123872,0.000008293603,6.2642323e-7,0.00028590407,0.00878112,0.00004907229],"about_ca_topic_score_codex":0.0006470479,"about_ca_topic_score_gemma":0.00058001664,"teacher_disagreement_score":0.25768822,"about_ca_system_score_codex":0.0006714598,"about_ca_system_score_gemma":0.001548449,"threshold_uncertainty_score":0.98614913},"labels":[],"label_agreement":null},{"id":"W4309546005","doi":"10.53967/cje-rce.5515","title":"A Course or a Pathway? Addressing French as a Second Language Teacher Recruitment and Retention in Canadian BEd Programs","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of New Brunswick; University of British Columbia; University of Ottawa","funders":"","keywords":"Practicum; Certification; Graduation (instrument); Teacher education; Professional development; Pedagogy; Medical education; Alternative teacher certification; Psychology; Public relations; Political science; Engineering; Medicine","score_opus":0.11541611075203806,"score_gpt":0.3692933403736302,"score_spread":0.25387722962159215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309546005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98402435,0.000808441,9.403927e-7,0.005768165,0.0020117643,0.00060689554,0.00001772112,0.0000051338834,0.006756604],"genre_scores_gemma":[0.9873493,0.000016181124,0.0001563216,0.00042561887,0.00040372682,0.00017140943,0.00006617298,0.00001696664,0.011394311],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99822545,0.00037679123,0.0003586253,0.00020052966,0.00014048522,0.0006981426],"domain_scores_gemma":[0.9976616,0.000042670494,0.00030796704,0.0001447525,0.00022076863,0.0016222594],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021818944,0.000117690244,0.00017295561,0.00072515936,0.0007258102,0.00019819128,0.0002652361,0.000079842896,0.0024174734],"category_scores_gemma":[0.00043233708,0.00013630808,0.000048761427,0.00068448647,0.00008397454,0.00029333917,0.000008836864,0.0003429348,0.0000029443784],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000016561049,0.00016428775,0.1715666,0.000043350625,0.00004333027,0.00014058646,0.75867575,0.000007733682,0.00009831697,0.0030852377,0.009112692,0.05704556],"study_design_scores_gemma":[0.00040501155,0.00020957083,0.1450044,0.00019100797,0.000052000938,0.00021489972,0.5754826,0.000028066692,0.0000051895777,0.00074277545,0.27740005,0.0002644272],"about_ca_topic_score_codex":0.9462234,"about_ca_topic_score_gemma":0.9996137,"teacher_disagreement_score":0.26828736,"about_ca_system_score_codex":0.009784113,"about_ca_system_score_gemma":0.041952267,"threshold_uncertainty_score":0.99849445},"labels":[],"label_agreement":null},{"id":"W4310224264","doi":"10.5430/wjel.v12n7p284","title":"Exploring L2 Written Corrective Feedback in the Saudi Context: A Critical Review","year":2022,"lang":"en","type":"review","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Context (archaeology); Corrective feedback; Diversity (politics); Computer science; Function (biology); Psychology; Knowledge management; Mathematics education; Political science","score_opus":0.14835845779168574,"score_gpt":0.4052358743294563,"score_spread":0.2568774165377705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310224264","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013939592,0.9266074,8.410071e-7,0.00036889216,0.0028582183,0.000663103,0.000011913746,0.000018636842,0.06945707],"genre_scores_gemma":[0.0002658263,0.9947072,0.000037604463,0.00063235196,0.0033436695,0.00013168217,0.000008745491,0.000036180943,0.000836686],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99442106,0.0023131084,0.0011327366,0.00026230543,0.0013672456,0.000503546],"domain_scores_gemma":[0.99493337,0.00358675,0.0007528413,0.0002926907,0.000292907,0.00014142659],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058174394,0.00033336747,0.0017343507,0.00045763626,0.0003319155,0.0001886748,0.0015155864,0.00007796798,0.00252122],"category_scores_gemma":[0.00774942,0.00022929028,0.00088162057,0.0018493455,0.00019478735,0.00052301056,0.00015962755,0.0020064425,0.000020919406],"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":[0.000009543413,0.0001564946,0.000044437355,0.003759046,0.00012478985,0.00056958065,0.09818444,6.960818e-8,9.974754e-9,0.0021144398,0.020229064,0.8748081],"study_design_scores_gemma":[0.00017092886,0.000044276807,0.000022507256,0.022808306,0.0005310256,0.000014536636,0.10029072,2.4929383e-8,1.2326552e-8,0.000012668457,0.8758844,0.00022056722],"about_ca_topic_score_codex":0.00018384976,"about_ca_topic_score_gemma":0.0011114458,"teacher_disagreement_score":0.87458754,"about_ca_system_score_codex":0.00053880777,"about_ca_system_score_gemma":0.00050794287,"threshold_uncertainty_score":0.9983906},"labels":[],"label_agreement":null},{"id":"W4310243809","doi":"10.5430/wjel.v13n1p121","title":"Investigating Saudi EFL University Teachers' Knowledge in Adopting Learning-Oriented Assessment","year":2022,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Competence (human resources); English as a foreign language; Mathematics education; Psychology; Foreign language; Medical education; Computer science; Medicine","score_opus":0.01518739486911758,"score_gpt":0.3115365173234899,"score_spread":0.29634912245437234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310243809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8656771,0.00046155002,0.000016989043,0.00019474472,0.0009090401,0.00009764673,0.0000014526317,0.000037177593,0.13260429],"genre_scores_gemma":[0.9893973,0.000036524154,0.0016410557,0.000037794023,0.0006725294,0.0000010639537,0.0000034287405,0.000011487709,0.008198848],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9977201,0.0009419433,0.00030883218,0.00013940007,0.0005815601,0.00030813008],"domain_scores_gemma":[0.99887705,0.00029915952,0.00040932806,0.00007711423,0.0002054592,0.00013190311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029221599,0.0001026131,0.0002228154,0.00034916814,0.00067847024,0.000053397966,0.00040131516,0.000030167195,0.0006375054],"category_scores_gemma":[0.0007802113,0.000115305906,0.000112667054,0.0012424279,0.00009305245,0.00030299975,0.00021041036,0.0010988988,0.0000018728517],"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":[0.000016250175,0.00023878705,0.43449816,0.000009260546,0.000049995833,0.00015847171,0.5497689,0.0007349779,0.00016358912,0.004834243,0.0021571736,0.0073701446],"study_design_scores_gemma":[0.00092331617,0.00007507682,0.032041006,0.000056745943,0.00002481593,8.83803e-7,0.6514668,0.000059258306,0.0000046733253,0.000009023631,0.31520346,0.00013494192],"about_ca_topic_score_codex":0.00039067486,"about_ca_topic_score_gemma":0.0016310365,"teacher_disagreement_score":0.40245715,"about_ca_system_score_codex":0.00089683,"about_ca_system_score_gemma":0.00032172626,"threshold_uncertainty_score":0.6980237},"labels":[],"label_agreement":null},{"id":"W4311636586","doi":"10.3390/higheredu1010002","title":"Improving Student Feedback Literacy in e-Assessments: A Framework for the Higher Education Context","year":2022,"lang":"en","type":"article","venue":"Trends in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Digital literacy; Literacy; Computer science; Process (computing); Formative assessment; Mathematics education; Psychology; Knowledge management; Pedagogy; World Wide Web","score_opus":0.06443909059896195,"score_gpt":0.45411602562832754,"score_spread":0.38967693502936557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311636586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7877024,0.007134115,0.00015082792,0.07941871,0.04726725,0.003315114,0.000028352033,0.00018626747,0.07479701],"genre_scores_gemma":[0.91613466,0.000037484526,0.0011652523,0.001474796,0.0010989876,0.0026165599,0.00006217898,0.000023476965,0.07738658],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99793756,0.00031196408,0.00039760236,0.000391566,0.0005676702,0.00039362334],"domain_scores_gemma":[0.9987804,0.0005064951,0.00023729124,0.00031274176,0.00009984481,0.0000631754],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00087181263,0.0001684076,0.00018252949,0.00036249132,0.00063687045,0.00027279582,0.00062110065,0.00008513154,0.0060257125],"category_scores_gemma":[0.000024686407,0.00015674872,0.00008602719,0.0013456623,0.00006910519,0.0004269066,0.00012364217,0.00037519797,0.000012872681],"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":[0.00007487871,0.002440908,0.2668349,0.000017042044,0.000032407785,3.7151764e-7,0.03932814,0.000027547361,0.000019013469,0.33507836,0.013411069,0.34273535],"study_design_scores_gemma":[0.00043612116,0.000059901668,0.677213,0.000032399366,0.0000268152,1.3261231e-7,0.027726911,0.000012433508,0.0000011175773,0.0065425406,0.2877665,0.00018211003],"about_ca_topic_score_codex":0.004098463,"about_ca_topic_score_gemma":0.0006843808,"teacher_disagreement_score":0.41037813,"about_ca_system_score_codex":0.0013096988,"about_ca_system_score_gemma":0.0006767991,"threshold_uncertainty_score":0.99488294},"labels":[],"label_agreement":null},{"id":"W4311788816","doi":"10.3389/fpsyg.2022.1047323","title":"Chinese university students’ conceptions of feedback and the relationships with self-regulated learning, self-efficacy, and English language achievement","year":2022,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada; Queen's University","keywords":"Formative assessment; Psychology; Mathematics education; Self-efficacy; Self-regulated learning; Context (archaeology); Peer feedback; Test (biology); Curriculum; Language proficiency; English language; Pedagogy; Social psychology","score_opus":0.010369725976700606,"score_gpt":0.30234627433970623,"score_spread":0.29197654836300563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311788816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99192923,0.00034247545,0.00014158657,0.0008499897,0.00034212563,0.00042841706,0.0000036360236,0.00005688866,0.0059056696],"genre_scores_gemma":[0.997736,0.00030603734,0.0012114149,0.000042874497,0.00003391451,0.000008485419,0.000007747653,0.0000062170006,0.00064731215],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981554,0.0010850308,0.00012688895,0.00020961338,0.00025845424,0.00016458408],"domain_scores_gemma":[0.9995449,0.00014822689,0.00011420335,0.00011901905,0.000032211778,0.000041399755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00103474,0.000082825645,0.00017728098,0.00011482294,0.000688919,0.00001955586,0.0002717644,0.000053344167,0.000052388867],"category_scores_gemma":[0.00004248874,0.00006740095,0.000020974428,0.00048886397,0.00050424173,0.00007581462,0.00013603628,0.0003606149,5.297137e-7],"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":[0.00019637533,0.00024244546,0.8494269,0.0000020969433,0.00009591406,0.00000343478,0.14727393,0.000015939053,0.0000017439825,0.0013166972,0.001149324,0.00027517029],"study_design_scores_gemma":[0.0052630603,0.000121392346,0.79992425,0.0000032681826,0.000050652816,8.6138476e-7,0.17921613,0.00003490544,7.6136e-8,0.00018396685,0.01511874,0.00008267594],"about_ca_topic_score_codex":0.00013437249,"about_ca_topic_score_gemma":0.00030536664,"teacher_disagreement_score":0.049502656,"about_ca_system_score_codex":0.000070133654,"about_ca_system_score_gemma":0.000031584004,"threshold_uncertainty_score":0.52986777},"labels":[],"label_agreement":null},{"id":"W4312094293","doi":"10.1037/spq0000527","title":"Potential scoring and predictive bias in interim and summative writing assessments.","year":2022,"lang":"en","type":"article","venue":"School Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Iowa Department of Education","keywords":"Interim; Summative assessment; Rubric; Psychology; PsycINFO; Test (biology); Scale (ratio); Mathematics education; Medical education; Formative assessment; Medicine; MEDLINE; Political science","score_opus":0.0793813733520772,"score_gpt":0.44927917828844777,"score_spread":0.3698978049363706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312094293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9654967,0.00022525583,0.00020877222,0.0011910325,0.0006709421,0.0002679231,0.000008900325,0.000031503474,0.03189896],"genre_scores_gemma":[0.9986435,0.00016539652,0.00031084477,0.00034948735,0.00015806891,0.00006981349,0.0000055194187,0.000008474062,0.00028885528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984127,0.00050655793,0.00020361105,0.00033810947,0.00024612492,0.00029287406],"domain_scores_gemma":[0.9996176,0.00009070896,0.000087670596,0.000088542896,0.000025002175,0.00009047173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011111718,0.000092352675,0.0001560286,0.00016616545,0.00048085055,0.000077655975,0.00016920992,0.000051455994,0.0005080285],"category_scores_gemma":[0.00007843638,0.000104849496,0.00002174572,0.00025091905,0.00020745573,0.00023464738,0.00025802464,0.00037652042,0.000005977596],"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":[0.00011837121,0.00009240854,0.98484904,0.000004839682,0.00003467344,0.00003248347,0.0066955118,0.000006626067,0.00040905768,0.0020906688,0.0008921977,0.0047741123],"study_design_scores_gemma":[0.0011751928,0.00026900158,0.9225516,0.000017116765,0.000013183701,0.000005635533,0.07048182,0.000091683905,0.000003239372,0.0029726487,0.0022704229,0.0001484859],"about_ca_topic_score_codex":0.00025468584,"about_ca_topic_score_gemma":0.00019371531,"teacher_disagreement_score":0.06378631,"about_ca_system_score_codex":0.00010248681,"about_ca_system_score_gemma":0.00004999572,"threshold_uncertainty_score":0.5562556},"labels":[],"label_agreement":null},{"id":"W4312736783","doi":"10.1007/978-3-031-12680-2_19","title":"Assessment Brokering and Collaboration: Ghostwriter and Student Academic Literacies","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cheating; Academic integrity; Literacy; Pedagogy; Sociology; Higher education; Information literacy; Social practice; Mathematics education; Psychology; Political science; Social psychology","score_opus":0.030094312329519538,"score_gpt":0.3854652751015496,"score_spread":0.35537096277203006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312736783","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045315465,0.0028098053,0.000008525541,0.002593476,0.00054513756,0.00061603857,0.000022313425,0.00009046401,0.9887827],"genre_scores_gemma":[0.045454446,0.015635218,0.0004671661,0.00053987966,0.00057613774,0.000051264786,0.00003365095,0.0000365682,0.9372057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980172,0.000058870417,0.00031970357,0.00044249863,0.00091377203,0.0002479767],"domain_scores_gemma":[0.999298,0.000164829,0.00016461786,0.00014289116,0.00009456061,0.00013511936],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005835743,0.00025811314,0.0003199077,0.00014295474,0.0008187586,0.00049112574,0.00022928481,0.00023366153,0.004606696],"category_scores_gemma":[0.000009727171,0.00025832342,0.000047031775,0.00006719483,0.0002447265,0.00042621445,0.0004778199,0.0005382183,0.000012026096],"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":[0.0000060352554,0.000013220031,0.018979631,0.000026746562,0.00010285855,0.000013359371,0.017151387,2.894434e-7,0.000017289392,0.9557504,0.004920184,0.003018583],"study_design_scores_gemma":[0.0002606794,0.00006785785,0.014853749,0.000051750685,0.00007082647,0.0000015906865,0.010751566,0.0000031979707,6.845488e-7,0.0029008684,0.9706786,0.0003585872],"about_ca_topic_score_codex":0.000075260206,"about_ca_topic_score_gemma":0.00027892675,"teacher_disagreement_score":0.96575844,"about_ca_system_score_codex":0.00022662139,"about_ca_system_score_gemma":0.00017321185,"threshold_uncertainty_score":0.9999869},"labels":[],"label_agreement":null},{"id":"W4313145915","doi":"10.7202/1093105ar","title":"Continuous assessment for learning: issues of multiple instances of peer feedback in a university course","year":2021,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Notice; Context (archaeology); Perception; Feeling; Peer assessment; Computer science; Mathematics education; Psychology; Course (navigation); Medical education; Social psychology; Engineering; Medicine","score_opus":0.062476903974542336,"score_gpt":0.415684196118278,"score_spread":0.3532072921437357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313145915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9553478,0.0015286311,0.0028112389,0.028122546,0.0017172336,0.00073119596,0.00003474967,0.000016322703,0.009690318],"genre_scores_gemma":[0.9553828,0.00090135884,0.00601219,0.000020860798,0.00011610625,0.000009428179,0.00017224929,0.000010166663,0.03737481],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99524623,0.0030868212,0.0004032457,0.0002687989,0.0008002432,0.00019468408],"domain_scores_gemma":[0.9967804,0.0010368171,0.00048451006,0.00013378338,0.001527526,0.00003698146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008757249,0.0001261973,0.00033199083,0.00009636716,0.00011812101,0.000029298892,0.0001570264,0.00016303846,0.00038379882],"category_scores_gemma":[0.0011912725,0.00015581744,0.00011322472,0.00066215784,0.00016466108,0.00041317905,0.000033279957,0.00016102662,0.0000052732307],"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":[0.00005904221,0.0012354205,0.68334687,0.00017013372,0.00011628189,0.000001102722,0.27158543,0.001258954,0.0014391764,0.025408346,0.0034580855,0.01192117],"study_design_scores_gemma":[0.0014561665,0.000112965354,0.8101916,0.00016472157,0.0001435182,2.1321644e-7,0.1400001,0.0020452284,0.0005647123,0.00081269915,0.044359606,0.00014849669],"about_ca_topic_score_codex":0.0011831064,"about_ca_topic_score_gemma":0.0081854025,"teacher_disagreement_score":0.13158534,"about_ca_system_score_codex":0.0003682262,"about_ca_system_score_gemma":0.0019593786,"threshold_uncertainty_score":0.63540506},"labels":[],"label_agreement":null},{"id":"W4313330978","doi":"10.18357/otessac.2022.2.1.125","title":"Feedback Generation through Artificial Intelligence","year":2022,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Process (computing); Dashboard; Artificial intelligence; Learning analytics; Educational data mining; Machine learning; Data science","score_opus":0.11938183437764223,"score_gpt":0.40382248502801654,"score_spread":0.2844406506503743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313330978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8454456,0.00047926782,0.0003690423,0.14043167,0.0014206322,0.0010320358,0.000009332038,0.00009395587,0.010718494],"genre_scores_gemma":[0.99281347,0.0009538551,0.0011639196,0.001696445,0.00017900315,0.0004233902,0.00002463585,0.000008470116,0.002736792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99776936,0.000693039,0.00034127812,0.00034516677,0.0005222083,0.00032897186],"domain_scores_gemma":[0.9989479,0.00019849493,0.00032944634,0.00022712017,0.0002600937,0.000036906444],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0040797074,0.00012088522,0.00017151372,0.00006691349,0.0027953421,0.0005687618,0.0010600083,0.00021715421,0.0006515369],"category_scores_gemma":[0.0005237844,0.00012245205,0.00005197798,0.0012379874,0.0002421136,0.0008080207,0.00045775066,0.00085223565,0.000026371628],"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":[0.000008932309,0.00025103052,0.083069175,0.0000023868556,0.000030532934,1.805314e-7,0.041836794,0.000018332328,0.00068144826,0.84747124,0.003164113,0.023465842],"study_design_scores_gemma":[0.00024795625,0.00007021704,0.030648224,0.00001852578,0.000040988572,0.0000017952643,0.3688032,0.00039315614,0.00038186254,0.53117394,0.067823984,0.00039617298],"about_ca_topic_score_codex":0.0005460516,"about_ca_topic_score_gemma":0.0009400761,"teacher_disagreement_score":0.3269664,"about_ca_system_score_codex":0.0008786204,"about_ca_system_score_gemma":0.0009710024,"threshold_uncertainty_score":0.9985029},"labels":[],"label_agreement":null},{"id":"W4313343544","doi":"10.18733/cpi29666","title":"All that Glitters is not Gold: Culturally Responsive Online Assessment and Pedagogy in Uncertain Times","year":2022,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Pedagogy; Psychology","score_opus":0.5267311310912989,"score_gpt":0.5478395655922317,"score_spread":0.021108434500932804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313343544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9643075,0.0006355717,0.0000018197406,0.030642116,0.00035450148,0.00034862568,0.000044875258,0.00005403222,0.0036109504],"genre_scores_gemma":[0.9777259,0.0013674956,0.00034438295,0.0056514433,0.0003724304,0.000055313332,0.00009473562,0.000009366983,0.014378937],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99753624,0.00053186575,0.0002757752,0.0005056015,0.0006683854,0.00048212163],"domain_scores_gemma":[0.9992578,0.0002522264,0.00010677208,0.00011210025,0.000066647095,0.00020443423],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005839303,0.000234484,0.00032419382,0.000074222364,0.00061883876,0.00020918035,0.00029267202,0.00010885869,0.0013810038],"category_scores_gemma":[0.000045923523,0.00016902898,0.000084295534,0.00024147576,0.0005646267,0.000354536,0.00042419683,0.0004453557,0.0000072448943],"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":[0.0007232767,0.00062254706,0.18581735,0.000045653967,0.0001612984,0.00024530126,0.71410507,0.000030571104,0.002941392,0.029327946,0.051168624,0.014810977],"study_design_scores_gemma":[0.0009807294,0.00023237128,0.24438979,0.000016585216,0.000035902205,0.000012747858,0.48061118,0.000071686445,0.000010904639,0.0006203363,0.27260476,0.00041300626],"about_ca_topic_score_codex":0.0013428719,"about_ca_topic_score_gemma":0.00048184898,"teacher_disagreement_score":0.23349388,"about_ca_system_score_codex":0.00019246811,"about_ca_system_score_gemma":0.00011037454,"threshold_uncertainty_score":0.99953187},"labels":[],"label_agreement":null},{"id":"W4317863115","doi":"10.46747/cfp.6901e21","title":"Assessing students and residents","year":2023,"lang":"en","type":"article","venue":"Canadian Family Physician","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Institut du Savoir Montfort","funders":"","keywords":"Process (computing); Computer science; Medical education; Core (optical fiber); Data science; Medicine","score_opus":0.06430008053675226,"score_gpt":0.37810740661134773,"score_spread":0.3138073260745955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317863115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69381434,0.00007773321,9.477328e-7,0.00067004014,0.00038086745,0.00014243415,0.0000049548858,0.00008672407,0.304822],"genre_scores_gemma":[0.98529583,0.000099018005,0.000022153348,0.011186326,0.00039617845,0.000010913409,0.0000128718775,0.000017189104,0.002959544],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985711,0.00008155919,0.00010554592,0.00022699048,0.00047051127,0.00054430286],"domain_scores_gemma":[0.9993255,0.00005479212,0.00003562605,0.00012705933,0.000042620366,0.00041441666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037911176,0.00009878663,0.00012182139,0.00020944398,0.0008773561,0.00065648445,0.00032884756,0.00006111688,0.0000049002265],"category_scores_gemma":[0.000018763702,0.00011391489,0.000033944874,0.0006859198,0.00014164891,0.0004551957,0.00005332967,0.00009382745,0.00038463602],"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":[0.0000071671157,0.00007031474,0.57772744,0.00002952941,0.00017529784,0.00025402103,0.018734464,0.0000055800656,0.001589934,0.02490536,0.2669243,0.10957658],"study_design_scores_gemma":[0.00016226633,0.0000070869096,0.9033325,0.000027004759,0.000011411136,1.7355138e-8,0.026439594,0.000008090559,0.0000036653062,0.0010371044,0.06881999,0.00015131372],"about_ca_topic_score_codex":0.07588345,"about_ca_topic_score_gemma":0.07522183,"teacher_disagreement_score":0.325605,"about_ca_system_score_codex":0.00020401223,"about_ca_system_score_gemma":0.00036326319,"threshold_uncertainty_score":0.94165295},"labels":[],"label_agreement":null},{"id":"W4319439102","doi":"10.31038/ijnm.2022332","title":"Peer-to-Peer Evaluation: Kritik Pilot at Two Post- secondary Canadian Institutions","year":2022,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Winnipeg; Brandon University","funders":"","keywords":"Peer review; Peer-to-peer; Political science; Psychology; Medical education; Public relations; Computer science; Medicine; World Wide Web; Law","score_opus":0.08764148884602259,"score_gpt":0.40143378418397824,"score_spread":0.31379229533795566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319439102","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106899925,0.000048993574,0.000013010479,0.07779077,0.0013791057,0.0005729811,0.00008097875,0.0000632761,0.81315094],"genre_scores_gemma":[0.8169692,0.0000016989342,0.00039938788,0.0047506443,0.00024168307,0.0001589889,0.00013264404,0.0000069410544,0.1773388],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972824,0.00026604196,0.00015209836,0.00024354544,0.0016523189,0.00040362737],"domain_scores_gemma":[0.99871075,0.00006012052,0.000028561515,0.00016812912,0.0006491901,0.00038322463],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002359098,0.00009016057,0.00009578391,0.00018176573,0.003582031,0.00013027352,0.00038989502,0.000022630249,0.10014404],"category_scores_gemma":[0.00024434648,0.000099877,0.000049564245,0.00055128586,0.00010032031,0.00020177891,0.00018863237,0.00016534695,0.0007366108],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022505401,0.00014642092,0.020330153,0.0000021749686,0.000057121517,0.000015834172,0.03215831,0.00026373228,0.0002366447,0.20866865,0.7275083,0.010590153],"study_design_scores_gemma":[0.00042936436,0.00009462579,0.025985163,0.0000010281348,0.000020974816,0.0000016719979,0.02045523,0.00003957662,0.0000061307446,0.0003841379,0.95242023,0.00016185094],"about_ca_topic_score_codex":0.47067663,"about_ca_topic_score_gemma":0.93273765,"teacher_disagreement_score":0.7100693,"about_ca_system_score_codex":0.0017737258,"about_ca_system_score_gemma":0.003796465,"threshold_uncertainty_score":0.9977152},"labels":[],"label_agreement":null},{"id":"W4321022335","doi":"10.22329/jtl.v16i3.6976","title":"From Assessment for Learning to Assessment for Expansion: Proposing a New Paradigm of Assessment as a Sociocultural Practice","year":2022,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Formative assessment; Sociocultural evolution; Situational ethics; Process (computing); Context (archaeology); Psychology; Pedagogy; Engineering ethics; Sociology; Computer science; Social psychology; Engineering","score_opus":0.03207830599429994,"score_gpt":0.4247365324597729,"score_spread":0.39265822646547294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321022335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8564045,0.00043899036,0.102665626,0.03128899,0.0012733222,0.0013803798,0.000007126503,0.000062635016,0.006478476],"genre_scores_gemma":[0.75983375,0.0000384208,0.23652613,0.0002444503,0.0009891071,0.000048257163,0.000011991371,0.000025962017,0.0022819492],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9952861,0.0020579116,0.0007107489,0.00030763252,0.0012202736,0.00041730943],"domain_scores_gemma":[0.9953321,0.0027288294,0.0013466692,0.00009456837,0.00024098154,0.00025681342],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.009512878,0.00020395701,0.00052179105,0.00017772849,0.0037902815,0.0003590319,0.0003435557,0.000073078125,0.00010915399],"category_scores_gemma":[0.0016578353,0.00018582525,0.0002736521,0.00016430857,0.000050486367,0.00063365407,0.00017429864,0.0020436246,4.168524e-7],"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":[0.0014574234,0.0014576874,0.06825383,0.00016673596,0.0017308084,0.000047008583,0.5304022,0.033183135,0.022367273,0.0390998,0.0099519575,0.29188216],"study_design_scores_gemma":[0.0032419357,0.0042248736,0.009909613,0.00025358086,0.00048798003,0.00002741595,0.5334457,0.0030810048,0.000024953746,0.0023987093,0.44246858,0.0004356432],"about_ca_topic_score_codex":0.0015649834,"about_ca_topic_score_gemma":0.000022317683,"teacher_disagreement_score":0.43251663,"about_ca_system_score_codex":0.0006391152,"about_ca_system_score_gemma":0.0014330558,"threshold_uncertainty_score":0.9975066},"labels":[],"label_agreement":null},{"id":"W4321099595","doi":"10.5539/elt.v16n3p1","title":"To What Extent are Japanese University Students Successful in Motivating Themselves to Learn English through Project-based Language Education? An Assessment of Students after Two Years of PBL-based English Language Education","year":2023,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics education; Curriculum; Perspective (graphical); Intrinsic motivation; Language proficiency; Goal theory; Self-determination theory; Motivation to learn; Pedagogy; English language; Language acquisition; Social psychology","score_opus":0.015617169646490323,"score_gpt":0.3975462875087326,"score_spread":0.38192911786224226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321099595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937237,0.00010999442,0.000026011585,0.00006288886,0.0012184879,0.0015463394,0.000032611246,0.00028036506,0.0029996384],"genre_scores_gemma":[0.99601316,0.000011070793,0.001799542,0.00022552376,0.00073508214,0.00010465329,0.00014125451,0.000053474585,0.00091622735],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99548316,0.0011434288,0.0005128373,0.0006694376,0.0016095914,0.0005815497],"domain_scores_gemma":[0.9980431,0.00043464024,0.0003589399,0.00060049427,0.00035916292,0.00020366165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024995303,0.0003087307,0.0004977613,0.00075312104,0.00023355699,0.00041285806,0.0013177694,0.00013171603,0.000095484946],"category_scores_gemma":[0.001515201,0.0003525082,0.00014203138,0.0015625308,0.0000874387,0.0013455698,0.00033612523,0.0004890696,0.0000059473136],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040438572,0.0010879347,0.39385164,0.000045406632,0.000027348146,0.000016499089,0.59860027,0.00021973145,0.0003370232,0.000057967394,0.000082370476,0.00563337],"study_design_scores_gemma":[0.000892677,0.000097382304,0.17599922,0.0005944729,0.000036257312,3.9732303e-8,0.82160366,0.000025256542,0.00019459998,0.0000014577195,0.00025414315,0.00030081804],"about_ca_topic_score_codex":0.013622955,"about_ca_topic_score_gemma":0.0077338396,"teacher_disagreement_score":0.22300339,"about_ca_system_score_codex":0.0005730476,"about_ca_system_score_gemma":0.0007334677,"threshold_uncertainty_score":0.9998927},"labels":[],"label_agreement":null},{"id":"W4321513722","doi":"10.7202/1096356ar","title":"Revue systématique sur les pratiques évaluatives probantes en évaluation formative à l’enseignement primaire et secondaire","year":2022,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université Laval","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.25248162448681627,"score_gpt":0.42620377040582413,"score_spread":0.17372214591900786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321513722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9121508,0.007185195,0.0029431547,0.022314535,0.0027190098,0.0020031,0.000048652433,0.00013178229,0.050503794],"genre_scores_gemma":[0.9768952,0.001474774,0.012073903,0.00028335306,0.00041827813,0.0007333486,0.00007811328,0.000024417737,0.008018581],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99158835,0.005271453,0.00077408226,0.0006298018,0.0010695263,0.00066679734],"domain_scores_gemma":[0.99737257,0.0009243553,0.0008705392,0.00024193955,0.00046285262,0.00012775662],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012615563,0.00031455889,0.00038618862,0.00026824028,0.0043436065,0.0004610301,0.0007853599,0.0001455981,0.0012726701],"category_scores_gemma":[0.0011088643,0.0003464127,0.00016478359,0.0015868929,0.0015179819,0.002197952,0.0002579459,0.0004572511,0.000036762198],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010482758,0.00041319433,0.005964875,0.000526465,0.000047604055,0.0000020098353,0.80200547,0.0029117314,0.00032739388,0.16932522,0.0026926363,0.015772924],"study_design_scores_gemma":[0.0004272289,0.0012715489,0.079641595,0.001232093,0.0001779807,0.000052315976,0.8237285,0.03725149,0.00030241805,0.04715496,0.008021193,0.0007386919],"about_ca_topic_score_codex":0.0012546051,"about_ca_topic_score_gemma":0.0043361876,"teacher_disagreement_score":0.12217025,"about_ca_system_score_codex":0.0043008486,"about_ca_system_score_gemma":0.0035723706,"threshold_uncertainty_score":0.9998988},"labels":[],"label_agreement":null},{"id":"W4321600738","doi":"10.1017/s0261444823000034","title":"The ethical turn in writing assessment: How far have we come, and where do we still need to go?","year":2023,"lang":"en","type":"article","venue":"Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Impromptu; Writing assessment; Globe; German; Test (biology); Language assessment; Second language writing; Academic writing; Psychology; Pedagogy; Sociology; Linguistics; Computer science; Second language; Philosophy","score_opus":0.02481394901592722,"score_gpt":0.37919138701233135,"score_spread":0.35437743799640414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321600738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8680614,0.0019040409,0.00011006933,0.103808194,0.00027490282,0.00042664833,0.0000067577075,0.00023882822,0.025169125],"genre_scores_gemma":[0.99242383,0.0007146916,0.0006525669,0.0003321441,0.00027295086,0.000023539445,0.0000029154965,0.000019114812,0.005558273],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9978718,0.00061343936,0.000186864,0.0002667103,0.0005450058,0.00051619194],"domain_scores_gemma":[0.9985132,0.0011065074,0.000065665714,0.00017488578,0.000018992352,0.00012071864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034067528,0.00013737977,0.00018478792,0.00011281233,0.0008326645,0.000755736,0.00036601868,0.00016049891,0.000036365906],"category_scores_gemma":[0.00043541566,0.00010688467,0.000048498965,0.0003321387,0.00010183268,0.0001683929,0.00024542297,0.0011125547,0.000029572697],"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":[0.000012813631,0.000034714623,0.23493084,0.000031369404,0.000034488083,0.00010638609,0.5493307,0.000010535726,0.0011069387,0.044562407,0.0048717353,0.16496703],"study_design_scores_gemma":[0.0005457467,0.000039007675,0.06445351,0.0002458083,0.000015468613,0.0000012456458,0.78464645,0.0008096583,0.0000051913626,0.0008719228,0.14806433,0.00030167104],"about_ca_topic_score_codex":0.0014129421,"about_ca_topic_score_gemma":0.012337329,"teacher_disagreement_score":0.23531571,"about_ca_system_score_codex":0.000105538,"about_ca_system_score_gemma":0.000044113367,"threshold_uncertainty_score":0.728758},"labels":[],"label_agreement":null},{"id":"W4322486740","doi":"10.5539/elt.v16n3p23","title":"The Accuracy of Students&amp;#39; Self-Assessment-How Useful Is a Checklist in EAP Writing","year":2023,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Checklist; Psychology; Autonomy; Learner autonomy; Self-assessment; Medical education; Pedagogy; Mathematics education; Language education; Medicine","score_opus":0.02164002909992158,"score_gpt":0.3833339188698593,"score_spread":0.3616938897699377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322486740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96386814,0.00017691236,0.000016948434,0.00097114174,0.0005366222,0.00039102577,0.000007183925,0.00039029747,0.033641744],"genre_scores_gemma":[0.9947109,0.00015219339,0.000650629,0.00010534385,0.00071882346,0.000040556024,0.000014867275,0.000028688106,0.0035779949],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9968996,0.0006425203,0.00037449086,0.00032199192,0.0011234334,0.00063792896],"domain_scores_gemma":[0.9976676,0.0015862173,0.00023397886,0.00035826568,0.00006594278,0.00008797023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054618274,0.00018060723,0.00026063866,0.0001662464,0.00095845637,0.00065881584,0.0010624364,0.00010353704,0.00008419214],"category_scores_gemma":[0.0016809326,0.00015286714,0.00012567807,0.00070327113,0.00010238777,0.0005302234,0.0003545183,0.00065863866,0.00002348118],"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":[0.000004441319,0.0000917725,0.4270626,0.000016752801,0.000046065874,0.000012807877,0.5646457,0.0000018329775,0.00031000376,0.0026752586,0.0016569706,0.003475794],"study_design_scores_gemma":[0.00076940784,0.000020469604,0.13048646,0.000098367884,0.000026928159,2.3196411e-7,0.82079613,0.00005467971,0.000040074327,0.00009178307,0.04735318,0.00026227417],"about_ca_topic_score_codex":0.0016378197,"about_ca_topic_score_gemma":0.002536071,"teacher_disagreement_score":0.29657617,"about_ca_system_score_codex":0.00023653972,"about_ca_system_score_gemma":0.00013567955,"threshold_uncertainty_score":0.73717684},"labels":[],"label_agreement":null},{"id":"W4323059193","doi":"10.1007/978-3-031-18950-0_17","title":"Product to Process: The Efficacy of Hybrid Feedback in Academic Writing Classrooms for Fostering Process-Oriented Writing","year":2023,"lang":"en","type":"book-chapter","venue":"New language learning and teaching environments","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Class (philosophy); Process (computing); Writing process; Mathematics education; Product (mathematics); Computer science; Academic writing; Psychology; Peer feedback; Artificial intelligence; Mathematics","score_opus":0.031609611929217,"score_gpt":0.35311848929843126,"score_spread":0.32150887736921424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323059193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8544719,0.0011264143,0.000511432,0.0016552221,0.00042865778,0.0034271318,0.000024074443,0.00031646626,0.1380387],"genre_scores_gemma":[0.8246276,0.00020050535,0.0002955874,0.000088254725,0.00086687546,0.000056350127,0.000053319865,0.00011882731,0.17369267],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9974891,0.00011957897,0.0005424368,0.00063794147,0.00068152964,0.00052942283],"domain_scores_gemma":[0.9986867,0.0005795071,0.0004183664,0.00017251255,0.000013801868,0.00012916524],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018381346,0.000324324,0.00042414299,0.00020471986,0.00061961886,0.00008219552,0.0003864289,0.00015706122,0.000041072202],"category_scores_gemma":[0.00087692234,0.0002946846,0.00009607643,0.00006694667,0.00012746011,0.00014790574,0.00025266482,0.0014762231,0.000020022177],"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":[0.00025926533,0.00012326198,0.06723289,0.00084496517,0.00029745593,0.000050269828,0.31909928,0.00126437,0.0015216224,0.0062141437,0.00036869475,0.6027238],"study_design_scores_gemma":[0.013504914,0.0014464234,0.047153365,0.022011034,0.0011340921,0.000033643926,0.46687296,0.0011182782,0.00078783755,0.005997778,0.43374613,0.0061935387],"about_ca_topic_score_codex":0.00017402525,"about_ca_topic_score_gemma":0.00005724885,"teacher_disagreement_score":0.59653026,"about_ca_system_score_codex":0.00011898457,"about_ca_system_score_gemma":0.00006931694,"threshold_uncertainty_score":0.9999505},"labels":[],"label_agreement":null},{"id":"W4327725721","doi":"10.18162/fp.2023.785","title":"Articuler l’évaluation des stagiaires à une approche par compétences : portrait et constats tirés de l’analyse d’outils en formation initiale à l’enseignement au Québec","year":2023,"lang":"fr","type":"article","venue":"Formation et profession","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université du Québec en Outaouais","funders":"","keywords":"Valuation (finance); Humanities; Sociology; Philosophy; Economics","score_opus":0.08175911890748164,"score_gpt":0.3961486240250622,"score_spread":0.31438950511758057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327725721","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9248527,0.00020791216,0.017028278,0.028954996,0.001003256,0.0012539412,0.000035474677,0.00026427678,0.02639915],"genre_scores_gemma":[0.9915429,0.0007031808,0.002845678,0.00060243864,0.0001831628,0.00019821707,0.00062677317,0.000021659138,0.0032760138],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9949117,0.0018955785,0.00094146177,0.00028690376,0.0012136216,0.0007507846],"domain_scores_gemma":[0.9981714,0.00043921993,0.0006496719,0.00019435816,0.0003557964,0.00018955288],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0054699266,0.0002998042,0.0003243977,0.00029015107,0.0015159283,0.00022025933,0.00026858982,0.00028390676,0.00036631981],"category_scores_gemma":[0.0002693417,0.0002730586,0.00014981472,0.0013594101,0.0004477292,0.0035285025,0.00014518875,0.00034496008,0.000532825],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007839272,0.00031248748,0.013075478,0.00038989552,0.000087929315,0.0000062434715,0.8878824,0.0008597268,0.0011084134,0.008826301,0.014024484,0.073348224],"study_design_scores_gemma":[0.0014845899,0.0002644665,0.23459762,0.00105369,0.00027744414,0.0000067058913,0.6963215,0.03782412,0.0018142405,0.013957024,0.011780392,0.00061821926],"about_ca_topic_score_codex":0.01853888,"about_ca_topic_score_gemma":0.0551686,"teacher_disagreement_score":0.22152214,"about_ca_system_score_codex":0.0011444613,"about_ca_system_score_gemma":0.0018810952,"threshold_uncertainty_score":0.99997216},"labels":[],"label_agreement":null},{"id":"W4361026956","doi":"10.1016/j.jslw.2023.100993","title":"Voices from L2 learners across different languages: Development and validation of a student writing assessment literacy scale","year":2023,"lang":"en","type":"article","venue":"Journal of Second Language Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Social Science Fund of China; National Office for Philosophy and Social Sciences","keywords":"Scale (ratio); Context (archaeology); Literacy; Computer science; Reliability (semiconductor); Mathematics education; Construct (python library); Structural equation modeling; Psychology; Pedagogy","score_opus":0.025685623423356133,"score_gpt":0.4048320796905727,"score_spread":0.3791464562672166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361026956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964804,0.0007872564,0.00003973099,0.00016887205,0.00017259283,0.00012976628,0.0000142774,0.00003285177,0.0021742345],"genre_scores_gemma":[0.9969308,0.000111882466,0.0019721973,0.000055012963,0.0005101126,0.000004558743,0.000019709796,0.000015008335,0.0003807435],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.997781,0.00018590862,0.0007415148,0.00017543789,0.0007790684,0.00033707992],"domain_scores_gemma":[0.9984634,0.00050423417,0.00066618726,0.00008789624,0.00015862225,0.000119653814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018320095,0.0001412208,0.0003426253,0.00014989117,0.00035605457,0.00034854215,0.00026192277,0.000071549744,0.00032343963],"category_scores_gemma":[0.00007218906,0.0001241136,0.00009289275,0.00025336703,0.000080329126,0.000495527,0.00014517516,0.0002578137,0.000004785617],"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":[0.000013015007,0.00010284339,0.52094316,0.00008145568,0.00014169524,0.00007685306,0.42109603,0.00000837716,0.012701309,0.00006545181,0.000059244732,0.04471053],"study_design_scores_gemma":[0.00057755166,0.000036570615,0.42611668,0.0003056416,0.000025665855,0.000002231408,0.56979835,0.00001902895,0.002680056,0.000015185552,0.0003045105,0.00011855245],"about_ca_topic_score_codex":0.0001822985,"about_ca_topic_score_gemma":0.0004494365,"teacher_disagreement_score":0.1487023,"about_ca_system_score_codex":0.0001217051,"about_ca_system_score_gemma":0.00009944668,"threshold_uncertainty_score":0.50612056},"labels":[],"label_agreement":null},{"id":"W4362575713","doi":"10.22215/etd/2023-15370","title":"The Development of Students' Assessment Literacies as They Transition to University: An Exploratory Case Study","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Context (archaeology); Psychology; Reflexivity; Pedagogy; Mathematics education; Sociology; Social science","score_opus":0.04499213898590357,"score_gpt":0.4135005371911826,"score_spread":0.36850839820527903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362575713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98314637,0.000009500832,0.000020746644,0.00009138069,0.0009071472,0.0014105116,0.000004237533,0.00011472133,0.0142954085],"genre_scores_gemma":[0.9649312,0.00005196511,0.0002973823,0.000018893714,0.00009544447,0.000050787097,0.00009898981,0.000025699375,0.034429636],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99711174,0.00041944598,0.000382758,0.00036197487,0.0014369467,0.00028716403],"domain_scores_gemma":[0.9989103,0.00017466099,0.0001758489,0.00024791888,0.00034116692,0.00015011223],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0017589057,0.000217532,0.0002742248,0.0002293539,0.0017587419,0.0003026914,0.00069904444,0.0001205605,0.00008484892],"category_scores_gemma":[0.0000169543,0.00017908851,0.00008058801,0.0004781666,0.00003899898,0.00031055123,0.00006922944,0.0001717009,0.00005553773],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090759626,0.0005869358,0.0041483203,0.000016693904,0.00023947358,0.00021361206,0.9884321,0.000003337486,0.000027768527,0.0010977114,0.00014863789,0.004994665],"study_design_scores_gemma":[0.00028560954,0.00021306924,0.020153187,0.00004094575,0.00009468147,5.508864e-7,0.97576255,0.0000011703189,0.000017205517,0.000068126246,0.0031433413,0.00021955528],"about_ca_topic_score_codex":0.0031674302,"about_ca_topic_score_gemma":0.34780854,"teacher_disagreement_score":0.34464112,"about_ca_system_score_codex":0.0002974721,"about_ca_system_score_gemma":0.00084049575,"threshold_uncertainty_score":0.9995408},"labels":[],"label_agreement":null},{"id":"W4362671389","doi":"10.3389/feduc.2023.1154592","title":"Teachers’ test construction competencies in examination-oriented educational system: Exploring teachers’ multiple-choice test construction competence","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Competence (human resources); Multiple choice; Exploratory factor analysis; Psychology; Test (biology); Mathematics education; Item analysis; Psychometrics; Social psychology; Developmental psychology; Mathematics; Statistics; Significant difference","score_opus":0.032207741940133636,"score_gpt":0.30252988988147195,"score_spread":0.2703221479413383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362671389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9778076,0.0001971221,0.0004995305,0.0012160264,0.011724417,0.0008224514,0.000012430457,0.0002447799,0.007475661],"genre_scores_gemma":[0.9817701,0.00020545593,0.015370784,0.000025136831,0.000748767,0.0005011811,0.00018161151,0.000022359256,0.0011745984],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975479,0.00033698377,0.0005404153,0.00048816984,0.0006150137,0.00047147382],"domain_scores_gemma":[0.99771696,0.001445595,0.0002716678,0.00021527433,0.00023119268,0.00011933305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001164732,0.00021408123,0.00027029504,0.0009348295,0.00053062016,0.00013621378,0.00030762647,0.0001546793,0.000051316223],"category_scores_gemma":[0.0033526595,0.0002622949,0.00006706442,0.0022713144,0.00048206703,0.0011043274,0.000043921227,0.00032573714,0.000052836123],"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":[0.0000030163144,0.00024942032,0.9323246,0.000027108676,0.0000106659045,5.656038e-7,0.047241643,0.00003590119,0.00014311976,0.0041161967,0.0020715788,0.013776165],"study_design_scores_gemma":[0.00038975495,0.000016324877,0.6485885,0.00015942051,0.000013646038,0.0000018448981,0.3460614,0.00047698672,0.000014740615,0.0002336229,0.0038538028,0.00018996652],"about_ca_topic_score_codex":0.0031415762,"about_ca_topic_score_gemma":0.0022977344,"teacher_disagreement_score":0.29881978,"about_ca_system_score_codex":0.0019329492,"about_ca_system_score_gemma":0.00093505543,"threshold_uncertainty_score":0.99998295},"labels":[],"label_agreement":null},{"id":"W4365144709","doi":"10.1080/0305764x.2023.2196245","title":"Toward a Praxis-Oriented Understanding of Student Self-Assessment in STEAM Education: How Exemplary Educators Leverage Self-Assessment","year":2023,"lang":"en","type":"article","venue":"Cambridge Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Praxis; Documentation; Mathematics education; Authentic assessment; Self-assessment; Pedagogy; Metacognition; Formative assessment; Psychology; Transformative learning; Grading (engineering); Process (computing); Leverage (statistics); Engineering ethics; Engineering; Curriculum; Computer science; Political science","score_opus":0.050377013661010335,"score_gpt":0.3862939383349915,"score_spread":0.33591692467398115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365144709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.970497,0.00036970084,0.00035617358,0.008559306,0.007882728,0.00080115447,0.000004251673,0.0000673727,0.011462284],"genre_scores_gemma":[0.9943735,0.0012690669,0.0022728199,0.00013163434,0.0010910302,0.00006465925,0.000024187708,0.000029800156,0.0007433292],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962683,0.00053288165,0.0009023459,0.00031593474,0.0014921449,0.0004884217],"domain_scores_gemma":[0.9973358,0.00029437835,0.0011436054,0.0002682129,0.00066169986,0.00029629935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026995067,0.00025770624,0.0004950461,0.0010678347,0.0003355452,0.00020839155,0.0005662938,0.00014027469,0.00006446623],"category_scores_gemma":[0.000058149923,0.00026089695,0.00020868746,0.001927557,0.00010977591,0.00093766017,0.00009819195,0.00048771713,0.000007717125],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00003654542,0.005364788,0.8079331,0.00019098866,0.000309333,0.000013631827,0.070036836,0.000020457335,0.00031422233,0.053246308,0.060151163,0.0023826035],"study_design_scores_gemma":[0.0006705485,0.00019360038,0.5959945,0.00025529147,0.00010765562,0.000009285437,0.39761704,0.00001782818,0.000027984714,0.00020872688,0.00468232,0.00021528552],"about_ca_topic_score_codex":0.00020101461,"about_ca_topic_score_gemma":0.000059931186,"teacher_disagreement_score":0.32758018,"about_ca_system_score_codex":0.0054283887,"about_ca_system_score_gemma":0.016207123,"threshold_uncertainty_score":0.9999843},"labels":[],"label_agreement":null},{"id":"W4366451349","doi":"10.3138/cjpe.0022.003","title":"Teachers’ and Researchers’ Uses of Assessment and Evaluation Can Bring Reading and Writing Together","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Viewpoints; Reading (process); Value (mathematics); Writing assessment; Psychology; Mathematics education; Scale (ratio); Pedagogy; Computer science; Linguistics","score_opus":0.3373658739577437,"score_gpt":0.5040456137303412,"score_spread":0.16667973977259748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451349","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944084,0.0012566382,0.000017419929,0.001089027,0.00007286531,0.00067626504,0.0000011375872,0.00000418723,0.0024740433],"genre_scores_gemma":[0.99700403,0.00023964272,0.002545303,0.000019296787,0.0001278272,0.00001421891,0.0000021953692,0.0000074192653,0.00004005324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997858,0.00064889336,0.0002804466,0.00012076357,0.00086369144,0.00022824165],"domain_scores_gemma":[0.99857336,0.00015505728,0.00023501583,0.000053118718,0.0007088583,0.00027459426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009059384,0.00007156649,0.00014515987,0.00023075099,0.0004429129,0.00014068317,0.00007608528,0.000063928994,0.00006527927],"category_scores_gemma":[0.0005842899,0.00007213814,0.00002406049,0.00019115952,0.00033669145,0.000320657,0.00001258434,0.0001607957,1.4802193e-7],"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":[0.0000032958028,0.0000113771885,0.71177614,0.000007708783,0.000034071076,0.000003490575,0.041983306,0.0000074391346,0.00015716173,0.0002541887,0.0000791306,0.24568269],"study_design_scores_gemma":[0.00082269066,0.0001999492,0.96380156,0.00012391234,0.00012326789,0.000019136727,0.031656936,0.0017165705,0.000021415763,0.0006724509,0.0007405401,0.000101569196],"about_ca_topic_score_codex":0.011072668,"about_ca_topic_score_gemma":0.035909973,"teacher_disagreement_score":0.25202543,"about_ca_system_score_codex":0.00040914916,"about_ca_system_score_gemma":0.0021693336,"threshold_uncertainty_score":0.99551266},"labels":[],"label_agreement":null},{"id":"W4375945263","doi":"10.1177/02655322231164565","title":"Book review: Learning-Oriented Language Assessment: Putting Theory into Practice","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Linguistics; Language assessment; Mathematics education; Philosophy","score_opus":0.019022381633885147,"score_gpt":0.40005753558139345,"score_spread":0.3810351539475083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375945263","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051553193,0.2413124,0.0008275859,0.016126383,0.0012845857,0.0019518003,0.000006141919,0.006044856,0.68089306],"genre_scores_gemma":[0.3674266,0.03261786,0.09934947,0.08418486,0.008543271,0.00064058416,0.00058315153,0.0005103832,0.4061438],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970041,0.00096218893,0.00032351783,0.00036723103,0.00075189903,0.00059106416],"domain_scores_gemma":[0.9959097,0.0032442336,0.00030764696,0.00023962246,0.00017126993,0.00012753968],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048042713,0.00018106427,0.00024749327,0.00009444316,0.0009959888,0.00014685236,0.00035248772,0.000079316975,0.0011448989],"category_scores_gemma":[0.016365716,0.00017749239,0.00008156287,0.0015448191,0.00011369696,0.00058392785,0.00021346073,0.00047489116,0.00046661234],"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":[0.000023457997,0.0002356266,0.03500423,0.0009644448,0.00022621853,0.0014340692,0.39756688,0.00004937011,0.0055034324,0.010286421,0.26342678,0.28527904],"study_design_scores_gemma":[0.0005266538,0.0001001418,0.0035646013,0.0014802852,0.00019283296,0.000009004284,0.26195997,0.000806368,0.000053815933,0.00016316737,0.73059696,0.0005461754],"about_ca_topic_score_codex":0.0011308017,"about_ca_topic_score_gemma":0.000042888387,"teacher_disagreement_score":0.46717018,"about_ca_system_score_codex":0.00014270454,"about_ca_system_score_gemma":0.00015993239,"threshold_uncertainty_score":0.9997682},"labels":[],"label_agreement":null},{"id":"W4376626995","doi":"10.58379/rshg8366","title":"DIF investigations across groups of gender and academic background in a large-scale high-stakes language test ","year":2015,"lang":"en","type":"article","venue":"Studies in Language Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University","keywords":"Test (biology); Differential item functioning; Psychology; Quality (philosophy); Reliability (semiconductor); Scale (ratio); Gender bias; Social psychology; Applied psychology; Mathematics education; Medical education; Item response theory; Developmental psychology; Psychometrics; Medicine","score_opus":0.11975842518511098,"score_gpt":0.46502313377722004,"score_spread":0.34526470859210906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376626995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98636734,0.0047463197,0.00004191389,0.0004094843,0.00031117335,0.00041644325,0.0000496051,0.000040424053,0.007617312],"genre_scores_gemma":[0.9959855,0.0006659263,0.0023416774,0.00014634518,0.00018698524,0.00009009223,0.000017609813,0.00001535267,0.00055052654],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9978556,0.00023150495,0.0004398239,0.00033195756,0.0005921518,0.00054896],"domain_scores_gemma":[0.9989382,0.00047928235,0.00015973712,0.00020108743,0.00009252957,0.00012914411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019399914,0.00018653033,0.00040690522,0.00012913356,0.00018604817,0.000043658878,0.00027335633,0.00012447257,0.000032739343],"category_scores_gemma":[0.00041159475,0.00017180621,0.000039043112,0.0006056115,0.00063442386,0.00032222382,0.000325607,0.0003399829,0.0000047998424],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005623615,0.00014555367,0.5478673,0.00003936946,0.000035100787,0.000033901124,0.4467611,0.000006284921,0.00036101392,0.0041692248,0.0003469616,0.00022857585],"study_design_scores_gemma":[0.0010421908,0.000044120367,0.2873902,0.000062714134,0.00001531911,6.906183e-7,0.7103823,0.00002939225,0.000034761466,0.00067448977,0.00017270898,0.00015110451],"about_ca_topic_score_codex":0.0019053619,"about_ca_topic_score_gemma":0.018284118,"teacher_disagreement_score":0.2636212,"about_ca_system_score_codex":0.0003683697,"about_ca_system_score_gemma":0.00015696963,"threshold_uncertainty_score":0.9996296},"labels":[],"label_agreement":null},{"id":"W4378193990","doi":"10.3138/jvme-2023-0011","title":"Student Use and Perceptions of Embedded Formative Assessments in a Basic Science Veterinary Program","year":2023,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Thematic analysis; Curriculum; Preference; Process (computing); Medical education; Psychology; Mathematics education; Perception; Computer science; Qualitative research; Pedagogy; Medicine; Sociology","score_opus":0.12170649137693154,"score_gpt":0.5276690941621207,"score_spread":0.40596260278518914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378193990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973269,0.000031975876,0.000016287662,0.0007651404,0.0008472941,0.00025433462,8.507773e-7,0.000014745291,0.0007424561],"genre_scores_gemma":[0.998004,0.0005465957,0.001109575,0.000060060676,0.00014380678,0.000024398267,0.0000021698856,0.000004837861,0.000104539],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99766093,0.0002189108,0.00045520274,0.000118233635,0.0013184607,0.00022824807],"domain_scores_gemma":[0.9989464,0.00017049133,0.00027554636,0.000084594896,0.0002830169,0.00023992371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024645356,0.00007789637,0.00018629269,0.00047115533,0.00019066315,0.000098881996,0.00034104925,0.00006141333,0.00016539254],"category_scores_gemma":[0.00069320126,0.000068186164,0.000048648544,0.00097442186,0.0005472621,0.0012160912,0.00012714222,0.00020401471,0.0000059979625],"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":[0.00030764894,0.0053418716,0.5277166,0.00015158525,0.000078118894,0.0001253266,0.23102105,0.000005969883,0.0069816313,0.0012977087,0.0026540505,0.22431843],"study_design_scores_gemma":[0.00046863715,0.0016235467,0.9286726,0.00025353668,0.000013515311,0.000038527345,0.0666997,0.00013768372,0.000003698212,0.00011222062,0.0019039429,0.000072374045],"about_ca_topic_score_codex":0.00006548352,"about_ca_topic_score_gemma":0.000012610312,"teacher_disagreement_score":0.400956,"about_ca_system_score_codex":0.0001990994,"about_ca_system_score_gemma":0.0018476916,"threshold_uncertainty_score":0.32777256},"labels":[],"label_agreement":null},{"id":"W4381250449","doi":"10.5206/cjsotlrcacea.2023.1.14439","title":"Assessing the Value of Integrating Writing and Writing Instruction into a Research Methods Course","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Attendance; Context (archaeology); Mathematics education; Situated; Value (mathematics); Academic writing; Pedagogy; Psychology; Computer science; Political science","score_opus":0.1725336623282052,"score_gpt":0.5409770908104593,"score_spread":0.3684434284822541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381250449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98835576,0.0011643441,0.0006235993,0.007867648,0.000272493,0.00019391505,5.4158164e-7,0.000014793905,0.0015069207],"genre_scores_gemma":[0.9939043,0.00007672682,0.005324168,0.00003585255,0.00041447312,0.0000055874175,6.290441e-7,0.000014700978,0.00022358622],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9923502,0.0063128895,0.00032718002,0.00012742073,0.00044377975,0.00043850404],"domain_scores_gemma":[0.99155366,0.0076682153,0.0002751122,0.000106114036,0.00024973432,0.00014715608],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09526734,0.000088481596,0.00015480154,0.00019520495,0.021075785,0.00145959,0.00045625676,0.0000761899,0.000006152703],"category_scores_gemma":[0.010331365,0.00005145512,0.00007324873,0.00046547115,0.0007818791,0.00049659685,0.00006893373,0.0035330025,3.358845e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009844041,0.000004069189,0.16149308,0.000044764638,0.000105234925,0.0000021765768,0.18515691,0.00036508794,0.001292319,0.05452418,0.00006091783,0.5969414],"study_design_scores_gemma":[0.00027776687,0.00006831204,0.13004126,0.0005988035,0.00008583473,0.000030232506,0.84427834,0.004594667,0.000034804223,0.01621329,0.003661664,0.000115057635],"about_ca_topic_score_codex":0.028096065,"about_ca_topic_score_gemma":0.011952092,"teacher_disagreement_score":0.6591214,"about_ca_system_score_codex":0.000101095466,"about_ca_system_score_gemma":0.0005144536,"threshold_uncertainty_score":0.999577},"labels":[],"label_agreement":null},{"id":"W4381623794","doi":"10.1007/978-981-287-079-7_135-1","title":"An Equitable Approach to Academic Integrity Through Alternative Assessment","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Academic dishonesty; Academic integrity; Disengagement theory; Competition (biology); Cheating; Engineering ethics; Political science; Action (physics); Psychology; Test (biology); Dishonesty; Public relations; Social psychology; Engineering; Medicine","score_opus":0.1827588145916285,"score_gpt":0.45288182951778605,"score_spread":0.27012301492615753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381623794","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007946489,0.00003589351,0.0060035726,0.0010600882,0.0012195919,0.0010869707,0.000038883143,0.0004415236,0.990034],"genre_scores_gemma":[0.0062169572,0.0007216104,0.007938117,0.0007219238,0.001677961,0.00009024218,0.00010947439,0.00008626356,0.98243743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962598,0.000106162915,0.00043441428,0.00084884855,0.0015852371,0.0007655056],"domain_scores_gemma":[0.9986924,0.0001834777,0.00020582453,0.00041277506,0.0002109737,0.00029452823],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016246862,0.00041966606,0.0005444281,0.00016881074,0.00058708043,0.0002478226,0.0014069427,0.0007355608,0.0015613586],"category_scores_gemma":[0.00004035479,0.00038284194,0.00018168645,0.00016074436,0.00022877104,0.0005705649,0.00047103816,0.001737339,0.0011648784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063224356,0.000044952092,0.00020348786,0.000010261336,0.00010183438,0.0000033701738,0.007310507,0.000008217553,0.000011165559,0.96693057,0.02435976,0.0010095281],"study_design_scores_gemma":[0.00043229293,0.00025685818,0.00050847104,0.00017557557,0.00015960343,5.531779e-7,0.022008887,0.0001942425,0.000011162766,0.33309472,0.64176387,0.0013937847],"about_ca_topic_score_codex":0.0036271918,"about_ca_topic_score_gemma":0.0008826699,"teacher_disagreement_score":0.6338359,"about_ca_system_score_codex":0.00063537306,"about_ca_system_score_gemma":0.0005279339,"threshold_uncertainty_score":0.9998624},"labels":[],"label_agreement":null},{"id":"W4381740816","doi":"10.1177/02655322231179128","title":"Rethinking student placement to enhance efficiency and student agency","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Carleton University; University of Ottawa","funders":"University of Ottawa","keywords":"Agency (philosophy); Context (archaeology); Psychology; Process (computing); Test (biology); Mathematics education; Language proficiency; Pedagogy; Computer science; Sociology","score_opus":0.0478632348052326,"score_gpt":0.4160427232575863,"score_spread":0.3681794884523537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381740816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94971275,0.00021792894,0.00010595553,0.0004611493,0.0003495526,0.00048172873,0.0000013241671,0.0004371943,0.048232384],"genre_scores_gemma":[0.99389774,0.000028631172,0.002103886,0.00026293355,0.00040765005,0.0000448326,0.0000024962098,0.000015715079,0.0032360952],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9979709,0.000112308124,0.0002277678,0.00036147915,0.00081005733,0.00051751395],"domain_scores_gemma":[0.9990919,0.00045106406,0.00007926141,0.000170709,0.000058859332,0.00014820482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001602769,0.00013370036,0.00015397898,0.00011753751,0.0007081409,0.00021468925,0.00036510933,0.000045539004,0.00010700741],"category_scores_gemma":[0.00063152873,0.00013091648,0.000028559472,0.0009903419,0.000059706337,0.00010308915,0.00035580684,0.00013261393,0.00018500326],"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":[0.0000039875254,0.00008559251,0.19629578,0.000019415485,0.00002164129,0.000102335456,0.77647007,0.00007105194,0.0052997563,0.001007949,0.0004322748,0.020190174],"study_design_scores_gemma":[0.00052160694,0.00029734726,0.68828404,0.00033124315,0.00005710832,0.0000018609,0.30677745,0.0002314834,0.0004572754,0.00059230387,0.0016879351,0.00076034863],"about_ca_topic_score_codex":0.0005803019,"about_ca_topic_score_gemma":0.00046971353,"teacher_disagreement_score":0.49198827,"about_ca_system_score_codex":0.00010541179,"about_ca_system_score_gemma":0.00005064946,"threshold_uncertainty_score":0.54465187},"labels":[],"label_agreement":null},{"id":"W4381937219","doi":"10.2478/jelpp-2023-0001","title":"Culturally responsive policy development: Co-constructing assessment and reporting practices with First Nation educators in Alberta","year":2023,"lang":"en","type":"article","venue":"Journal of Educational Leadership Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Mary's University","funders":"","keywords":"Indigenous; Project commissioning; Work (physics); Publishing; Political science; Best practice; Pedagogy; Educational assessment; Sociology; Public relations; Medical education; Engineering; Medicine","score_opus":0.24300334854349917,"score_gpt":0.5005989092489506,"score_spread":0.2575955607054514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381937219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5290534,0.00011948078,0.0000019025539,0.4380827,0.00017002373,0.000154259,5.9466214e-7,0.0000059624963,0.032411683],"genre_scores_gemma":[0.9875653,0.00046927872,0.0066770217,0.0010631466,0.001672367,0.000011654695,0.000006387357,0.000011217484,0.0025236523],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9976259,0.00052057323,0.00075499475,0.00018452019,0.000603089,0.00031092268],"domain_scores_gemma":[0.9796163,0.014627144,0.0050967066,0.00006286081,0.00042967033,0.0001673394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004928334,0.00012786237,0.00020580945,0.0006871323,0.00063355773,0.00032345686,0.00013216291,0.00007946512,0.000029343748],"category_scores_gemma":[0.08114671,0.00010935639,0.000027729953,0.0010659816,0.00020926628,0.0020956346,0.000025603198,0.0003586027,0.000005491003],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038985634,0.00021737783,0.57786787,0.00010910078,0.00020882508,0.000020846572,0.28140968,0.000016108721,0.000088547364,0.13492115,0.0019648483,0.00278578],"study_design_scores_gemma":[0.00049940456,0.00007534036,0.44843245,0.00024910827,0.000047456964,0.00041117662,0.47183973,0.0000026295718,0.000014248046,0.0011021136,0.07713081,0.00019556202],"about_ca_topic_score_codex":0.0054926006,"about_ca_topic_score_gemma":0.0054409136,"teacher_disagreement_score":0.45851186,"about_ca_system_score_codex":0.00042152818,"about_ca_system_score_gemma":0.00884667,"threshold_uncertainty_score":0.9967722},"labels":[],"label_agreement":null},{"id":"W4382752350","doi":"10.3389/feduc.2023.1192754","title":"Assessment purposes and methods used by EFL teachers in secondary schools in Jordan","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Descriptive statistics; Medical education; Psychology; Mathematics education; English as a foreign language; Pedagogy; Medicine; Mathematics","score_opus":0.019255209631174445,"score_gpt":0.4148986868049889,"score_spread":0.3956434771738145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382752350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9748075,0.00070830906,0.00020223114,0.0027061158,0.0021804345,0.00053152506,0.0000021080382,0.00003560191,0.01882616],"genre_scores_gemma":[0.94657916,0.00087318884,0.046796743,0.00014980181,0.00014097891,0.00026503069,0.000059184957,0.00001730248,0.005118616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99845636,0.00054910674,0.00023383969,0.0002563566,0.00021773309,0.0002866293],"domain_scores_gemma":[0.99965405,0.00009615492,0.00006585582,0.000101768754,0.000015972222,0.000066219836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021128673,0.00009482175,0.00017968423,0.000457255,0.00009211901,0.000105660445,0.00017351015,0.00010078584,0.000051727548],"category_scores_gemma":[0.00014455852,0.00010838403,0.000020887832,0.0010141277,0.00007705919,0.00038723307,0.000034540877,0.0003145041,0.0000048597435],"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":[0.0000028866452,0.00010384559,0.8213439,0.000006562202,0.0000052022724,5.438465e-7,0.023437075,0.0000024737087,0.00011614656,0.00037691533,0.040828157,0.11377632],"study_design_scores_gemma":[0.00036339174,0.000012582148,0.7551817,0.000033297765,0.000003909133,4.589889e-8,0.21494295,0.000073287076,0.000018001963,0.0038325172,0.02541892,0.00011937329],"about_ca_topic_score_codex":0.0029368342,"about_ca_topic_score_gemma":0.0020057363,"teacher_disagreement_score":0.19150586,"about_ca_system_score_codex":0.00057781045,"about_ca_system_score_gemma":0.00069973205,"threshold_uncertainty_score":0.44396347},"labels":[],"label_agreement":null},{"id":"W4384788716","doi":"10.1007/978-3-031-33541-9_4","title":"Speaking “CEFR” about Local Tests: What Mapping a Placement Test to the CEFR Can and Can’t Do","year":2023,"lang":"en","type":"book-chapter","venue":"Educational linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Documentation; Test (biology); Computer science; Language proficiency; Language assessment; Local language; Psychology; Linguistics; Political science; Mathematics education; Natural language processing","score_opus":0.0452173759265551,"score_gpt":0.3451583806976567,"score_spread":0.2999410047711016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384788716","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017596291,0.0017982272,0.000083720355,0.0326175,0.0149296075,0.0012278307,0.00039120176,0.000113225135,0.9486627],"genre_scores_gemma":[0.08588209,0.0025235277,0.0013278296,0.0025044621,0.036322024,0.00011201728,0.00033589083,0.00013086652,0.8708613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99793833,0.000027501412,0.00034676274,0.00042172646,0.0008855234,0.00038013002],"domain_scores_gemma":[0.9972171,0.0014583619,0.00020481422,0.00024251094,0.0006644458,0.00021274299],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005766251,0.0002742619,0.00023455982,0.0001468517,0.00087662676,0.000684062,0.00042668846,0.0001627962,0.00039243206],"category_scores_gemma":[0.0031723445,0.00024867966,0.00006532094,0.000126574,0.00030746678,0.000027443604,0.00019288057,0.00033918698,0.00021040002],"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":[0.0000051014504,0.00005662216,0.0032072507,0.000050526032,0.000108144726,0.000008984006,0.043524638,0.000045414377,7.6939426e-7,0.8870397,0.06085268,0.0051001273],"study_design_scores_gemma":[0.000090797395,0.000027022032,0.0036279452,0.00061793305,0.00006711106,7.8490916e-7,0.02199692,0.000011714845,2.2651182e-7,0.01633368,0.956874,0.000351831],"about_ca_topic_score_codex":0.0012658422,"about_ca_topic_score_gemma":0.011803066,"teacher_disagreement_score":0.89602137,"about_ca_system_score_codex":0.00068043335,"about_ca_system_score_gemma":0.0016729267,"threshold_uncertainty_score":0.99999654},"labels":[],"label_agreement":null},{"id":"W4385240403","doi":"10.5430/wjel.v13n7p243","title":"Peer- and Self-Assessment in Primary School English Language Classrooms","year":2023,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Kebangsaan Malaysia","keywords":"Reading (process); English language; Peer assessment; Mathematics education; Peer feedback; Psychology; Self-assessment; Language assessment; Pedagogy; Medical education; Medicine; Linguistics","score_opus":0.009286252171380948,"score_gpt":0.3089423695732991,"score_spread":0.29965611740191817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385240403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82352394,0.0009168485,0.0000030904314,0.0006892586,0.001675071,0.00020498308,0.0000057565753,0.0001533055,0.17282772],"genre_scores_gemma":[0.98291254,0.00053150975,0.00097545696,0.0002032565,0.0031909598,0.000008217718,0.000010764149,0.000027451939,0.012139866],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9973046,0.0002740493,0.0005133896,0.00021389317,0.0011904503,0.00050359673],"domain_scores_gemma":[0.9983979,0.0003531495,0.00028479454,0.00017281446,0.0005113593,0.0002799876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031689566,0.00017880625,0.00038214508,0.00067782344,0.00017538281,0.0002580649,0.00043653863,0.00009545148,0.0005016158],"category_scores_gemma":[0.0012394589,0.00016596916,0.00012836234,0.0012693118,0.00008676182,0.0006149334,0.00013887692,0.0007062262,0.00001731624],"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":[0.000046731497,0.0003274126,0.3644846,0.000051872794,0.00012347779,0.0007604805,0.5934441,0.000014108553,0.00031501328,0.0023545662,0.031540174,0.0065374714],"study_design_scores_gemma":[0.0022532546,0.00009813284,0.32570115,0.00014832824,0.00006296224,0.0000020184386,0.5181047,0.000014782368,0.000022999153,0.00008919708,0.15316671,0.00033576583],"about_ca_topic_score_codex":0.0001880557,"about_ca_topic_score_gemma":0.0018787882,"teacher_disagreement_score":0.16068785,"about_ca_system_score_codex":0.0004433811,"about_ca_system_score_gemma":0.00039036895,"threshold_uncertainty_score":0.67680264},"labels":[],"label_agreement":null},{"id":"W4385416815","doi":"10.1080/0969594x.2023.2242004","title":"Educational assessment in Ghana: The influence of historical colonization and political accountability","year":2023,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Formative assessment; Summative assessment; Accountability; Context (archaeology); Politics; Political science; Educational assessment; Government (linguistics); Pedagogy; Sociology; Public administration; Geography; Law","score_opus":0.05672128565655436,"score_gpt":0.46713834296963386,"score_spread":0.4104170573130795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385416815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8525159,0.000063992586,0.0000075991147,0.11386093,0.00017602945,0.00045381385,0.000002222905,0.000015920346,0.0329036],"genre_scores_gemma":[0.9964124,0.00055481546,0.0010142884,0.00083041645,0.00023995875,0.00015742531,0.000016185864,0.000007011174,0.0007675307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976172,0.0008570211,0.00044047425,0.00026892612,0.0004929104,0.00032348375],"domain_scores_gemma":[0.9945495,0.0047159297,0.00023195472,0.00018071197,0.00021729586,0.00010458911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034560594,0.000110588066,0.00016418549,0.00029613698,0.00028385723,0.00011000153,0.00019860156,0.00009351248,0.00002947463],"category_scores_gemma":[0.003672015,0.00010117978,0.000020173,0.0012379269,0.00024828862,0.00082463137,0.00012231516,0.00029202702,0.000003204019],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011255331,0.00036091308,0.393255,0.000021231728,0.0000067953038,2.003859e-7,0.0077857953,0.000033155913,0.000017529534,0.5977758,0.00017398155,0.000558323],"study_design_scores_gemma":[0.00018809766,0.000028215374,0.91925967,0.000026342443,0.000016339422,0.0000019938914,0.043123953,0.000101031976,0.0000011176586,0.008023916,0.029132405,0.00009692396],"about_ca_topic_score_codex":0.024352672,"about_ca_topic_score_gemma":0.003076569,"teacher_disagreement_score":0.5897519,"about_ca_system_score_codex":0.0015360827,"about_ca_system_score_gemma":0.0045618047,"threshold_uncertainty_score":0.98214424},"labels":[],"label_agreement":null},{"id":"W4385721572","doi":"10.1080/20004508.2023.2244136","title":"Conceptions of classroom assessment and approaches to grading: teachers’ and students’ perspectives","year":2023,"lang":"en","type":"article","venue":"Education Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Grading (engineering); Psychology; Situational ethics; Mathematics education; Accountability; Pedagogy; Social psychology","score_opus":0.249927262996829,"score_gpt":0.46178672550008454,"score_spread":0.21185946250325555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385721572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870575,0.00016460485,0.00012769,0.0042828424,0.0005461384,0.00032330214,0.000001486528,0.000051779156,0.0074446267],"genre_scores_gemma":[0.9948585,0.00019523154,0.0010596617,0.000048100163,0.00036256658,0.00008299478,0.0000063895623,0.000006714546,0.0033798274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990886,0.000111456386,0.00012863944,0.00020985538,0.00031324782,0.00014822472],"domain_scores_gemma":[0.9995827,0.00010848347,0.000058516824,0.00009334054,0.000049397553,0.000107533604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056067505,0.000071106726,0.00010824228,0.00015361216,0.0002967593,0.00010032624,0.00013543363,0.000044182358,0.000061133396],"category_scores_gemma":[0.000060141545,0.0000735135,0.00002143561,0.00041110854,0.00033693103,0.00016232279,0.00007874996,0.0000693614,0.0000121890735],"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":[0.0000013216344,0.00011705041,0.5369006,0.0000047054114,0.000019132682,5.166055e-8,0.4102192,6.954838e-7,0.00006456879,0.044713058,0.0047031413,0.003256505],"study_design_scores_gemma":[0.00007207049,0.000017645096,0.53279203,0.000008754739,0.000009498486,7.821069e-8,0.46402764,0.0000023444147,0.0000026258515,0.0005168893,0.0025018621,0.000048583457],"about_ca_topic_score_codex":0.0001442773,"about_ca_topic_score_gemma":0.000048347596,"teacher_disagreement_score":0.053808432,"about_ca_system_score_codex":0.00010305536,"about_ca_system_score_gemma":0.00022603785,"threshold_uncertainty_score":0.2997794},"labels":[],"label_agreement":null},{"id":"W4385727033","doi":"10.1080/13562517.2023.2244439","title":"Applying Sadler’s principles in holistic assessment design: a retrospective account","year":2023,"lang":"en","type":"article","venue":"Teaching in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Coursework; Epistemology; Engineering ethics; Interpretation (philosophy); Higher education; Work (physics); Psychology; Sociology; Management science; Mathematics education; Pedagogy; Computer science; Engineering; Philosophy; Political science","score_opus":0.18477408254957373,"score_gpt":0.4522338658129323,"score_spread":0.26745978326335856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385727033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8923871,0.000062175786,0.00018618611,0.002576497,0.0026089924,0.0013657198,0.0000013098465,0.00024690322,0.10056514],"genre_scores_gemma":[0.98955953,0.000034229415,0.0018273945,0.00011276156,0.0004928702,0.00078082253,0.00001786887,0.000015929698,0.00715859],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99820405,0.00043302556,0.00025386098,0.00029541287,0.00046139536,0.00035224314],"domain_scores_gemma":[0.99940675,0.00025824085,0.000102552636,0.00015352272,0.000028853485,0.000050078706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026244333,0.000115210096,0.0001564788,0.00036560118,0.00031725666,0.00016447618,0.00025582805,0.00008558075,0.00015332097],"category_scores_gemma":[0.0001439591,0.00012392054,0.00002991044,0.00076440186,0.000049964154,0.00031556815,0.00005670598,0.00037932137,0.00005935437],"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":[0.0000051179645,0.00022141745,0.84205055,0.000009783263,0.0000058877476,0.0000019381553,0.023733824,0.00025358674,0.00008363921,0.13058424,0.0011395889,0.0019104262],"study_design_scores_gemma":[0.00017822362,0.000013614498,0.96768254,0.00007648205,0.000006115451,8.501803e-8,0.010753383,0.00022613088,9.521989e-7,0.0056129675,0.015303676,0.00014583833],"about_ca_topic_score_codex":0.0035735955,"about_ca_topic_score_gemma":0.0014336089,"teacher_disagreement_score":0.12563197,"about_ca_system_score_codex":0.0015815634,"about_ca_system_score_gemma":0.00045958432,"threshold_uncertainty_score":0.5402231},"labels":[],"label_agreement":null},{"id":"W4385780286","doi":"10.1016/j.ijedro.2023.100275","title":"Teachers’ beliefs and attitudes towards students’ self assessment: A latent profile analysis","year":2023,"lang":"en","type":"article","venue":"International Journal of Educational Research Open","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Lifelong learning; Psychology; Context (archaeology); Mathematics education; Self-assessment; Self-efficacy; Pedagogy; Social psychology","score_opus":0.17298423100958948,"score_gpt":0.5825242070376433,"score_spread":0.4095399760280538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385780286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8971917,0.00013364808,0.0000120440955,0.056929912,0.00080813456,0.0005049283,0.00002059288,0.000012100037,0.044386946],"genre_scores_gemma":[0.9781216,0.0010348362,0.0017997774,0.00009543074,0.0010105665,0.000057142493,0.00004058298,0.000010357295,0.0178297],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994622,0.0005215403,0.0004220115,0.00022997013,0.0038672166,0.00033725414],"domain_scores_gemma":[0.99625975,0.001097556,0.0002290446,0.00011949175,0.0020430295,0.000251129],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007676366,0.0000976086,0.00022354301,0.0010954143,0.0004916678,0.0015375867,0.0025332542,0.000061288854,0.0032975483],"category_scores_gemma":[0.0008955293,0.000086719236,0.00012800207,0.0014568863,0.00020948236,0.00087024225,0.0008789912,0.00039241338,0.000121936035],"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":[0.000031959782,0.0005916589,0.9398472,0.0000032369696,0.0019889933,0.000012383448,0.013251515,0.000013158425,0.000043303065,0.021864763,0.0207594,0.0015924859],"study_design_scores_gemma":[0.00050732715,0.00007149228,0.9719688,0.000040172294,0.00006345976,0.0000025493696,0.0047130343,0.000029089477,0.000004507492,0.002227881,0.020281928,0.0000897217],"about_ca_topic_score_codex":0.0015692298,"about_ca_topic_score_gemma":0.0005806658,"teacher_disagreement_score":0.08092991,"about_ca_system_score_codex":0.0007167241,"about_ca_system_score_gemma":0.0024272215,"threshold_uncertainty_score":0.9994989},"labels":[],"label_agreement":null},{"id":"W4385816187","doi":"10.37213/cjal.2023.32829","title":"Teachers’ Perceptions Toward Video as a Tool for Feedback on Students’ Oral Performance","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Leeds","keywords":"Perception; Quality (philosophy); Psychology; Multimedia; Peer feedback; Process (computing); Educational technology; Mathematics education; Computer science","score_opus":0.04550380798343907,"score_gpt":0.35256506685414957,"score_spread":0.3070612588707105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385816187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90947485,0.000014036079,0.000050104256,0.0006578392,0.00246987,0.00045008402,0.00002555576,0.000037507718,0.08682014],"genre_scores_gemma":[0.99337447,0.000071170514,0.0008884478,0.00040874712,0.0025272486,0.0000152414505,0.000010108083,0.000024853256,0.0026797163],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836606,0.000030362862,0.0003544264,0.00015299697,0.0005576562,0.0005384947],"domain_scores_gemma":[0.99863374,0.00018804363,0.00017697655,0.00012307007,0.00037312147,0.00050506956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012208075,0.00014184884,0.000236071,0.00030576496,0.00074732944,0.00025371058,0.0006025576,0.00013065332,0.00026384555],"category_scores_gemma":[0.0012459067,0.00014329352,0.00012304145,0.0004037997,0.00018057687,0.000032191758,0.000019295589,0.00031263573,0.00028878334],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033274322,0.00019404711,0.24867123,0.00008056135,0.00046144976,0.00015022774,0.2659248,0.0010400712,0.000083610255,0.19440356,0.2705904,0.018067293],"study_design_scores_gemma":[0.0013374245,0.00036757253,0.08359749,0.00008075877,0.00013295749,0.0000017535422,0.048320618,0.00005393283,0.000015906531,0.002863098,0.86285245,0.00037600918],"about_ca_topic_score_codex":0.000961214,"about_ca_topic_score_gemma":0.005192194,"teacher_disagreement_score":0.5922621,"about_ca_system_score_codex":0.0004048799,"about_ca_system_score_gemma":0.0015313103,"threshold_uncertainty_score":0.584334},"labels":[],"label_agreement":null},{"id":"W4386172632","doi":"10.4018/978-1-6684-8213-1.ch002","title":"Do Our Test Scores Mean What We Think?","year":2023,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Christian Studies; University of Toronto; Memorial University of Newfoundland","funders":"","keywords":"Active listening; Construct (python library); Test (biology); Construct validity; Scale (ratio); Language assessment; English language; Psychology; Writing assessment; Cognition; Computer science; Applied psychology; Mathematics education; Psychometrics; Developmental psychology; Communication; Geography; Cartography","score_opus":0.038357665505082114,"score_gpt":0.3299552900022539,"score_spread":0.29159762449717175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386172632","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044089725,0.27356926,0.00010122118,0.1045939,0.013073633,0.0028950572,0.00017876207,0.0026281446,0.60251915],"genre_scores_gemma":[0.0015147936,0.65841025,0.0078252675,0.00008376548,0.00059990375,0.0001303461,0.000044401007,0.000047743717,0.3313435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979022,0.000029460447,0.00041652215,0.0005951987,0.00069765985,0.0003589625],"domain_scores_gemma":[0.9986721,0.00056232343,0.0002797433,0.00024467937,0.0001875875,0.000053531436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032099753,0.00036932467,0.0003633546,0.00047742037,0.0006755707,0.0003646951,0.000531205,0.00047908837,0.00019118874],"category_scores_gemma":[0.00027264742,0.00036401232,0.00008482977,0.00020080192,0.0012196442,0.0038991657,0.00019584471,0.00048727306,0.000069549176],"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":[0.000022590766,0.000022710366,0.0006211443,0.000032593656,0.000031043888,0.0000034446095,0.00096089713,0.000013201124,0.0000048958946,0.92948955,0.0026157552,0.06618218],"study_design_scores_gemma":[0.00009197115,0.00006112374,0.0004252748,0.00035891263,0.000013109468,0.000008673829,0.03399303,8.309492e-7,0.000007708075,0.57653165,0.38821396,0.00029377383],"about_ca_topic_score_codex":0.000020630123,"about_ca_topic_score_gemma":0.00041591533,"teacher_disagreement_score":0.3855982,"about_ca_system_score_codex":0.00025472493,"about_ca_system_score_gemma":0.00052134506,"threshold_uncertainty_score":0.9998812},"labels":[],"label_agreement":null},{"id":"W4386301473","doi":"10.25071/1497-3170.2440","title":"Further Resources on Assignments and Assessing Student Learning","year":2004,"lang":"en","type":"article","venue":"CORE","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Computer science; Medical education; Pedagogy; Medicine","score_opus":0.05337328706321376,"score_gpt":0.39242412687652994,"score_spread":0.3390508398133162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386301473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9106778,0.00009024003,0.00003222412,0.000647268,0.00016346636,0.00010075649,1.6199667e-7,0.00005522241,0.08823286],"genre_scores_gemma":[0.99695593,0.00005025167,0.00012679795,0.00013865982,0.00020324338,0.0000050529893,8.7707224e-7,0.000008411512,0.0025107942],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99908364,0.000055384266,0.00008162117,0.00016414441,0.00041995506,0.00019523442],"domain_scores_gemma":[0.99973756,0.0000598967,0.000052800882,0.00006224389,0.000019547393,0.00006795971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030682265,0.000074192554,0.00008507733,0.000036288468,0.0005150833,0.00023404935,0.00012778188,0.000048526887,0.00010197393],"category_scores_gemma":[0.00004193348,0.00006605406,0.000023278024,0.00010023886,0.00010852779,0.00012704924,0.000050535047,0.00012678411,0.000047152895],"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":[0.000009521666,0.00011697482,0.8931345,0.000003775611,0.000027726395,0.0000146394095,0.08789315,0.00007307486,0.00047048426,0.0064225392,0.00015408672,0.0116795795],"study_design_scores_gemma":[0.00088241044,0.00012989734,0.86106575,0.000095138486,0.000020364258,3.7388082e-7,0.09776564,0.0000044695553,0.000037327547,0.0013670464,0.03842952,0.00020204927],"about_ca_topic_score_codex":0.00009992632,"about_ca_topic_score_gemma":0.00006774362,"teacher_disagreement_score":0.08627811,"about_ca_system_score_codex":0.00009111014,"about_ca_system_score_gemma":0.000030317175,"threshold_uncertainty_score":0.39616564},"labels":[],"label_agreement":null},{"id":"W4386423373","doi":"10.1080/14703297.2023.2254275","title":"The impact of a feedback intervention on university students’ second language writing feedback literacy","year":2023,"lang":"en","type":"article","venue":"Innovations in Education and Teaching International","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Universidade de Macau","keywords":"Peer feedback; Literacy; Affect (linguistics); Language proficiency; Psychology; Mathematics education; Action research; Intervention (counseling); Corrective feedback; Pedagogy","score_opus":0.019851093037725944,"score_gpt":0.4230627981079701,"score_spread":0.4032117050702442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386423373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95945364,0.000015412146,0.000027162245,0.0014075184,0.0007095703,0.00014120666,0.000011735837,0.000034537545,0.038199224],"genre_scores_gemma":[0.9855339,0.00003691044,0.00011656421,0.00003464882,0.00016737504,0.00000638228,0.00006906214,0.0000052045,0.014029935],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99903107,0.00015869398,0.00024292982,0.00013584757,0.00030225582,0.00012922041],"domain_scores_gemma":[0.99927264,0.00027585696,0.00015643911,0.00009220684,0.00017810303,0.000024738705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012907574,0.000069284055,0.00006924913,0.00042379444,0.00043315842,0.00020146738,0.00032225836,0.000038798178,0.00019151239],"category_scores_gemma":[0.00030304334,0.00006220537,0.000053666103,0.0004921908,0.0000868546,0.00033237218,0.000074047,0.00020834371,0.000025035672],"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":[0.000032366406,0.0005490942,0.6735895,0.0000064695596,0.00007455293,9.846048e-7,0.035318926,0.000020438381,0.00017003504,0.19950813,0.005885825,0.08484363],"study_design_scores_gemma":[0.0004075268,0.000026724738,0.92000693,0.00009066914,0.000003018065,5.153836e-7,0.06616658,0.00018549906,0.0000044420754,0.0007932882,0.012243541,0.000071286115],"about_ca_topic_score_codex":0.0010136295,"about_ca_topic_score_gemma":0.00026260503,"teacher_disagreement_score":0.24641736,"about_ca_system_score_codex":0.00027509886,"about_ca_system_score_gemma":0.00012495932,"threshold_uncertainty_score":0.3331548},"labels":[],"label_agreement":null},{"id":"W4386475491","doi":"10.3928/01484834-20230712-12","title":"Optimizing Student Self-Efficacy and Success on the National Registration Examination","year":2023,"lang":"en","type":"article","venue":"Journal of Nursing Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Georgian College","funders":"","keywords":"Medical education; Psychology; Medical physics; Medicine","score_opus":0.09151724207427203,"score_gpt":0.4555501671324382,"score_spread":0.36403292505816615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386475491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.923636,0.00005710249,0.000056662422,0.015547091,0.0011979036,0.0001753623,2.2061045e-7,0.000043788197,0.05928584],"genre_scores_gemma":[0.99738157,0.00014905162,0.00035691893,0.00008619166,0.0008036811,0.000003479612,0.0000019173006,0.0000070777282,0.0012101114],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99885976,0.00016259083,0.00016291677,0.00006630859,0.0006620183,0.00008639948],"domain_scores_gemma":[0.9991999,0.00023870851,0.0002643283,0.00003458805,0.00022492769,0.000037521724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016460898,0.00004576092,0.000055787506,0.00018065432,0.00033719314,0.00017161337,0.00011869821,0.000032507767,0.000013313123],"category_scores_gemma":[0.00016684119,0.000035803223,0.000020886211,0.0003347297,0.000057345933,0.00024325287,0.0000046378855,0.00008640835,0.000004542165],"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":[0.000047094607,0.0038587498,0.012813422,0.000017594171,0.00011712045,0.0000017601425,0.45737433,0.00023706732,0.0009868778,0.15647167,0.25977254,0.10830177],"study_design_scores_gemma":[0.00038211013,0.00013305566,0.8977255,0.0003361798,0.000047590762,0.0000052583073,0.092963144,0.00014077245,0.000048041806,0.0020268157,0.006085827,0.00010568728],"about_ca_topic_score_codex":0.0000109423845,"about_ca_topic_score_gemma":0.000005698117,"teacher_disagreement_score":0.8849121,"about_ca_system_score_codex":0.00025304398,"about_ca_system_score_gemma":0.00024159053,"threshold_uncertainty_score":0.2593451},"labels":[],"label_agreement":null},{"id":"W4386482646","doi":"10.1111/emip.12572","title":"Digital Module 33: Fairness in Classroom Assessment: Dimensions and Tensions","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Legitimacy; Perception; Psychology; Disengagement theory; Critical reflection; Social psychology; Pedagogy; Political science","score_opus":0.11055476844730784,"score_gpt":0.42774349726989375,"score_spread":0.3171887288225859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386482646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3753265,0.0028346744,0.000071374256,0.34057158,0.0018806208,0.0010588059,0.000030502868,0.000169603,0.27805632],"genre_scores_gemma":[0.9923266,0.0017450446,0.00075913593,0.00025001357,0.0003146202,0.00004968646,0.000025288478,0.000010213589,0.0045193895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99813956,0.00023057607,0.00019286534,0.0002794463,0.00089393073,0.00026361714],"domain_scores_gemma":[0.99834305,0.0010262298,0.00008493406,0.00010979914,0.000302262,0.00013374774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019567437,0.00011178975,0.00013009754,0.00013731551,0.0005760218,0.0003445279,0.000097349046,0.000056958725,0.000110290486],"category_scores_gemma":[0.0019162768,0.0001090962,0.000022264927,0.0004800252,0.00012242737,0.0010405605,0.00006147143,0.00014723347,0.000065389555],"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":[0.00007850265,0.0011977461,0.69323367,0.00004227895,0.00015549571,0.000014294961,0.02457322,0.00003580787,0.00064999436,0.22044367,0.04708235,0.012492997],"study_design_scores_gemma":[0.00031490525,0.0000326041,0.58683985,0.000051282885,0.000033872195,0.0000028944983,0.02771617,0.00007061109,0.0000021209025,0.005760249,0.3789951,0.00018032767],"about_ca_topic_score_codex":0.00086373993,"about_ca_topic_score_gemma":0.00051592034,"teacher_disagreement_score":0.6170001,"about_ca_system_score_codex":0.000113587055,"about_ca_system_score_gemma":0.00031283146,"threshold_uncertainty_score":0.4448814},"labels":[],"label_agreement":null},{"id":"W4386496830","doi":"10.1080/0969594x.2023.2255936","title":"Classroom assessment fairness inventory: a new instrument to support perceived fairness in classroom assessment","year":2023,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; University of Saskatchewan; University of Alberta","funders":"","keywords":"Psychology; Grading (engineering); Equity (law); Perception; Legitimacy; Diversity (politics); Pedagogy; Medical education; Sociology; Political science","score_opus":0.08886918950009094,"score_gpt":0.4589116453380946,"score_spread":0.37004245583800366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386496830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6615182,0.00004463403,0.0005469086,0.1122525,0.002284787,0.0028941017,0.000020113612,0.00028469338,0.22015405],"genre_scores_gemma":[0.9700794,0.0017173869,0.010489179,0.0033379544,0.0010471317,0.000908075,0.00018724645,0.00006838489,0.012165192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.992456,0.0019430494,0.0012559444,0.0011685333,0.0017919795,0.0013844671],"domain_scores_gemma":[0.9958108,0.0017920613,0.0006003101,0.0006774919,0.00029540906,0.0008239021],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0061838585,0.0005577894,0.000667404,0.0017188645,0.00068840757,0.00085684704,0.00087975356,0.00034176512,0.00041278847],"category_scores_gemma":[0.0014396104,0.0006220013,0.00012699983,0.0036851414,0.00019393934,0.0023422176,0.00059982366,0.0009779381,0.00014395529],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000098902754,0.0018658825,0.49710014,0.000091964954,0.000099798955,0.000028977383,0.036839876,0.00026171122,0.0002231536,0.42352745,0.0066524013,0.03320973],"study_design_scores_gemma":[0.0011724074,0.00021044635,0.59669405,0.00012598922,0.00004972657,0.000005983081,0.09425754,0.0002687263,0.0000032248902,0.0040766248,0.30260876,0.000526513],"about_ca_topic_score_codex":0.022421379,"about_ca_topic_score_gemma":0.013723578,"teacher_disagreement_score":0.41945085,"about_ca_system_score_codex":0.0040853405,"about_ca_system_score_gemma":0.016742397,"threshold_uncertainty_score":0.9997378},"labels":[],"label_agreement":null},{"id":"W4386646311","doi":"10.24918/cs.2023.35","title":"A Multi-Institutional Alternative Assessment Faculty Learning Community: Supporting Teaching in Higher Education","year":2023,"lang":"en","type":"article","venue":"CourseSource","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Missouri-St. Louis; National Science Foundation","keywords":"Higher education; Mathematics education; Pedagogy; Sociology; Medical education; Political science; Psychology; Medicine","score_opus":0.13876697072006697,"score_gpt":0.47052804912822604,"score_spread":0.33176107840815905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386646311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90146077,0.000016703103,0.0001766233,0.0023802565,0.0007488828,0.00026389453,0.0000051504608,0.0002368867,0.09471086],"genre_scores_gemma":[0.9716445,0.000009619544,0.00088437897,0.0001618916,0.00035975475,0.000047793546,0.00017787583,0.0000125825045,0.026701612],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979556,0.0007500946,0.00022375655,0.00017945634,0.0005110885,0.00037995804],"domain_scores_gemma":[0.999333,0.00026155778,0.00015301215,0.000110064466,0.00005548063,0.00008688176],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0024189441,0.00012366728,0.00015251883,0.00018913274,0.0017098964,0.00014899531,0.00033329386,0.00007049946,0.00022380907],"category_scores_gemma":[0.00024177936,0.00012347486,0.000060066133,0.0004091325,0.00014461282,0.0002652006,0.00013566733,0.0008305378,0.00008729641],"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":[0.0000060348893,0.00052865467,0.8555721,0.000014926758,0.000039088172,0.000011765072,0.096405014,0.00200794,0.0004020657,0.027638672,0.0024322919,0.014941432],"study_design_scores_gemma":[0.0005376987,0.00002520707,0.67041117,0.00009267447,0.000015028342,5.208071e-7,0.1417227,0.0021802362,0.0000035745165,0.00030320892,0.18449005,0.00021794348],"about_ca_topic_score_codex":0.0034404672,"about_ca_topic_score_gemma":0.001081594,"teacher_disagreement_score":0.18516095,"about_ca_system_score_codex":0.00040162692,"about_ca_system_score_gemma":0.0003877306,"threshold_uncertainty_score":0.99958974},"labels":[],"label_agreement":null},{"id":"W4387092961","doi":"10.7202/1106315ar","title":"(Un)making the grade: An instructor’s guide to mitigating the negative impacts of grades within a neoliberal university system","year":2023,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Autonomy; Ideology; Mathematics education; Higher education; Pedagogy; Psychology; Sociology; Political science; Politics; Engineering; Law","score_opus":0.24062593713932814,"score_gpt":0.4462539837511797,"score_spread":0.20562804661185155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387092961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98567814,0.00003434375,0.00005811001,0.004634681,0.001363179,0.0002815854,0.000012221859,0.000032682197,0.007905059],"genre_scores_gemma":[0.99072397,0.00004534865,0.008107157,0.0003571583,0.00027637492,0.0000048826337,0.0000013513771,0.000009338168,0.00047444834],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9972353,0.0011209549,0.00048920384,0.00019709952,0.0005892256,0.0003682316],"domain_scores_gemma":[0.9973475,0.00067054824,0.00089588825,0.00019031462,0.0006883152,0.0002074593],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005907128,0.0001268045,0.00018925406,0.0003581636,0.0035200026,0.00014712913,0.0011300746,0.00005834591,0.000019887711],"category_scores_gemma":[0.0012864176,0.00009186232,0.0001125171,0.0026427452,0.0007895319,0.00088884495,0.00007138194,0.00019817892,0.000005572724],"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":[0.000071421346,0.00028917377,0.03068262,0.00016518222,0.00012294053,0.000008760709,0.5433372,0.0039983285,0.0027032054,0.4079427,0.00495106,0.0057273656],"study_design_scores_gemma":[0.00022713603,0.00021720832,0.09843479,0.0006014231,0.00008752173,0.00012558249,0.88197273,0.0007848951,0.0009409036,0.009972519,0.006419738,0.00021552501],"about_ca_topic_score_codex":0.0019780206,"about_ca_topic_score_gemma":0.0012700299,"teacher_disagreement_score":0.39797017,"about_ca_system_score_codex":0.0014305693,"about_ca_system_score_gemma":0.001105005,"threshold_uncertainty_score":0.9977773},"labels":[],"label_agreement":null},{"id":"W4387127679","doi":"10.1007/s11409-023-09359-6","title":"Towards a new theory of student self-assessment: Tracing learners’ cognitive and affective processes","year":2023,"lang":"en","type":"article","venue":"Metacognition and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Cognition; Metacognition; Session (web analytics); Self-assessment; Qualitative property; Learning analytics; Cognitive psychology; Applied psychology; Mathematics education; Social psychology; Computer science; Data science; World Wide Web","score_opus":0.03971913758098297,"score_gpt":0.3714180673073345,"score_spread":0.3316989297263515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387127679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674474,0.0004066519,0.0011071371,0.00022169454,0.00007665879,0.00036057015,0.0000021169385,0.00021165491,0.030166095],"genre_scores_gemma":[0.9969379,0.0013498128,0.00026057835,0.00005076377,0.00011652282,0.000026282041,0.000012490824,0.000013680184,0.0012320111],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99826056,0.00067824725,0.00016659177,0.00022958934,0.00041908328,0.00024594995],"domain_scores_gemma":[0.9987103,0.0008448613,0.00013686965,0.000031767857,0.0001613729,0.00011484774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017661067,0.0001288486,0.00023007317,0.0001855854,0.00063334743,0.00014034128,0.000065463086,0.00006969462,0.00015056715],"category_scores_gemma":[0.00034072588,0.000121761164,0.0000436853,0.0006430356,0.00014737254,0.00030693476,0.00006789222,0.00026753359,0.000013717286],"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":[0.00009640171,0.00019867088,0.24136558,0.00024342134,0.00052752433,0.000012895673,0.5321858,0.000011425265,0.0004602227,0.008190863,0.00006120296,0.21664597],"study_design_scores_gemma":[0.0012874668,0.00021910618,0.48261684,0.0001813613,0.00030108166,0.000001257623,0.51225877,0.00004623634,0.00013594677,0.0022449393,0.0004890507,0.00021790298],"about_ca_topic_score_codex":0.00010617476,"about_ca_topic_score_gemma":0.00005826311,"teacher_disagreement_score":0.24125126,"about_ca_system_score_codex":0.000027859873,"about_ca_system_score_gemma":0.00021179163,"threshold_uncertainty_score":0.4965276},"labels":[],"label_agreement":null},{"id":"W4387429753","doi":"10.1177/02655322231202947","title":"Our validity looks like justice. Does yours?","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Economic Justice; Oppression; Psychology; Licensure; Set (abstract data type); Social psychology; Mathematics education; Pedagogy; Law; Political science; Computer science","score_opus":0.13450710571791363,"score_gpt":0.4132933080995925,"score_spread":0.2787862023816789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387429753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89666235,0.000042534888,0.00002493187,0.00083892414,0.0013660688,0.00015779288,0.000005546059,0.000987027,0.09991485],"genre_scores_gemma":[0.97990924,0.0000090632675,0.0012383129,0.00018962126,0.0016122058,0.000010182652,0.0000083954965,0.000015319325,0.017007655],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99865353,0.00010982661,0.00013187181,0.00020619419,0.00045963709,0.00043895125],"domain_scores_gemma":[0.99924207,0.00037487902,0.00007408189,0.00014682808,0.000066049484,0.0000960645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009659495,0.00009823933,0.00011867457,0.000067729314,0.0006002703,0.00015313464,0.00027854677,0.000071526,0.00011683192],"category_scores_gemma":[0.0013526478,0.00007979859,0.000047180947,0.00061866327,0.000041474017,0.00013664062,0.000107228334,0.0001505593,0.00048063803],"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":[0.000008392523,0.000090939306,0.74093914,0.000106600615,0.000044307424,0.00045663145,0.19791172,0.000022100432,0.005274525,0.0026375633,0.025422718,0.027085343],"study_design_scores_gemma":[0.000614701,0.00006505467,0.22554983,0.0001364411,0.00020208077,0.000002362614,0.7611564,0.0006111523,0.00024903382,0.0013688776,0.009372399,0.0006716757],"about_ca_topic_score_codex":0.002054527,"about_ca_topic_score_gemma":0.0009748512,"teacher_disagreement_score":0.56324464,"about_ca_system_score_codex":0.00004373112,"about_ca_system_score_gemma":0.000070377115,"threshold_uncertainty_score":0.61777896},"labels":[],"label_agreement":null},{"id":"W4387645971","doi":"10.1007/978-3-319-17461-7_23","title":"Structural Assessment of Knowledge as, of, and for Learning","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Summative assessment; Computer science; Grading (engineering); Knowledge survey; Knowledge transfer; Knowledge management; Engineering; Mathematics education; Psychology","score_opus":0.07878391421382185,"score_gpt":0.42132641150073846,"score_spread":0.3425424972869166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387645971","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021832013,0.00013353728,0.00003569023,0.00007312991,0.00029969652,0.00038740246,0.000009590387,0.000041150026,0.9968366],"genre_scores_gemma":[0.11490246,0.00035426582,0.0006561809,0.0000044073563,0.00018318594,0.000006440328,0.000018426443,0.00002191855,0.8838527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911624,0.000020581307,0.00024465658,0.0001814915,0.00029126176,0.0001457584],"domain_scores_gemma":[0.9991534,0.00034600854,0.0002197619,0.000072097275,0.00016202535,0.000046749836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039622842,0.0001272711,0.0003280588,0.000097411124,0.00015737112,0.000022243159,0.000152788,0.0001725254,0.0006235666],"category_scores_gemma":[0.000044322533,0.00011441694,0.000113523936,0.00003262832,0.0002195127,0.0000494967,0.00009379982,0.0001339035,0.000007781575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000456458,0.0000034952925,0.0032941059,0.00007440263,0.00008158535,2.6814757e-7,0.0018995282,8.1064195e-7,0.000015420595,0.98801464,0.0007020079,0.005909182],"study_design_scores_gemma":[0.0023718888,0.0012856132,0.04656856,0.0008032881,0.0006782645,7.985672e-7,0.020603048,0.00089546526,0.000048984508,0.25262982,0.67260367,0.0015105963],"about_ca_topic_score_codex":0.00020408972,"about_ca_topic_score_gemma":0.0005691047,"teacher_disagreement_score":0.7353848,"about_ca_system_score_codex":0.00003633452,"about_ca_system_score_gemma":0.00020912758,"threshold_uncertainty_score":0.6827617},"labels":[],"label_agreement":null},{"id":"W4387821100","doi":"10.1186/s40468-023-00261-1","title":"Instructional practices and students’ reading performance: a comparative study of 10 top performing regions in PISA 2018","year":2023,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Enthusiasm; Psychology; Reading (process); Multilevel model; Mathematics education; China; Sample (material); Teacher education; Pedagogy; Geography; Social psychology; Political science; Chemistry","score_opus":0.1189039487434486,"score_gpt":0.4392416959406387,"score_spread":0.3203377471971901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387821100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9801283,0.000029146879,2.665783e-7,0.000056621506,0.00009448681,0.00032880483,7.0812433e-7,0.000054479155,0.019307222],"genre_scores_gemma":[0.99840325,0.000015896532,0.00064408913,0.0000051310153,0.00007744503,0.00002700377,0.0000025615786,0.000005682444,0.00081894966],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987656,0.00013947088,0.0002451937,0.00019633671,0.00042690232,0.00022649759],"domain_scores_gemma":[0.99903995,0.000550924,0.00024366446,0.00008858718,0.000042997184,0.00003388579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011062715,0.00008586227,0.00018035315,0.0002450246,0.0002254995,0.0000631839,0.00019429532,0.000040422514,0.000041812546],"category_scores_gemma":[0.0006629465,0.00008531625,0.000011347044,0.001151276,0.000096103395,0.00034719708,0.0001140482,0.00017086469,0.00000954461],"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":[0.0000121440535,0.000116823874,0.81576747,0.000012274435,0.000008748239,0.000013494255,0.18271083,0.000027252543,0.00015912241,0.00010714851,0.000038461414,0.0010262599],"study_design_scores_gemma":[0.00045138807,0.00009097797,0.6555846,0.0000816633,0.000006686676,0.0000014344936,0.3431694,0.00047882026,0.000010644953,0.000014963482,0.00004333949,0.00006609773],"about_ca_topic_score_codex":0.003298593,"about_ca_topic_score_gemma":0.00445518,"teacher_disagreement_score":0.16045856,"about_ca_system_score_codex":0.000076135235,"about_ca_system_score_gemma":0.000058882964,"threshold_uncertainty_score":0.4986508},"labels":[],"label_agreement":null},{"id":"W4387886945","doi":"10.7202/1106853ar","title":"La planification flexible des démarches d’évaluation, un levier vers une évaluation pour apprendre ?","year":2023,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Political science; Humanities; Valuation (finance); Philosophy; Economics","score_opus":0.16570951755185664,"score_gpt":0.42937230069526217,"score_spread":0.2636627831434055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387886945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8044774,0.0022283907,0.019354828,0.09882442,0.0064466842,0.0026067805,0.00006514349,0.0007682623,0.06522812],"genre_scores_gemma":[0.9404224,0.005650473,0.0046242406,0.00019280746,0.0011265621,0.000370922,0.0023191962,0.00008427905,0.045209125],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9817632,0.013317295,0.00097362197,0.0008551974,0.002389892,0.0007007796],"domain_scores_gemma":[0.9951714,0.0024912334,0.00064801634,0.0005116126,0.0010040986,0.00017360019],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.041380852,0.00045357094,0.00040375366,0.00056911755,0.0010691644,0.0004014957,0.0004937006,0.00055794074,0.001829531],"category_scores_gemma":[0.0025994424,0.00052579853,0.00022112695,0.0038339002,0.0006226604,0.0015737946,0.00008047447,0.00045414007,0.0030550174],"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":[0.000044833683,0.00050071836,0.021626301,0.0001661444,0.00022113991,0.0000015922602,0.5757654,0.0053765783,0.0015158197,0.041359723,0.034482718,0.31893903],"study_design_scores_gemma":[0.0012063619,0.00008689767,0.8512449,0.00023389015,0.0004935716,0.0000038810113,0.05432253,0.0110253375,0.00042418324,0.031296283,0.049062252,0.00059991004],"about_ca_topic_score_codex":0.0021452187,"about_ca_topic_score_gemma":0.0020118668,"teacher_disagreement_score":0.8296186,"about_ca_system_score_codex":0.0013988446,"about_ca_system_score_gemma":0.003082386,"threshold_uncertainty_score":0.9997194},"labels":[],"label_agreement":null},{"id":"W4388945822","doi":"10.3389/feduc.2023.1270700","title":"Challenges and opportunities for classroom-based formative assessment and AI: a perspective article","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Formative assessment; Perspective (graphical); Computer science; Mathematics education; Engineering ethics; Psychology; Artificial intelligence; Engineering","score_opus":0.08248159969855182,"score_gpt":0.40453806837561695,"score_spread":0.32205646867706517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388945822","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7789204,0.0070825587,0.0043434286,0.13510467,0.0034165806,0.0019377229,0.000013766033,0.00018598976,0.06899485],"genre_scores_gemma":[0.9905671,0.0042057387,0.0037838588,0.00032167404,0.00012192543,0.0002554235,0.000010328776,0.000007091842,0.0007268942],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9993693,0.00008062852,0.000094169845,0.00014577009,0.00013665698,0.00017342277],"domain_scores_gemma":[0.9996624,0.00009068137,0.00004389932,0.000052873143,0.00009417996,0.000055978315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005136054,0.00006277323,0.00009719751,0.00016859574,0.00019689296,0.000061178835,0.00005349977,0.00004531327,0.0000049028445],"category_scores_gemma":[0.000048331498,0.00006591071,0.000016709877,0.00011448758,0.00013032752,0.0003039717,0.0000148086365,0.000054592874,7.2163306e-7],"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":[0.000043491684,0.0002552772,0.0839034,0.00005825922,0.000042234795,6.784403e-7,0.28848892,0.0000045817787,0.000014731936,0.21690801,0.04825319,0.3620272],"study_design_scores_gemma":[0.00034868656,0.000053547265,0.22121131,0.00002393752,0.000012180098,6.125186e-8,0.72763026,0.0014558331,0.000005692597,0.037340663,0.011827842,0.000089993475],"about_ca_topic_score_codex":0.000074746036,"about_ca_topic_score_gemma":0.00024540417,"teacher_disagreement_score":0.43914133,"about_ca_system_score_codex":0.00024024841,"about_ca_system_score_gemma":0.00037821618,"threshold_uncertainty_score":0.2687761},"labels":[],"label_agreement":null},{"id":"W4389063152","doi":"10.1007/978-3-031-42675-9_10","title":"Continuing Professional Development for TESOL Instructors Working in Canadian Settlement Language Training Programmes in Alberta","year":2023,"lang":"en","type":"book-chapter","venue":"Springer texts in education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading (process); Professional development; Context (archaeology); Pedagogy; Situated; Continuing professional development; Best practice; Medical education; Construct (python library); Psychology; Political science; Public relations; Medicine; Computer science; Geography","score_opus":0.03501021238634065,"score_gpt":0.3496769211331269,"score_spread":0.3146667087467862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389063152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54417396,0.0005295249,0.000002217753,0.0025112962,0.010981278,0.006347334,0.000012101313,0.00009434676,0.4353479],"genre_scores_gemma":[0.7233493,0.000039157963,0.0014541982,0.00006877974,0.0005712177,0.000685869,0.0001856971,0.000057560337,0.2735882],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816513,0.00003598243,0.00047122635,0.00038103302,0.00032713148,0.0006194831],"domain_scores_gemma":[0.9993709,0.00018534726,0.00017340611,0.00010925525,0.000039426995,0.000121711135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010643273,0.0002089124,0.00025513352,0.0008187204,0.0001405091,0.00008959696,0.00026020044,0.00024790323,0.000096216056],"category_scores_gemma":[0.00015128669,0.00023888063,0.0000445743,0.00019684032,0.000052609394,0.00009944108,0.000048281643,0.00031544472,0.000017810917],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070995025,0.000045918936,0.22229671,0.000043967146,0.0000140334905,0.000002761231,0.30325317,0.0000028567677,0.0000029836006,0.035238776,0.0002018779,0.43888986],"study_design_scores_gemma":[0.0006324928,0.000014375594,0.22632475,0.0038744407,0.000012884859,1.7916607e-7,0.07053599,0.000010333378,0.00000677539,0.003240147,0.69466245,0.0006851506],"about_ca_topic_score_codex":0.11594534,"about_ca_topic_score_gemma":0.9720429,"teacher_disagreement_score":0.8560976,"about_ca_system_score_codex":0.0016723709,"about_ca_system_score_gemma":0.0033065313,"threshold_uncertainty_score":0.974127},"labels":[],"label_agreement":null},{"id":"W4389071196","doi":"10.55016/ojs/ajer.v69i1.73115","title":"Examining School Principals' Conceptions of Assessment and Grading Practices","year":2023,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada; Queen's University","keywords":"Summative assessment; Accountability; Grading (engineering); Pedagogy; Valuation (finance); Psychology; Mathematics education; Political science; Formative assessment; Engineering","score_opus":0.3830018737737938,"score_gpt":0.5869952308588688,"score_spread":0.20399335708507504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389071196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8878515,0.00016208748,0.0000013917697,0.013078646,0.00025051893,0.000121119294,7.229205e-7,7.8795756e-7,0.09853326],"genre_scores_gemma":[0.9760067,0.0010507808,0.000469744,0.000017853865,0.0005384329,0.000010916139,0.000002539096,0.000006082852,0.021896956],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99770886,0.00046831474,0.00032668468,0.00011308925,0.0011176349,0.00026542615],"domain_scores_gemma":[0.9768451,0.021704238,0.00044818842,0.0000831199,0.00071618205,0.0002031996],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0042934166,0.000053076263,0.00013386118,0.00040665272,0.00051797775,0.00012723406,0.00030292044,0.000043076463,0.0041743377],"category_scores_gemma":[0.016338805,0.000048229103,0.000037229333,0.0008251311,0.00031580648,0.0005345067,0.000083892395,0.00032425002,0.00006575991],"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":[0.000011991857,0.000114389964,0.9175911,0.000014728687,0.00006550425,5.067103e-7,0.008520656,0.0000052930072,0.00092268706,0.063579775,0.008872842,0.0003005488],"study_design_scores_gemma":[0.00023799248,0.00012278176,0.92406553,0.0000935867,0.000020632224,0.000004005558,0.053664617,0.000022785118,0.000015753045,0.001470009,0.020221055,0.00006124565],"about_ca_topic_score_codex":0.0012597609,"about_ca_topic_score_gemma":0.0010924604,"teacher_disagreement_score":0.088155225,"about_ca_system_score_codex":0.00016203841,"about_ca_system_score_gemma":0.0022591942,"threshold_uncertainty_score":0.996736},"labels":[],"label_agreement":null},{"id":"W4389150341","doi":"10.1111/medu.15287","title":"Timing's not everything: Immediate and delayed feedback are equally beneficial for performance in formative multiple‐choice testing","year":2023,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"University of Melbourne","keywords":"Formative assessment; Psychology; Medical education; Medicine; Computer science; Mathematics education","score_opus":0.060264609286590116,"score_gpt":0.3781464413277802,"score_spread":0.3178818320411901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389150341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907428,0.000036685997,0.000060476257,0.006279228,0.00094901875,0.000433629,0.0000041094695,0.00007704448,0.0014169841],"genre_scores_gemma":[0.9972656,0.00009454503,0.0005269952,0.00083223253,0.0007184792,0.00013725286,0.000041620733,0.00001091488,0.00037237655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99848247,0.00006956682,0.00028493162,0.00020714122,0.00059065595,0.00036523066],"domain_scores_gemma":[0.997606,0.0019061277,0.00014450059,0.00006721531,0.0001459637,0.00013022208],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014203561,0.000102370606,0.00015082669,0.00013616352,0.00041776363,0.00007131634,0.00019513734,0.00013389734,0.000035408157],"category_scores_gemma":[0.011093827,0.00010075246,0.000026569172,0.0005650402,0.00010945294,0.00036714744,0.0000585692,0.00017370719,0.000026952694],"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":[0.00011801882,0.00030614372,0.6789207,0.00016957177,0.000023559915,0.0000017393611,0.13698801,0.000040563184,0.00006046361,0.00061440404,0.006699132,0.1760577],"study_design_scores_gemma":[0.00095642766,0.00007909102,0.9351023,0.00021896017,0.000016081214,5.709287e-7,0.03275819,0.022875672,0.000018441804,0.00023000747,0.0075309803,0.00021331837],"about_ca_topic_score_codex":0.0006738343,"about_ca_topic_score_gemma":0.0024783611,"teacher_disagreement_score":0.25618157,"about_ca_system_score_codex":0.00012565844,"about_ca_system_score_gemma":0.00077047857,"threshold_uncertainty_score":0.99723613},"labels":[],"label_agreement":null},{"id":"W4389312553","doi":"10.5070/w4jwa.6559","title":"Editor’s Introduction: Contract Grading, Portfolios, and Reflection","year":2023,"lang":"en","type":"article","venue":"Journal of writing assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Colorado Colorado Springs; California State University, Fresno; San Francisco State University; University of Toronto Mississauga; Fairleigh Dickinson University; University of Toronto; University of Denver; Appalachian State University; University of South Florida; University of Nevada, Reno; University of Lethbridge; Grand Valley State University; Boise State University; Elon University; University of Central Florida; Wayne State University; University of Miami; York University; Idaho State Board of Education; Montclair State University; Middle Tennessee State University; University of California, Davis; Arizona State University; Florida State University; Santa Clara University","keywords":"Grading (engineering); Watson; Reflection (computer programming); Construct (python library); Mathematics education; Engineering ethics; Sociology; Computer science; Psychology; Engineering; Programming language; Natural language processing; Civil engineering","score_opus":0.02656024756128134,"score_gpt":0.3992466048207308,"score_spread":0.3726863572594495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389312553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9309751,0.0002512414,0.00027101493,0.028091568,0.018886719,0.00020605941,0.0000015360454,0.000135972,0.021180782],"genre_scores_gemma":[0.9577304,0.000957104,0.0010364259,0.00006320123,0.038892873,0.0000030087717,0.0000019700271,0.000010315763,0.0013046713],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982807,0.0001508823,0.00042525085,0.00013131417,0.0007525305,0.00025930963],"domain_scores_gemma":[0.99894756,0.00016109935,0.00042803827,0.00006688199,0.0002715527,0.00012489148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030609085,0.000088200984,0.00020254723,0.00023312055,0.00050053996,0.00023374846,0.00012690315,0.000067194655,0.00011608544],"category_scores_gemma":[0.00016285451,0.00008287682,0.00007946478,0.0004430325,0.00008226141,0.00046153294,0.000031721698,0.00029170705,0.0000068901118],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043652086,0.00019349021,0.38303012,0.00003253537,0.00023395928,0.00010638688,0.0048453575,0.00003547643,0.0046498235,0.021340678,0.5628905,0.022598017],"study_design_scores_gemma":[0.0011926173,0.0003848876,0.40260172,0.00012228024,0.00012393246,0.00006600137,0.03633398,0.00018580582,0.000082257386,0.0017598377,0.5568622,0.0002845121],"about_ca_topic_score_codex":0.00006989268,"about_ca_topic_score_gemma":0.000029651022,"teacher_disagreement_score":0.031488623,"about_ca_system_score_codex":0.00020830851,"about_ca_system_score_gemma":0.00020001113,"threshold_uncertainty_score":0.3849799},"labels":[],"label_agreement":null},{"id":"W4389314126","doi":"10.5206/cjsotlrcacea.2023.2.14217","title":"Engagement in Assessment Change and the Role of SoTL","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Valuation (finance); Psychology; Pedagogy; Sociology; Business","score_opus":0.0955023403316147,"score_gpt":0.38207473942755693,"score_spread":0.28657239909594223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389314126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9815603,0.0017388545,0.000011488543,0.013175727,0.00020657263,0.00034748277,0.0000015556042,0.00000703137,0.0029509868],"genre_scores_gemma":[0.9988153,0.00025665516,0.00007097116,0.000088089924,0.00017388994,0.000014645371,5.6356174e-7,0.0000069556295,0.00057293114],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973932,0.0018656881,0.00016789173,0.000070042435,0.00024407836,0.00025908015],"domain_scores_gemma":[0.9980505,0.0015964522,0.00014804944,0.000074505384,0.000038485003,0.00009199735],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.027303843,0.00006270534,0.00012374975,0.000114158036,0.0047148783,0.0002445479,0.0003277558,0.000036156423,0.000015722499],"category_scores_gemma":[0.0012025293,0.000033195003,0.000055207285,0.00014523987,0.00031173704,0.00014709531,0.000037843583,0.0014757095,5.577049e-7],"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":[0.00004133285,0.00000804468,0.44970128,0.000016759384,0.00011165139,0.0000022683078,0.32118866,0.00019556539,0.00008844721,0.125756,0.00008628585,0.102803715],"study_design_scores_gemma":[0.0011878535,0.0000822237,0.6016595,0.00017379544,0.00009166053,0.0000045348097,0.30127957,0.0012482883,0.000005569652,0.016979098,0.07716572,0.00012219163],"about_ca_topic_score_codex":0.03959194,"about_ca_topic_score_gemma":0.04913035,"teacher_disagreement_score":0.1519582,"about_ca_system_score_codex":0.000058714115,"about_ca_system_score_gemma":0.0001977514,"threshold_uncertainty_score":0.99658084},"labels":[],"label_agreement":null},{"id":"W4389317357","doi":"10.1007/978-3-031-39989-3_135","title":"An Equitable Approach to Academic Integrity Through Alternative Assessment","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Academic dishonesty; Academic integrity; Disengagement theory; Competition (biology); Cheating; Psychology; Dishonesty; Action (physics); Engineering ethics; Test (biology); Political science; Public relations; Social psychology; Engineering; Medicine","score_opus":0.1827588145916285,"score_gpt":0.45288182951778605,"score_spread":0.27012301492615753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389317357","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007946489,0.00003589351,0.0060035726,0.0010600882,0.0012195919,0.0010869707,0.000038883143,0.0004415236,0.990034],"genre_scores_gemma":[0.0062169572,0.0007216104,0.007938117,0.0007219238,0.001677961,0.00009024218,0.00010947439,0.00008626356,0.98243743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962598,0.000106162915,0.00043441428,0.00084884855,0.0015852371,0.0007655056],"domain_scores_gemma":[0.9986924,0.0001834777,0.00020582453,0.00041277506,0.0002109737,0.00029452823],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016246862,0.00041966606,0.0005444281,0.00016881074,0.00058708043,0.0002478226,0.0014069427,0.0007355608,0.0015613586],"category_scores_gemma":[0.00004035479,0.00038284194,0.00018168645,0.00016074436,0.00022877104,0.0005705649,0.00047103816,0.001737339,0.0011648784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063224356,0.000044952092,0.00020348786,0.000010261336,0.00010183438,0.0000033701738,0.007310507,0.000008217553,0.000011165559,0.96693057,0.02435976,0.0010095281],"study_design_scores_gemma":[0.00043229293,0.00025685818,0.00050847104,0.00017557557,0.00015960343,5.531779e-7,0.022008887,0.0001942425,0.000011162766,0.33309472,0.64176387,0.0013937847],"about_ca_topic_score_codex":0.0036271918,"about_ca_topic_score_gemma":0.0008826699,"teacher_disagreement_score":0.6338359,"about_ca_system_score_codex":0.00063537306,"about_ca_system_score_gemma":0.0005279339,"threshold_uncertainty_score":0.9998624},"labels":[],"label_agreement":null},{"id":"W4389437665","doi":"10.1007/s13384-023-00675-z","title":"Mediating teachers’ assessment work","year":2023,"lang":"en","type":"article","venue":"The Australian Educational Researcher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Australian Research Council; University of Western Australia; Department of Education and Training, Queensland Government; Australian Catholic University","keywords":"Work (physics); Psychology; Mathematics education; Computer science; Medical education; Medicine; Engineering; Mechanical engineering","score_opus":0.20188555313891177,"score_gpt":0.5174908116563913,"score_spread":0.31560525851747956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389437665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56859636,0.0000196433,0.0000021952942,0.3031661,0.00053005957,0.00037072875,0.000004011785,0.00009278638,0.12721808],"genre_scores_gemma":[0.69596213,0.00004457302,0.00024184214,0.00010331281,0.0010392031,0.000090258145,0.000030711843,0.000009917998,0.30247802],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99743265,0.00045323084,0.00014086795,0.0001765467,0.0012611435,0.00053558394],"domain_scores_gemma":[0.99839437,0.0010757326,0.000046773894,0.00020240793,0.00011893957,0.00016177532],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038108416,0.00007730583,0.00007327622,0.000096539494,0.00087314786,0.00020740645,0.0006428814,0.000059567392,0.006502208],"category_scores_gemma":[0.0007094141,0.000058358266,0.00005662225,0.00130473,0.00036069276,0.00014983353,0.000095204305,0.0003460138,0.0018343765],"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":[0.0000051447423,0.00007640425,0.32687065,0.0000037479467,0.000046401063,0.0000013458363,0.03910953,0.000010518458,0.000107548374,0.045433696,0.5848933,0.003441694],"study_design_scores_gemma":[0.00008241625,0.000006870721,0.852999,0.000010511522,0.0000052664714,7.618907e-8,0.030342884,0.0000027917226,0.0000054566435,0.004720759,0.111748464,0.0000755422],"about_ca_topic_score_codex":0.0011167022,"about_ca_topic_score_gemma":0.00021326792,"teacher_disagreement_score":0.5261283,"about_ca_system_score_codex":0.00026367587,"about_ca_system_score_gemma":0.0008925007,"threshold_uncertainty_score":0.9989428},"labels":[],"label_agreement":null},{"id":"W4390142211","doi":"10.18733/cpi29712","title":"Designing Culturally Responsive Online Assessments for Equity-Deserving Students","year":2023,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Alberta","keywords":"Equity (law); Key (lock); Alternative assessment; Psychology; Engineering ethics; Knowledge management; Sociology; Engineering; Pedagogy; Computer science; Political science; Computer security","score_opus":0.8118352865393967,"score_gpt":0.6370228546540551,"score_spread":0.17481243188534168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390142211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99323994,0.00016932585,0.00018468896,0.0021897708,0.0007289829,0.00063039386,0.000020567866,0.0002771228,0.0025591978],"genre_scores_gemma":[0.96397,0.0011011891,0.0026647612,0.0006906644,0.0018456882,0.00010307116,0.00022176046,0.000019478119,0.029383404],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9977505,0.00021289114,0.00027939302,0.0004051867,0.00074303657,0.0006089929],"domain_scores_gemma":[0.9988567,0.00045586613,0.00010182089,0.00010327073,0.00024871298,0.00023362208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010053975,0.00020240319,0.00026830708,0.00006401636,0.0012123926,0.0005307288,0.0005279696,0.00016215412,0.00011930953],"category_scores_gemma":[0.00039019505,0.0001415418,0.00011925847,0.00042093432,0.00031389558,0.00053332705,0.0005275846,0.0001844601,0.000054358985],"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":[0.0012107007,0.0010826043,0.24007231,0.00030813122,0.00070930226,0.00015980331,0.47366175,0.0000478516,0.05406592,0.046277687,0.12606546,0.05633847],"study_design_scores_gemma":[0.0022883078,0.0005562127,0.29072243,0.0001901527,0.000138413,0.0000035028102,0.56367856,0.00013655126,0.0001458571,0.0049137403,0.13631392,0.0009123546],"about_ca_topic_score_codex":0.00009562526,"about_ca_topic_score_gemma":0.00014267337,"teacher_disagreement_score":0.09001683,"about_ca_system_score_codex":0.00008314387,"about_ca_system_score_gemma":0.00006272991,"threshold_uncertainty_score":0.9324866},"labels":[],"label_agreement":null},{"id":"W4390142485","doi":"10.18733/cpi29704","title":"CPI Special Issue: \"All That Glitters is Not Gold: Culturally Responsive Online Assessment and Pedagogy in Uncertain Times\"","year":2023,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Alberta","keywords":"Narrative; Pedagogy; Psychology; Art; Literature","score_opus":0.5297709765784591,"score_gpt":0.5571719172056213,"score_spread":0.02740094062716225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390142485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95209104,0.00019994949,0.0000010004122,0.0352398,0.00080348836,0.0004146862,0.000037479953,0.00011588397,0.011096656],"genre_scores_gemma":[0.9041445,0.0058781174,0.00043426934,0.005032,0.007280466,0.000044141547,0.00022543296,0.000022050204,0.076938994],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99734867,0.00034748012,0.00034403126,0.0006049893,0.00068940653,0.0006654009],"domain_scores_gemma":[0.99904317,0.00031882417,0.00010779725,0.0001332876,0.00010737037,0.0002895367],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006164032,0.00030199726,0.0004140404,0.0001151484,0.00037479217,0.00033533803,0.00029902963,0.00025240413,0.0015028911],"category_scores_gemma":[0.000098798424,0.00021002628,0.000103439816,0.00047775375,0.000765793,0.000489516,0.00027695176,0.00038217808,0.000119914526],"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":[0.0005525952,0.00030248257,0.08988956,0.00006907882,0.00014534614,0.00035482278,0.5758639,0.000009204327,0.0024352937,0.015876189,0.28064775,0.03385374],"study_design_scores_gemma":[0.0009392182,0.00014570786,0.32956308,0.000044445627,0.000034440665,0.0000052657483,0.26539508,0.00007391997,0.000016014777,0.0006984567,0.40265092,0.00043348307],"about_ca_topic_score_codex":0.0007432841,"about_ca_topic_score_gemma":0.00089789875,"teacher_disagreement_score":0.31046885,"about_ca_system_score_codex":0.00013698214,"about_ca_system_score_gemma":0.00010790472,"threshold_uncertainty_score":0.99940985},"labels":[],"label_agreement":null},{"id":"W4390142649","doi":"10.18733/cpi29703","title":"CPI Welcomes the Summer 2023 Special Issue “All That Glitters is Not Gold: Culturally Responsive Online Assessment and Pedagogy in Uncertain Times” with Kim Koh, Jennifer Lock, and Cecille DePass, invited Guest Editors","year":2023,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Alberta","keywords":"Lock (firearm); Pedagogy; Psychology; Sociology; Engineering; Mechanical engineering","score_opus":0.3971217374120482,"score_gpt":0.5071894733987232,"score_spread":0.11006773598667502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390142649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92372626,0.0002663983,7.6145585e-7,0.07085532,0.001752386,0.00056733645,0.00004430857,0.00007300007,0.002714201],"genre_scores_gemma":[0.89352775,0.008371174,0.00036791767,0.009854505,0.03964112,0.00012813987,0.000445179,0.000052667616,0.047611564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99714136,0.00041491108,0.00034203366,0.0006542045,0.00078758097,0.0006599338],"domain_scores_gemma":[0.99875116,0.00053790724,0.00013504723,0.00016769953,0.00012665587,0.00028153116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061666564,0.0003854919,0.00045064115,0.000100352154,0.0005737098,0.0004162826,0.00031113785,0.00025672629,0.00051565503],"category_scores_gemma":[0.00009215411,0.00020852289,0.0000741464,0.00060181186,0.00134632,0.0004921638,0.00036585276,0.00046655978,0.00003588334],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004519378,0.00013846974,0.18051104,0.000032405176,0.00014190981,0.00014971753,0.1252534,0.000008734263,0.00029121272,0.0007518838,0.6895695,0.0026998147],"study_design_scores_gemma":[0.00086033385,0.0001711742,0.3409026,0.000043188476,0.000050492832,0.000007502946,0.15547757,0.000042158204,0.000007525073,0.00009817378,0.5019779,0.00036139926],"about_ca_topic_score_codex":0.0018183199,"about_ca_topic_score_gemma":0.004202182,"teacher_disagreement_score":0.18759157,"about_ca_system_score_codex":0.00010851058,"about_ca_system_score_gemma":0.00007424508,"threshold_uncertainty_score":0.85033166},"labels":[],"label_agreement":null},{"id":"W4390224877","doi":"10.59668/279.12260","title":"Ten principles of alternative assessment","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Section (typography); Context (archaeology); Engineering ethics; Work (physics); Process (computing); Alternative assessment; Computer science; Mathematics education; Management science; Engineering; Psychology; History; Mechanical engineering","score_opus":0.10060607331262066,"score_gpt":0.3916637760829068,"score_spread":0.29105770277028614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390224877","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000072510855,0.000022300643,0.000057961774,0.00048850686,0.00069123023,0.00036285337,0.000021986682,0.00011968316,0.998163],"genre_scores_gemma":[0.0028790077,0.0008484776,0.0006606767,0.00003770596,0.000434333,0.000010671556,0.000021400552,0.000034720808,0.995073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981602,0.000029057459,0.00032018503,0.00027017703,0.001002139,0.00021828641],"domain_scores_gemma":[0.9990481,0.0002183586,0.00029681742,0.00019273556,0.00016850152,0.00007544741],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053804606,0.00018468987,0.00034098604,0.00014409197,0.00014812955,0.000046389036,0.0004617165,0.00020090837,0.0034659444],"category_scores_gemma":[0.000026265581,0.00016301498,0.00017593976,0.00004831113,0.00026679444,0.000076720215,0.00019989786,0.00019448451,0.00032654722],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021308044,0.000013072222,0.00096807175,0.00001055201,0.000147619,0.0000060110924,0.0012534651,0.0000014993878,0.0000044512885,0.99429643,0.0022191743,0.0010775045],"study_design_scores_gemma":[0.00031243867,0.000093382274,0.0042505544,0.00020676064,0.00012027118,1.2373042e-7,0.0031870035,0.000030759533,0.000015083264,0.059342932,0.9319461,0.00049458165],"about_ca_topic_score_codex":0.0007175585,"about_ca_topic_score_gemma":0.001592055,"teacher_disagreement_score":0.9349535,"about_ca_system_score_codex":0.0001478047,"about_ca_system_score_gemma":0.00029885737,"threshold_uncertainty_score":0.99744505},"labels":[],"label_agreement":null},{"id":"W4390275381","doi":"","title":"The Pedagogical Anatomy of Peer-Assessment: Dissecting a peerScholar Assignment","year":2009,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Psychology; Anatomy; Computer science; Medical education; Medicine","score_opus":0.3579369119647551,"score_gpt":0.6569333339152776,"score_spread":0.29899642195052256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390275381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88183546,0.0052573793,0.0002949191,0.0039456934,0.0010543122,0.00086024177,0.000012178724,0.00005242303,0.10668742],"genre_scores_gemma":[0.99173605,0.0049651726,0.00025761,0.00016688857,0.00039327994,0.000021886195,0.000004410289,0.000020697613,0.002434011],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9942771,0.0007636634,0.00096904347,0.00041338426,0.0029357094,0.0006410783],"domain_scores_gemma":[0.9962783,0.00092741573,0.0011155601,0.0004189992,0.0009384258,0.00032132605],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006866975,0.00029046115,0.00065872475,0.00031537272,0.0017237111,0.002696152,0.0040144958,0.00014059819,0.0043942383],"category_scores_gemma":[0.0011253936,0.00021536657,0.00031192586,0.0012256742,0.00033771672,0.0022505552,0.0005693161,0.00064369506,0.000007546832],"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":[0.00014092747,0.0006997518,0.90857714,0.000019151872,0.00025607191,0.00002626742,0.006029999,0.00002919215,0.013400192,0.011068098,0.02853723,0.031215949],"study_design_scores_gemma":[0.00056033273,0.00003498201,0.91660684,0.00015314318,0.00009560283,0.0000015206905,0.012724013,0.000023702747,0.0011785147,0.009533448,0.05874114,0.00034673317],"about_ca_topic_score_codex":0.00095893774,"about_ca_topic_score_gemma":0.00019845268,"teacher_disagreement_score":0.10990061,"about_ca_system_score_codex":0.00024856278,"about_ca_system_score_gemma":0.00039522353,"threshold_uncertainty_score":0.9995759},"labels":[],"label_agreement":null},{"id":"W4390393512","doi":"10.1016/j.chbah.2023.100040","title":"A review of assessment for learning with artificial intelligence","year":2023,"lang":"en","type":"review","venue":"Computers in Human Behavior Artificial Humans","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Scopus; Web of science; Artificial intelligence; Field (mathematics); Work (physics); Applications of artificial intelligence; Computer science; Engineering ethics; Engineering; Political science; MEDLINE","score_opus":0.27226750927799603,"score_gpt":0.506271922895003,"score_spread":0.23400441361700697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390393512","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015095573,0.9829538,0.005298186,0.00005842577,0.0015118198,0.008208286,0.000043957785,0.00030377266,0.0014708005],"genre_scores_gemma":[0.00014578493,0.99518245,0.0019544044,0.000025576559,0.00069184817,0.0014100464,0.00023294188,0.00010980896,0.00024710502],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952496,0.00062200386,0.0018377278,0.00079522893,0.0007889637,0.00070644665],"domain_scores_gemma":[0.9975499,0.00065029203,0.001004381,0.00043097796,0.0002388236,0.00012562114],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023936892,0.0005248553,0.002159167,0.0005799917,0.00079488335,0.00018220406,0.0011053679,0.00029534067,0.00016249563],"category_scores_gemma":[0.00007889474,0.0004935153,0.0006631285,0.0011300684,0.0005551526,0.00014279639,0.00019926428,0.0007311286,0.000028886328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006828664,0.0004982075,0.00013565496,0.034893434,0.00008868043,0.000036512898,0.002471736,0.000007772732,0.0000011271089,0.073598646,0.00042049077,0.8878409],"study_design_scores_gemma":[0.00016258366,0.0008977276,0.000102332604,0.274951,0.0029794236,0.000002553428,0.0037439207,0.00003345118,0.00000153026,0.0038522899,0.7114352,0.0018379951],"about_ca_topic_score_codex":0.00021188137,"about_ca_topic_score_gemma":0.0015161176,"teacher_disagreement_score":0.8860029,"about_ca_system_score_codex":0.000462492,"about_ca_system_score_gemma":0.00060801907,"threshold_uncertainty_score":0.9997516},"labels":[],"label_agreement":null},{"id":"W4390474923","doi":"10.1007/978-981-99-6199-3_7","title":"Experiential Assessment Capacity","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Experiential learning; Narrative; Experiential education; Embodied cognition; Action (physics); Psychology; Pedagogy; Experiential knowledge; Engineering ethics; Reflective practice; Capacity building; Epistemology; Political science; Engineering; Art; Philosophy","score_opus":0.06506989302560887,"score_gpt":0.3921458850700106,"score_spread":0.32707599204440174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390474923","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14114025,0.000041153162,0.00008611473,0.0017498038,0.002064498,0.00062134943,0.000005683675,0.0004137281,0.8538774],"genre_scores_gemma":[0.36017948,0.000062328574,0.00025428255,0.00016175167,0.0011282342,0.00006963483,0.00022353385,0.000044363584,0.6378764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99771726,0.00014868542,0.0005514665,0.00056730607,0.0007381651,0.00027712176],"domain_scores_gemma":[0.9982232,0.00012527288,0.0004493027,0.00027571118,0.000850889,0.00007563482],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023269702,0.00028116017,0.00029863956,0.00031836197,0.001005167,0.0003418534,0.00022570908,0.0003988632,0.0043213167],"category_scores_gemma":[0.00033963373,0.00031269417,0.00006819748,0.00035453588,0.00046564208,0.00036292168,0.000089084075,0.0008711763,0.00011599915],"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":[0.000007192021,0.00016576,0.15197943,0.00004665426,0.000045264052,1.4027523e-7,0.026016032,9.2772353e-7,0.00002401522,0.79720926,0.009302373,0.015202962],"study_design_scores_gemma":[0.00017248816,0.000024512266,0.1226967,0.00005398076,0.000043771288,3.3181257e-7,0.01759657,0.000008747948,0.0000012733299,0.019630857,0.8393295,0.0004412839],"about_ca_topic_score_codex":0.0009002665,"about_ca_topic_score_gemma":0.00037045105,"teacher_disagreement_score":0.8300271,"about_ca_system_score_codex":0.0005169322,"about_ca_system_score_gemma":0.0012345614,"threshold_uncertainty_score":0.9999325},"labels":[],"label_agreement":null},{"id":"W4390474934","doi":"10.1007/978-981-99-6199-3_1","title":"Cultivating Teacher Assessment Capacity","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Articulation (sociology); Negotiation; Argument (complex analysis); Politics; Pedagogy; Political science; Sociology; Psychology; Engineering ethics; Engineering; Social science; Medicine","score_opus":0.07216905478032726,"score_gpt":0.39311875628174436,"score_spread":0.3209497015014171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390474934","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17769386,0.00004580976,0.000059543512,0.0019278071,0.0010142446,0.000679922,0.0000046553782,0.00048418096,0.81808996],"genre_scores_gemma":[0.2672631,0.00006660976,0.0005232959,0.00018924598,0.0013126598,0.00006999628,0.00023316372,0.00006528429,0.73027664],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971544,0.00023010596,0.00072387484,0.00068844395,0.00084495515,0.0003581934],"domain_scores_gemma":[0.9976766,0.0002134231,0.0006770569,0.00031953282,0.0010253382,0.00008802029],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039967033,0.00036813083,0.00038440226,0.00036287692,0.0012559572,0.00038624147,0.00027664896,0.00050300313,0.0039424323],"category_scores_gemma":[0.00083673367,0.0003967077,0.00008163316,0.00048350057,0.0004542054,0.00045340208,0.00011113345,0.0014140069,0.00014220268],"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":[0.00000637582,0.00022379655,0.50443107,0.00008272273,0.0000710295,1.6310099e-7,0.018457972,0.000002277424,0.00004592231,0.42754692,0.0132891545,0.035842583],"study_design_scores_gemma":[0.00020675645,0.00002165376,0.33319202,0.00013871005,0.000058129444,4.2527284e-7,0.015975457,0.000021583082,0.0000011828184,0.020203738,0.6296037,0.0005766514],"about_ca_topic_score_codex":0.0016130423,"about_ca_topic_score_gemma":0.000391542,"teacher_disagreement_score":0.61631453,"about_ca_system_score_codex":0.0007761132,"about_ca_system_score_gemma":0.0012834274,"threshold_uncertainty_score":0.9998485},"labels":[],"label_agreement":null},{"id":"W4390474953","doi":"10.1007/978-981-99-6199-3_6","title":"Ethical Assessment Capacity","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Experiential learning; Pedagogy; Engineering ethics; Equity (law); Narrative; Agency (philosophy); Embodied cognition; Capacity building; Psychology; Sociology; Political science; Epistemology; Engineering; Social science","score_opus":0.07947626433589683,"score_gpt":0.4106638558035805,"score_spread":0.3311875914676837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390474953","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064279586,0.00004070623,0.00008274307,0.0080351075,0.0014310766,0.00061635853,0.000005573321,0.00045462002,0.92505425],"genre_scores_gemma":[0.27143604,0.00011238798,0.00037669085,0.0006768029,0.0012130401,0.00005613654,0.00021953754,0.000051080406,0.7258583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997493,0.00023995127,0.00057747617,0.00057023903,0.00083881867,0.00028046622],"domain_scores_gemma":[0.99791634,0.00027980833,0.00043470986,0.0002757362,0.0010100037,0.00008341829],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046098544,0.00027997367,0.0003221331,0.00030300766,0.000983763,0.00031160566,0.0002371523,0.00088434137,0.0030630894],"category_scores_gemma":[0.00076899916,0.00030348817,0.000067619876,0.0003867135,0.00055327156,0.00023256705,0.00008940624,0.0023377452,0.00017449055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043682976,0.000092461865,0.13260055,0.00004560796,0.000032491374,1.0628968e-7,0.007702473,7.703776e-7,0.000009117672,0.83703285,0.009425494,0.013053716],"study_design_scores_gemma":[0.00013075562,0.000021730139,0.21249413,0.00007162834,0.00004276775,3.328362e-7,0.005506776,0.000009788218,4.0674018e-7,0.050407242,0.73094064,0.00037376888],"about_ca_topic_score_codex":0.001062836,"about_ca_topic_score_gemma":0.00050711026,"teacher_disagreement_score":0.7866256,"about_ca_system_score_codex":0.000566716,"about_ca_system_score_gemma":0.0015919849,"threshold_uncertainty_score":0.9999639},"labels":[],"label_agreement":null},{"id":"W4390475020","doi":"10.1007/978-981-99-6199-3_3","title":"The Constellation of Assessment Capacity Discourses","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Construct (python library); Constellation; Pedagogy; Literacy; Assessment for learning; Educational assessment; Identity (music); Space (punctuation); Work (physics); Engineering ethics; Psychology; Sociology; Political science; Formative assessment; Engineering; Computer science","score_opus":0.05910327133928453,"score_gpt":0.3902570655338809,"score_spread":0.33115379419459634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390475020","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12341689,0.000113213704,0.000048524234,0.0026827122,0.0012031331,0.0006708869,0.000006379105,0.00013635188,0.8717219],"genre_scores_gemma":[0.6312119,0.00029654775,0.00010563517,0.000042666274,0.00045886615,0.000015908938,0.000096790995,0.000024819255,0.36774686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816525,0.0001691865,0.00057417067,0.00030443133,0.00060851447,0.00017843905],"domain_scores_gemma":[0.997638,0.0004828731,0.00070659205,0.00023847133,0.0008994712,0.00003462077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032523945,0.0001847147,0.00023085492,0.00015974576,0.0010596991,0.00019820212,0.000195137,0.00022246028,0.0005625562],"category_scores_gemma":[0.0003860688,0.0001568611,0.000053593016,0.00029070617,0.00087774044,0.00021791153,0.000054936943,0.00054267957,0.000017557262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055597607,0.00006286757,0.2553593,0.00003479247,0.000037727692,1.7141527e-8,0.0051109027,0.0000031726165,0.000013319194,0.71005714,0.0027268322,0.026588362],"study_design_scores_gemma":[0.00015480579,0.000030064673,0.313783,0.00011199227,0.00007231541,2.4989023e-7,0.023285486,0.000024986348,0.0000027549204,0.05276311,0.6094518,0.00031944798],"about_ca_topic_score_codex":0.0006793617,"about_ca_topic_score_gemma":0.00045041472,"teacher_disagreement_score":0.65729403,"about_ca_system_score_codex":0.0002510611,"about_ca_system_score_gemma":0.0011373048,"threshold_uncertainty_score":0.81504554},"labels":[],"label_agreement":null},{"id":"W4391027447","doi":"10.5430/wjel.v14n2p260","title":"Written Corrective Feedback in EFL Context: Contextual and Individual Factors Influencing Students’ Responses","year":2024,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Qassim University","keywords":"Corrective feedback; Context (archaeology); Psychology; Variation (astronomy); English as a foreign language; Mathematics education; Foreign language","score_opus":0.024428141494156005,"score_gpt":0.3371142447297113,"score_spread":0.3126861032355553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391027447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98416024,0.0055668843,0.0000025490333,0.00013538101,0.0017308241,0.0001815262,0.000014426871,0.000042034168,0.008166151],"genre_scores_gemma":[0.9964997,0.00014472642,0.00003786224,0.00013300996,0.0009028286,0.0000026591085,0.0000020027617,0.000017324084,0.0022598587],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9977727,0.00036172775,0.00046549074,0.00019315231,0.0008733969,0.0003335659],"domain_scores_gemma":[0.9981834,0.00115597,0.00017278668,0.00008116104,0.00024438772,0.00016228722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020120644,0.00016912956,0.00034750448,0.0006782217,0.00014970487,0.0005680805,0.0004213001,0.00007810406,0.00022021853],"category_scores_gemma":[0.001612357,0.00014303706,0.000107391556,0.0006885024,0.00021044418,0.00069452066,0.00011208623,0.00058165094,0.0000053722124],"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":[0.000093980045,0.000052181786,0.4489062,0.000009793259,0.00011385777,0.00021021946,0.54242206,8.6247263e-7,0.00006620065,0.0007065922,0.0012687534,0.0061493074],"study_design_scores_gemma":[0.000818832,0.00009681707,0.4034534,0.0003449842,0.000057591566,0.0000027790948,0.579512,0.00000102457,0.00006248152,0.0000405641,0.015444171,0.00016532236],"about_ca_topic_score_codex":0.00066844525,"about_ca_topic_score_gemma":0.0081258975,"teacher_disagreement_score":0.045452792,"about_ca_system_score_codex":0.00021597533,"about_ca_system_score_gemma":0.00021799821,"threshold_uncertainty_score":0.5832882},"labels":[],"label_agreement":null},{"id":"W4391144344","doi":"10.1002/berj.3979","title":"How hermeneutics can guide grading in integrated <scp>STEAM</scp> education: An evidence‐informed perspective","year":2024,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Summative assessment; Grading (engineering); Formative assessment; Mathematics education; Pedagogy; Psychology; Qualitative research; Engineering; Sociology","score_opus":0.1468865405520672,"score_gpt":0.5037919696087552,"score_spread":0.356905429056688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391144344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.685454,0.011284718,0.000012568664,0.10304238,0.004122023,0.00087263546,0.000020546217,0.00006336017,0.19512776],"genre_scores_gemma":[0.88698024,0.008374259,0.0006658279,0.00016253896,0.0039155656,0.00011706773,0.000024342917,0.000026847723,0.099733315],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9955676,0.00076424197,0.00035896763,0.0003896533,0.002085308,0.0008342056],"domain_scores_gemma":[0.99470556,0.0025149998,0.00007589386,0.00014204023,0.0019877483,0.0005737679],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0041079097,0.00013831547,0.00016895415,0.0007674841,0.0012967695,0.0056685153,0.00077188667,0.00012209623,0.0005523867],"category_scores_gemma":[0.012047522,0.00016016471,0.00009705805,0.0020115247,0.00048683363,0.0021695455,0.00006939415,0.0012568732,0.000038198174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000104387855,0.00078921736,0.06595242,0.00006537792,0.00011285848,0.00011717144,0.09617266,0.0000059728,0.00018090883,0.17328486,0.6016688,0.06163932],"study_design_scores_gemma":[0.00019242978,0.00010832297,0.11085046,0.0017644136,0.00001450565,0.000296201,0.54502875,0.000057690933,0.00001528132,0.049665097,0.2918684,0.00013847109],"about_ca_topic_score_codex":0.011168848,"about_ca_topic_score_gemma":0.03897381,"teacher_disagreement_score":0.4488561,"about_ca_system_score_codex":0.0047138757,"about_ca_system_score_gemma":0.028788554,"threshold_uncertainty_score":0.9991068},"labels":[],"label_agreement":null},{"id":"W4391562794","doi":"10.18260/1-2--41504","title":"Exploring Advantages of the Implementation of a Peer-Assessment Tool in a First-Year Undergraduate Course","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Experiential learning; Course (navigation); Passion; Process (computing); Computer science; Mathematics education; Medical education; Multimedia; Engineering ethics; Psychology; Engineering; Medicine","score_opus":0.06224010583132068,"score_gpt":0.4188568108375629,"score_spread":0.3566167050062422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391562794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97802544,0.000040334082,0.00009098198,0.009140186,0.00042763082,0.00033840182,0.0000061148894,0.000027339,0.011903557],"genre_scores_gemma":[0.9981509,0.00029434107,0.0003783191,0.000011579973,0.00004157207,0.000037033096,0.000001607015,0.000005586944,0.001079082],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988468,0.00006810052,0.0002268847,0.00011798563,0.0005887846,0.0001514081],"domain_scores_gemma":[0.9996567,0.000121021294,0.000055084867,0.000098072946,0.000055324967,0.000013832046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006357907,0.00006048279,0.000103393744,0.000058768826,0.00008141043,0.000041520347,0.00017406029,0.000017951977,0.00028233268],"category_scores_gemma":[0.000013717405,0.00004369849,0.00006754829,0.00041228932,0.000074727635,0.00031661984,0.00006303241,0.00006608993,0.0000040511227],"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":[0.0000046591317,0.000079308,0.65043896,0.000056477867,0.000044055327,0.0000015828133,0.02131241,0.000013832551,0.00037420765,0.3238702,0.0009477486,0.0028565458],"study_design_scores_gemma":[0.0005058443,0.00006199349,0.7453316,0.00013227657,0.0000461892,1.2039328e-7,0.24265616,0.000072638846,0.001136318,0.0041641844,0.0057698404,0.00012286406],"about_ca_topic_score_codex":0.0024653992,"about_ca_topic_score_gemma":0.011533454,"teacher_disagreement_score":0.31970602,"about_ca_system_score_codex":0.00009209614,"about_ca_system_score_gemma":0.00020453698,"threshold_uncertainty_score":0.64359385},"labels":[],"label_agreement":null},{"id":"W4391603175","doi":"10.18260/1-2--42438","title":"Board 128: An Automated Management Process for Digital Correction","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Upload; Grading (engineering); Python (programming language); Pace; Process (computing); Multimedia; World Wide Web; Operating system; Engineering","score_opus":0.029052146222369585,"score_gpt":0.40511158577998435,"score_spread":0.3760594395576148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391603175","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13476895,0.000037677357,0.003848116,0.0009070799,0.0038953996,0.0009264221,0.0000052816613,0.003533064,0.852078],"genre_scores_gemma":[0.93524796,0.000011328022,0.00015951667,0.000044750195,0.00023252325,0.00006756911,0.000016946777,0.000008581708,0.064210825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999323,0.000010027192,0.00008427726,0.00017797832,0.00022861037,0.00017610512],"domain_scores_gemma":[0.99981594,0.000032372896,0.000012230301,0.000051513452,0.00003796437,0.00005000325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015774374,0.000059628204,0.000054888096,0.000055356526,0.00020671201,0.0006121609,0.000118998876,0.00003508542,0.00018514226],"category_scores_gemma":[0.000008902808,0.000051449777,0.00003901127,0.00023793346,0.000035703837,0.00062645506,0.000015027261,0.000027681692,0.00009645611],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010200769,0.00059416116,0.018102856,0.0003568471,0.0003951208,0.000026325597,0.04740933,0.00008113121,0.000057862213,0.21503137,0.43192142,0.28592154],"study_design_scores_gemma":[0.00071887014,0.0003464924,0.01361828,0.00012702876,0.0001291229,9.1823847e-7,0.12644593,0.09260022,0.00013887904,0.0071728956,0.75803953,0.0006618281],"about_ca_topic_score_codex":0.00006789734,"about_ca_topic_score_gemma":0.00018685817,"teacher_disagreement_score":0.800479,"about_ca_system_score_codex":0.000057600686,"about_ca_system_score_gemma":0.000033484204,"threshold_uncertainty_score":0.5903081},"labels":[],"label_agreement":null},{"id":"W4391606049","doi":"10.18260/1-2--44480","title":"The Role of Feedback in Enhancing Students’ Learning Experience: An Evaluation of Student Perspectives and Attitudes","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Mathematics education; Knowledge management; Human–computer interaction; Psychology; Multimedia; Pedagogy","score_opus":0.03956692107570287,"score_gpt":0.44224854324523777,"score_spread":0.4026816221695349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391606049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9817869,0.00435642,0.000008093037,0.000063054584,0.00009916965,0.00030033907,1.7159712e-7,0.00002226821,0.013363587],"genre_scores_gemma":[0.99878216,0.00069428806,0.00004601938,0.000001835833,0.000054474185,0.00002859284,3.612594e-7,0.0000051880106,0.0003870729],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9978285,0.0003595749,0.00022846332,0.0002004741,0.0012237488,0.00015923334],"domain_scores_gemma":[0.9994309,0.00023044038,0.000057487003,0.00008282174,0.00016521594,0.000033162003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032779684,0.00007097741,0.00012011,0.00007629875,0.00022903006,0.00018866039,0.00025791,0.000036504654,0.00014525629],"category_scores_gemma":[0.00010678679,0.000051508334,0.00003036696,0.00028940794,0.00026117364,0.0003167836,0.00009132834,0.00009838389,0.000001971353],"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":[0.000005306768,0.00008429859,0.5667834,0.000004852357,0.000023073746,1.6989632e-7,0.415045,0.000021840238,0.0018691296,0.009481952,0.0000011645204,0.006679782],"study_design_scores_gemma":[0.000111018795,0.00004203907,0.4573863,0.00003296072,0.000013668318,4.5500446e-8,0.5413515,0.00024321204,0.00038864138,0.00028865007,0.000101589554,0.000040365234],"about_ca_topic_score_codex":0.00089853606,"about_ca_topic_score_gemma":0.004807119,"teacher_disagreement_score":0.12630649,"about_ca_system_score_codex":0.000111418696,"about_ca_system_score_gemma":0.00009914079,"threshold_uncertainty_score":0.26824853},"labels":[],"label_agreement":null},{"id":"W4391731495","doi":"10.1016/j.tate.2024.104518","title":"Evidence of teacher assessment work and its relationship to their assessment identity","year":2024,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Australian Research Council; University of Western Australia; Department of Education and Training, Queensland Government; Australian Catholic University","keywords":"Identity (music); Psychology; Work (physics); Pedagogy; Mathematics education; Social psychology; Engineering; Philosophy; Aesthetics","score_opus":0.09114490559044283,"score_gpt":0.4525132888131091,"score_spread":0.3613683832226663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391731495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96380055,0.0037905169,0.0010664852,0.008904476,0.0006307235,0.00042089482,0.0000010478046,0.000115507246,0.021269828],"genre_scores_gemma":[0.98902863,0.00015380452,0.0022020156,0.00008789853,0.0003827284,0.00006199743,0.000005078616,0.000015481557,0.008062338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980709,0.0007062689,0.0002575842,0.0003473275,0.00040717164,0.00021074532],"domain_scores_gemma":[0.9990462,0.000514848,0.000077354685,0.00015545158,0.00006068384,0.00014548449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041115265,0.00014250328,0.0001644689,0.00017774968,0.0005822184,0.0004021241,0.00017556269,0.00009423719,0.00012283893],"category_scores_gemma":[0.00037484342,0.00012922242,0.00004568989,0.0003362682,0.00006822232,0.0009180116,0.00008664792,0.00055926683,0.00000946019],"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":[0.0000073616734,0.0002820712,0.6216629,0.00009827359,0.000041416046,3.5579052e-7,0.070980415,0.0000020406126,0.00032647842,0.22573492,0.0025770047,0.078286745],"study_design_scores_gemma":[0.000066735774,0.000048768627,0.9711759,0.00057309924,0.00006636546,6.3136326e-7,0.016099382,0.00008716182,0.0000052245173,0.0031390286,0.008554916,0.0001828065],"about_ca_topic_score_codex":0.0010587042,"about_ca_topic_score_gemma":0.00018286661,"teacher_disagreement_score":0.34951296,"about_ca_system_score_codex":0.00024493388,"about_ca_system_score_gemma":0.00046725347,"threshold_uncertainty_score":0.52695376},"labels":[],"label_agreement":null},{"id":"W4391905991","doi":"10.55016/ojs/ajer.v46i3.54818","title":"Changing Assessment Practices in the Classroom: A Study of One Teacher's Challenge","year":2000,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Mathematics education; Pedagogy","score_opus":0.24058453480634495,"score_gpt":0.5385362550330982,"score_spread":0.29795172022675326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391905991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.707316,0.00019994171,1.1352385e-7,0.02714411,0.000065255714,0.00028143774,1.5330099e-7,2.0161895e-7,0.2649928],"genre_scores_gemma":[0.9815971,0.00057516526,0.00006200795,0.000033956054,0.00068773195,0.000030202928,8.2547115e-7,0.000005981012,0.017006997],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953491,0.0017043422,0.00041252392,0.00013039274,0.0020451767,0.00035844202],"domain_scores_gemma":[0.9862181,0.012772196,0.0003683871,0.00015727556,0.00040506353,0.000079008154],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0081906635,0.00006841362,0.00016861118,0.0003991017,0.00040421638,0.00011288483,0.00082217285,0.000046472353,0.014423336],"category_scores_gemma":[0.0029826046,0.000050760238,0.000054382544,0.000956858,0.00014689504,0.00044076203,0.000039054306,0.00061305735,0.000043459255],"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":[0.00015482264,0.015571361,0.6165395,0.000019709512,0.00020906272,0.000002959322,0.332003,0.000015982896,0.00003614724,0.026453173,0.0032245037,0.0057697934],"study_design_scores_gemma":[0.00084696343,0.0008884006,0.5118548,0.00008695155,0.00003767145,0.0000035570088,0.46295172,0.0000135592845,0.0000016118452,0.0012352285,0.021987734,0.00009179643],"about_ca_topic_score_codex":0.00620073,"about_ca_topic_score_gemma":0.01704891,"teacher_disagreement_score":0.27428114,"about_ca_system_score_codex":0.00019942921,"about_ca_system_score_gemma":0.001192251,"threshold_uncertainty_score":0.9864776},"labels":[],"label_agreement":null},{"id":"W4392378798","doi":"10.1002/sfr.32356","title":"Expand Your Reach Through Nontraditional Methods","year":2024,"lang":"en","type":"article","venue":"Successful Fundraising","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Computer science","score_opus":0.1027487616261196,"score_gpt":0.4767338591528656,"score_spread":0.373985097526746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392378798","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08444591,0.0042940504,0.04891514,0.0051674847,0.0052020373,0.00031815152,0.000017889173,0.00063459406,0.8510047],"genre_scores_gemma":[0.96216214,0.00024346253,0.02699943,0.00026202554,0.0025387623,0.000020920883,0.00002501013,0.000032502176,0.0077157267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998054,0.00029533074,0.00023867624,0.00038380583,0.00057221367,0.0004559542],"domain_scores_gemma":[0.9990961,0.00054664776,0.00004458992,0.00014872832,0.00006479645,0.00009912247],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012235699,0.0001523634,0.00018414296,0.000096726064,0.0007735109,0.00090322504,0.0003171058,0.000112986534,0.0018087281],"category_scores_gemma":[0.000107477965,0.00014723108,0.00013498451,0.0005616857,0.00023315288,0.0011455745,0.00005708356,0.00023330598,0.0001857729],"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":[0.00003084198,0.00013801985,0.013497217,0.00010523644,0.0002601572,0.00012705698,0.08501375,0.000013602015,0.0035980619,0.77578527,0.024665292,0.0967655],"study_design_scores_gemma":[0.00029501063,0.000039184684,0.007138132,0.00019587917,0.00009016386,0.000008554309,0.016079998,0.00023449911,0.00045959497,0.07285981,0.9021051,0.0004940513],"about_ca_topic_score_codex":0.0010394625,"about_ca_topic_score_gemma":0.00020970863,"teacher_disagreement_score":0.87771624,"about_ca_system_score_codex":0.00016322668,"about_ca_system_score_gemma":0.00025022618,"threshold_uncertainty_score":0.9991037},"labels":[],"label_agreement":null},{"id":"W4392426567","doi":"10.58680/la201424590","title":"Commentaries: Common Core, Rotten Core","year":2014,"lang":"en","type":"article","venue":"Language Arts","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Core (optical fiber); Common core; Psychology; Mathematics education; Pedagogy; Sociology; Computer science","score_opus":0.04165454797447994,"score_gpt":0.36865748933656556,"score_spread":0.32700294136208563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392426567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6902768,0.00008646586,0.000052848463,0.0022753917,0.00040631194,0.0001942006,0.000004029278,0.00013625289,0.3065677],"genre_scores_gemma":[0.99003834,0.000011916825,0.0002861697,0.003755975,0.00046740336,0.000011604543,0.000028459444,0.0000103505145,0.0053897696],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906623,0.00005839008,0.0001230407,0.00014603039,0.0003198108,0.00028647625],"domain_scores_gemma":[0.9993793,0.00023505044,0.00005842714,0.0002046539,0.00002374232,0.00009887668],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038636144,0.00009008588,0.00014094012,0.000031706397,0.00039494698,0.00009052358,0.00027312653,0.000053819538,0.0013353028],"category_scores_gemma":[0.000085688094,0.00008305383,0.00004925872,0.00012178681,0.00014774941,0.00012130986,0.000069784866,0.000093750765,0.000273397],"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":[0.000025443589,0.0001608564,0.530056,0.000011457088,0.00004749141,0.000031659747,0.18409288,0.0000016533791,0.0005619627,0.11708808,0.14824489,0.019677646],"study_design_scores_gemma":[0.0008739079,0.000092293805,0.06132566,0.000030900534,0.00003546931,0.0000010994077,0.057754025,0.00009127586,0.00013980057,0.0028382996,0.8764777,0.0003395373],"about_ca_topic_score_codex":0.004344537,"about_ca_topic_score_gemma":0.010146938,"teacher_disagreement_score":0.72823286,"about_ca_system_score_codex":0.000046854966,"about_ca_system_score_gemma":0.000017921948,"threshold_uncertainty_score":0.99957764},"labels":[],"label_agreement":null},{"id":"W4392681814","doi":"10.22318/icls2023.105241","title":"Social Context Challenges in Administering Authentic Assessments of Citizenship Competency","year":2023,"lang":"en","type":"article","venue":"Proceedings.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Island University","funders":"","keywords":"Citizenship; Situated; Context (archaeology); Dimension (graph theory); Competency assessment; Vocational education; Pedagogy; Authentic assessment; Medical education; Psychology; Sociology; Computer science; Medicine; Political science; Artificial intelligence; Curriculum; Politics","score_opus":0.18707567280741413,"score_gpt":0.42022678500476013,"score_spread":0.233151112197346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392681814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72682226,0.00013131161,7.53364e-7,0.0018612996,0.00022204863,0.00022353647,0.0000016688402,0.00012377472,0.27061334],"genre_scores_gemma":[0.99814916,0.00041777655,0.0000650792,0.000023202945,0.00019590741,0.00003398121,0.0000017734247,0.00001328781,0.0010998461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99858963,0.000026241825,0.00026853138,0.00022406377,0.00050664635,0.00038490453],"domain_scores_gemma":[0.9995889,0.00007265144,0.00013672649,0.000037493486,0.0001074555,0.000056756027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008820615,0.0001070259,0.00023712897,0.00018599308,0.00021630306,0.000063846164,0.0003010793,0.00008968905,0.00008483026],"category_scores_gemma":[0.00012983668,0.00011516446,0.00006529114,0.00056312,0.00014620325,0.00014943419,0.00010625124,0.00011902094,0.000050958923],"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":[0.00004532234,0.0001437143,0.2994901,0.00029458673,0.000069462156,0.000009169996,0.16297863,1.1333526e-7,0.00080621376,0.51099926,0.0018621299,0.023301303],"study_design_scores_gemma":[0.0010309938,0.00015481033,0.6989754,0.00028882982,0.000034616893,5.6810666e-7,0.27344078,0.00012216502,0.00012872087,0.017962437,0.0074562854,0.00040441778],"about_ca_topic_score_codex":0.0000572474,"about_ca_topic_score_gemma":0.00016485646,"teacher_disagreement_score":0.49303684,"about_ca_system_score_codex":0.00008105631,"about_ca_system_score_gemma":0.000087139444,"threshold_uncertainty_score":0.46962702},"labels":[],"label_agreement":null},{"id":"W4393037999","doi":"10.1080/0145935x.2026.2656753","title":"The Strengths/Structured Assessment for Youth (S/SAY): Evaluating Strengths in a Case Study of a Justice-Involved Youth","year":2024,"lang":"en","type":"preprint","venue":"Child & Youth Services","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"Social Sciences and Humanities Research Council","keywords":"Strengths and weaknesses; Economic Justice; Psychology; Political science; Applied psychology; Social psychology; Law","score_opus":0.05176695592938487,"score_gpt":0.40860619212623783,"score_spread":0.356839236196853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393037999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836358,0.0016137912,0.0000059419986,0.00033466986,0.0035441227,0.005575853,0.0012533014,0.0001867688,0.0038497807],"genre_scores_gemma":[0.99700475,0.0002254676,0.00041142717,0.00007626875,0.0013484971,0.00032885472,0.00040869013,0.00009750815,0.00009856406],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9932372,0.00090745493,0.0015709255,0.0014170768,0.0018473965,0.001019943],"domain_scores_gemma":[0.995772,0.0011405301,0.0012286033,0.0011195762,0.0005117912,0.00022751205],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0036890712,0.00082670216,0.0010916701,0.00036174193,0.0016247683,0.0011147425,0.0019316969,0.00050955743,0.000033205877],"category_scores_gemma":[0.00019017566,0.0006429865,0.000437058,0.00078948005,0.00021695442,0.00018335241,0.001917357,0.0015648656,0.000003898715],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014499931,0.00068266975,0.024762647,0.0013085391,0.00073550653,0.00006532715,0.96660215,0.00061153853,0.0000020557327,0.00054249895,0.000010937429,0.0045311092],"study_design_scores_gemma":[0.0021734582,0.00033953236,0.0042390754,0.0012218433,0.0035479646,0.0000010767417,0.9840228,0.0026320093,0.000004582388,0.0011309894,0.000029749728,0.000656915],"about_ca_topic_score_codex":0.03526282,"about_ca_topic_score_gemma":0.20246315,"teacher_disagreement_score":0.16720034,"about_ca_system_score_codex":0.00038674366,"about_ca_system_score_gemma":0.0008592052,"threshold_uncertainty_score":0.9999222},"labels":[],"label_agreement":null},{"id":"W4393071056","doi":"10.3389/feduc.2024.1366215","title":"Formative assessment in higher education: an exploratory study within programs for professionals in education","year":2024,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Exploratory research; Higher education; Computer science; Engineering management; Medical education; Knowledge management; Mathematics education; Engineering; Psychology; Political science; Sociology; Medicine","score_opus":0.05206261374251999,"score_gpt":0.43691539345796154,"score_spread":0.3848527797154416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393071056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94423926,0.0019524475,0.00013452601,0.004070672,0.031592347,0.0056964406,0.000002502364,0.00008340171,0.012228408],"genre_scores_gemma":[0.9770809,0.000039886305,0.008094091,0.00022487174,0.0008016294,0.0069734333,0.00015524153,0.000022377602,0.00660757],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9979368,0.00046503436,0.00048770724,0.00040621078,0.0004095266,0.00029474133],"domain_scores_gemma":[0.9993823,0.000058164336,0.00013078087,0.00018429152,0.00015505236,0.00008940696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017618879,0.00016184442,0.00020728582,0.0006574479,0.00016036765,0.00023900691,0.00027618234,0.00012016283,0.00007488974],"category_scores_gemma":[0.000039025403,0.00016402894,0.00003735739,0.0011714336,0.00006499693,0.0016322818,0.000026649604,0.00027238022,0.000006428073],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002647398,0.009587922,0.4487053,0.00008514971,0.00001610552,2.8684366e-7,0.38401163,0.0000044491007,0.0000037462382,0.017298078,0.0305619,0.10969897],"study_design_scores_gemma":[0.0002898099,0.00011185951,0.18664742,0.00037048385,0.000014321015,7.423124e-8,0.7797125,0.00011310902,0.000002684381,0.012699906,0.019834412,0.00020342202],"about_ca_topic_score_codex":0.00047495955,"about_ca_topic_score_gemma":0.0032921778,"teacher_disagreement_score":0.3957009,"about_ca_system_score_codex":0.0016770955,"about_ca_system_score_gemma":0.008231749,"threshold_uncertainty_score":0.9973906},"labels":[],"label_agreement":null},{"id":"W4393370921","doi":"10.37514/per-b.2024.2326.2.14","title":"Chapter 14. Ethical Considerations and Writing Assessment","year":2024,"lang":"en","type":"book-chapter","venue":"The WAC Clearinghouse; University Press of Colorado eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Engineering ethics; Report writing; Psychology; Engineering","score_opus":0.05163489517100832,"score_gpt":0.309715548798189,"score_spread":0.2580806536271807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393370921","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037009413,0.000117618714,0.000015222661,0.0027491362,0.00023862513,0.00057811214,0.00003121623,0.00016907377,0.99240005],"genre_scores_gemma":[0.5481407,0.000263032,0.00017661521,0.00011892364,0.00015492848,0.0000010905195,0.0000023027778,0.000037925944,0.4511045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983458,0.000098934135,0.00026535752,0.00037639026,0.00063831353,0.00027518463],"domain_scores_gemma":[0.99853754,0.00063546095,0.000223626,0.00029768082,0.00018450049,0.000121218996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075970264,0.00025175448,0.00038643807,0.00013249945,0.0010837778,0.00021822039,0.0004151106,0.00053749495,0.00018926349],"category_scores_gemma":[0.000019915087,0.00024222989,0.0001696347,0.000017312817,0.0015145371,0.0000867547,0.00067417003,0.0012527868,0.000014131132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027097627,0.000008723503,0.00006272788,0.000040392137,0.00019902783,0.00004034457,0.0050376095,0.0000034363995,0.000020364232,0.993187,0.0008654585,0.0005078143],"study_design_scores_gemma":[0.0007677087,0.00017767426,0.000924533,0.0005350923,0.0009737291,0.000006962922,0.0075253886,0.000101548576,0.000019243282,0.061786383,0.9264694,0.00071233715],"about_ca_topic_score_codex":0.0005089156,"about_ca_topic_score_gemma":0.00063091004,"teacher_disagreement_score":0.9314006,"about_ca_system_score_codex":0.0001375261,"about_ca_system_score_gemma":0.00019200575,"threshold_uncertainty_score":0.9877848},"labels":[],"label_agreement":null},{"id":"W4393899036","doi":"10.5430/wjel.v14n4p215","title":"Beyond the Red Pen: Exploring the Impact of Language Peer Assessment Technology on the ESL/EFL Writers’ Performance","year":2024,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Peer assessment; Linguistics; Mathematics education; Psychology; Philosophy","score_opus":0.026399321928394653,"score_gpt":0.34784514275770956,"score_spread":0.3214458208293149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393899036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9106153,0.0013203006,0.0000047186227,0.008235364,0.0014123959,0.00021528831,0.0000049598852,0.00004117778,0.078150444],"genre_scores_gemma":[0.99458355,0.00022054037,0.00007521323,0.000106099396,0.0016312102,0.0000150685855,0.0000010624175,0.000017894672,0.003349346],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99802345,0.0002447048,0.00036068473,0.00013204028,0.0009161413,0.00032296454],"domain_scores_gemma":[0.9982555,0.00083843747,0.00023565335,0.0003217674,0.0002962544,0.000052395473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031368497,0.00015508481,0.00022474538,0.00027117986,0.0003900035,0.00024505606,0.0009928922,0.000046559042,0.0005412725],"category_scores_gemma":[0.00059889816,0.00006734383,0.00028348056,0.0010368625,0.00028948934,0.0003445502,0.000105022686,0.0008583126,0.0000055236123],"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":[0.00011427691,0.00022836284,0.028715638,0.000041581858,0.0008549166,0.0002070204,0.80550396,0.0001342621,0.0020941808,0.054580532,0.071192384,0.036332887],"study_design_scores_gemma":[0.0008183127,0.0006387442,0.054096248,0.0006186006,0.00024834747,0.000015680209,0.8798488,0.00015521832,0.0013042472,0.0012620857,0.060593884,0.00039985726],"about_ca_topic_score_codex":0.000102152175,"about_ca_topic_score_gemma":0.00017814188,"teacher_disagreement_score":0.083968215,"about_ca_system_score_codex":0.00018740506,"about_ca_system_score_gemma":0.00018378824,"threshold_uncertainty_score":0.5926554},"labels":[],"label_agreement":null},{"id":"W4395110387","doi":"10.1080/08957347.2024.2345594","title":"A Critical Review of Fairness from Multiple Perspectives: Implications for Classroom Assessment Theory","year":2024,"lang":"en","type":"review","venue":"Applied Measurement in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Item response theory; Critical theory; Mathematics education; Political science; Developmental psychology; Psychometrics","score_opus":0.1496372500266458,"score_gpt":0.4788594395403927,"score_spread":0.3292221895137469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395110387","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.3227037e-7,0.9658984,0.0010978892,0.0012189794,0.000915042,0.004639262,0.00009748145,0.000045147222,0.026087154],"genre_scores_gemma":[0.001294066,0.988445,0.0011836976,0.00015558393,0.0006002989,0.007940052,0.00023796843,0.000045020384,0.00009835713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708855,0.00038011407,0.00080409076,0.0006489864,0.00077201007,0.0003062323],"domain_scores_gemma":[0.9974158,0.0011943923,0.00031595712,0.00044801147,0.00053444365,0.00009142701],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003264273,0.00032420625,0.001007217,0.00024768634,0.00019044062,0.000080776554,0.0004897895,0.00021657131,0.00010557402],"category_scores_gemma":[0.0010151581,0.0002849067,0.0003772509,0.00062107376,0.00015281889,0.00007751377,0.000043816683,0.00032507733,0.000039072525],"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":[0.0000047105787,0.0008212969,0.000027299184,0.022496851,0.00012153052,2.710359e-8,0.0023660427,4.4347132e-8,0.0000014879687,0.51688343,0.006791314,0.45048597],"study_design_scores_gemma":[0.00013070884,0.000024822468,0.0001499932,0.06344053,0.001504282,6.400764e-8,0.013054452,3.4715956e-7,2.9992702e-7,0.030597333,0.89079094,0.00030624535],"about_ca_topic_score_codex":0.00010412796,"about_ca_topic_score_gemma":0.00012842758,"teacher_disagreement_score":0.8839996,"about_ca_system_score_codex":0.0023871684,"about_ca_system_score_gemma":0.00442754,"threshold_uncertainty_score":0.9999603},"labels":[],"label_agreement":null},{"id":"W4396538087","doi":"10.18357/otessaj.2024.4.1.57","title":"Technology-Integrated Assessment: A Literature Review","year":2024,"lang":"en","type":"review","venue":"The Open/Technology in Education Society and Scholarship Association Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta; University of Victoria","funders":"","keywords":"Computer science","score_opus":0.04140750914591002,"score_gpt":0.45492046864975083,"score_spread":0.4135129595038408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396538087","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036008172,0.9333413,0.000003277448,0.060290918,0.0016708657,0.0016739677,0.000018457935,0.00012796615,0.0028372004],"genre_scores_gemma":[0.000038691447,0.9884003,0.00092380756,0.001066812,0.0004693588,0.0004778658,0.00006201678,0.000043583306,0.00851758],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955901,0.0014153714,0.0010971249,0.00055273133,0.00072605,0.00061862136],"domain_scores_gemma":[0.9970303,0.00033990896,0.0014039997,0.00041743103,0.00069318386,0.00011516419],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.011302666,0.00046498876,0.0013463551,0.0006473045,0.0017309906,0.0023953198,0.002407164,0.0020602734,0.0001279403],"category_scores_gemma":[0.0012056709,0.00032299221,0.0005101348,0.007065861,0.00033421273,0.0009777894,0.0004778226,0.0074304533,0.00007755997],"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":[0.0000016479645,0.00023122819,0.00387878,0.003427825,0.00070616324,0.000009689375,0.003004231,2.0536492e-8,3.489229e-7,0.060260866,0.09003155,0.83844763],"study_design_scores_gemma":[0.00015452197,0.000019824893,0.00006064203,0.055923115,0.0009775179,0.00008685187,0.007831913,3.8672292e-7,5.0512043e-8,0.020192968,0.91444725,0.0003049799],"about_ca_topic_score_codex":0.000011214716,"about_ca_topic_score_gemma":0.000037079142,"teacher_disagreement_score":0.8381427,"about_ca_system_score_codex":0.0023552186,"about_ca_system_score_gemma":0.004914512,"threshold_uncertainty_score":0.9999222},"labels":[],"label_agreement":null},{"id":"W4396665291","doi":"10.5206/cjsotlrcacea.2024.1.14923","title":"The Choice is Theirs: Students Achieve Positive Outcomes when Offered Flexibility in Course Assessment Options","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Flexibility (engineering); Course (navigation); Mathematics education; Psychology; Medical education; Computer science; Medicine; Engineering; Mathematics; Statistics","score_opus":0.06607427284343663,"score_gpt":0.43688141993953306,"score_spread":0.3708071470960964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396665291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92839265,0.0041039684,0.000118505566,0.0632554,0.00096985383,0.00058707845,0.000016452068,0.000022145165,0.002533945],"genre_scores_gemma":[0.99388057,0.00013028107,0.00012906296,0.00025435424,0.00022519294,0.000015394033,0.0000015814342,0.000015004891,0.005348539],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962712,0.002294795,0.00028596693,0.00017120308,0.0005307829,0.0004460355],"domain_scores_gemma":[0.9951023,0.004296016,0.00013293204,0.00017277627,0.00009666483,0.0001993146],"candidate_categories":["sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.017669061,0.00013774133,0.00017183005,0.000090033296,0.010708144,0.0022481356,0.0009100997,0.000076397264,0.000039727798],"category_scores_gemma":[0.0015022071,0.00007087417,0.00015964311,0.00013397212,0.00037717444,0.0003675989,0.000054610835,0.0030581714,0.0000024764915],"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":[0.000024313918,0.000035709752,0.7800927,0.00001247617,0.00048981165,0.0000052924743,0.15527835,0.00025628117,0.000014006743,0.02861348,0.00054368505,0.034633867],"study_design_scores_gemma":[0.00035758043,0.000098098535,0.87736064,0.00023421201,0.00016278948,0.0000057546567,0.07698276,0.00042035434,0.0000010764808,0.013557697,0.030669956,0.00014908113],"about_ca_topic_score_codex":0.032734305,"about_ca_topic_score_gemma":0.14098468,"teacher_disagreement_score":0.10825038,"about_ca_system_score_codex":0.00034479497,"about_ca_system_score_gemma":0.0007613599,"threshold_uncertainty_score":0.9992418},"labels":[],"label_agreement":null},{"id":"W4396689913","doi":"10.7202/1111099ar","title":"Analyse des émotions et des compétences émotionnelles d’étudiants universitaires dans le traitement d’un feedback formatif à distance","year":2023,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Cognitive psychology; Mathematics education; Social psychology; Applied psychology","score_opus":0.07563898955206862,"score_gpt":0.36806984425791356,"score_spread":0.29243085470584496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396689913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9081933,0.0007251089,0.041295346,0.034852583,0.0015614396,0.0006739682,0.0000756431,0.0001974143,0.01242522],"genre_scores_gemma":[0.98456156,0.0030963183,0.00515166,0.00008460853,0.0001968125,0.000054013646,0.00055593386,0.000025159392,0.0062739216],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99330896,0.0041873106,0.0005540735,0.0004446329,0.0009934885,0.0005115527],"domain_scores_gemma":[0.99805754,0.0006514631,0.00037274556,0.0002456276,0.000528177,0.00014446079],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.008854722,0.00029223802,0.00029003626,0.0003109463,0.0020856399,0.00029089188,0.0004079025,0.00016962383,0.00065118616],"category_scores_gemma":[0.00040946066,0.0003208483,0.00018858422,0.0025356465,0.0007566889,0.0024461872,0.00007864339,0.00020012283,0.0003956205],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000125149245,0.00070987275,0.11822018,0.00011191739,0.0002512848,0.0000021603223,0.7876537,0.0061849062,0.00025495596,0.050783332,0.009068587,0.026746573],"study_design_scores_gemma":[0.0005154535,0.00005305429,0.68486446,0.00016092372,0.00017712808,9.080905e-7,0.28687674,0.0040899687,0.000062472085,0.021677546,0.0012696651,0.00025168894],"about_ca_topic_score_codex":0.0022169005,"about_ca_topic_score_gemma":0.029466873,"teacher_disagreement_score":0.56664425,"about_ca_system_score_codex":0.000955157,"about_ca_system_score_gemma":0.0009819443,"threshold_uncertainty_score":0.99992436},"labels":[],"label_agreement":null},{"id":"W4396755911","doi":"10.7202/1110995ar","title":"Adapting to the Ethics of Differentiated Learning Assessment: Analysis of Foreign-trained Teachers’ Experiences in Quebec","year":2022,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Engineering ethics; Psychology; Mathematics education; Pedagogy; Sociology; Engineering","score_opus":0.10672369507891309,"score_gpt":0.44606418875250586,"score_spread":0.33934049367359276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396755911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869966,0.000021468899,0.0035348034,0.0044046547,0.0001854514,0.00036281566,0.0000021151934,0.000017081038,0.0044750012],"genre_scores_gemma":[0.9984852,0.000009716909,0.00036885787,0.000056392313,0.000027984708,0.00016309439,0.00008884089,0.0000055783967,0.0007943433],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99054116,0.0075812726,0.00038257326,0.00018219699,0.0011716231,0.00014118699],"domain_scores_gemma":[0.99822336,0.001103552,0.00034552754,0.00012503553,0.00017986265,0.000022633096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022431768,0.00007439326,0.00019206034,0.00036156856,0.00043952567,0.000042388034,0.0002738398,0.00005407153,0.0008657307],"category_scores_gemma":[0.0013673604,0.00006632147,0.000084490835,0.0020875381,0.000053164156,0.00019580885,0.00006108691,0.00032821365,6.484323e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053844306,0.00007469876,0.1725019,0.0000024244,0.00007603902,3.4476813e-8,0.81033725,0.010734401,0.00037682042,0.0046680965,0.00004103145,0.0011819463],"study_design_scores_gemma":[0.0000960742,0.000025055175,0.5263031,0.00000529899,0.00009700969,9.27227e-9,0.46944764,0.0036329224,0.00001822201,0.00009038254,0.00023823281,0.000046068926],"about_ca_topic_score_codex":0.020428909,"about_ca_topic_score_gemma":0.07208384,"teacher_disagreement_score":0.3538012,"about_ca_system_score_codex":0.00028242692,"about_ca_system_score_gemma":0.0007777523,"threshold_uncertainty_score":0.9860941},"labels":[],"label_agreement":null},{"id":"W4396881195","doi":"10.1016/j.tate.2024.104634","title":"Assessment practices of teachers in Myanmar: Are we there yet?","year":2024,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Mathematics education; Pedagogy; Psychology; Sociology; Political science","score_opus":0.0511862017902367,"score_gpt":0.4463976810256406,"score_spread":0.3952114792354039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396881195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89633584,0.0038282212,0.00007228437,0.014166434,0.00063600537,0.00020370918,9.604719e-7,0.00008450375,0.08467204],"genre_scores_gemma":[0.987555,0.00045776184,0.0014806136,0.00004674709,0.0002898053,0.000028193983,0.0000049796126,0.000012897696,0.010123955],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985055,0.00060830964,0.0001937615,0.0002381443,0.00028073863,0.00017360215],"domain_scores_gemma":[0.99925613,0.00035847025,0.00018969672,0.00011855978,0.000021490458,0.00005566639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002437931,0.00010148388,0.00013635319,0.00015189545,0.00021131997,0.00018618483,0.00014117252,0.00008798301,0.00014346161],"category_scores_gemma":[0.00029545894,0.00009260346,0.0000383151,0.00017868908,0.00008250766,0.00043406175,0.000028140503,0.00055264425,0.0000067478445],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040756904,0.0005576299,0.5193158,0.00008465308,0.000035234123,0.0000013599507,0.20877416,0.0000010699181,0.00016499188,0.054045215,0.005137855,0.21187797],"study_design_scores_gemma":[0.00012142545,0.00003144487,0.56543875,0.00052905356,0.0000528595,8.8314675e-7,0.26901665,0.00009592082,0.0000045794654,0.005318592,0.15920977,0.00018004408],"about_ca_topic_score_codex":0.008193015,"about_ca_topic_score_gemma":0.0008886138,"teacher_disagreement_score":0.21169794,"about_ca_system_score_codex":0.00017947242,"about_ca_system_score_gemma":0.00042154305,"threshold_uncertainty_score":0.99841154},"labels":[],"label_agreement":null},{"id":"W4396978444","doi":"10.21449/ijate.1376160","title":"The difference between estimated and perceived item difficulty: An empirical study","year":2024,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Statistics; Empirical research; Econometrics; Mathematics education; Mathematics","score_opus":0.08975046533286718,"score_gpt":0.5107784354602035,"score_spread":0.42102797012733634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396978444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99013275,0.00016271582,0.00015145601,0.0056187944,0.002500994,0.00022585124,0.0000026399891,0.000018239249,0.0011865712],"genre_scores_gemma":[0.99776673,0.00038784338,0.00048436414,0.000048127462,0.00096488144,0.000014998167,0.000009163883,0.000007304943,0.0003165973],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99808455,0.00031847184,0.00042534224,0.00015383569,0.00087601616,0.00014180451],"domain_scores_gemma":[0.9984225,0.0009151304,0.00015337832,0.000074779986,0.00034723524,0.000087001805],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012243337,0.000095337855,0.00013362317,0.00019084424,0.0001962712,0.0012563962,0.00049963366,0.00004666487,0.000035927198],"category_scores_gemma":[0.00024548694,0.000066311695,0.00004395479,0.00020179545,0.00009665512,0.0007077001,0.000050294446,0.00028364995,0.0000026391258],"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":[0.00001230981,0.00042878254,0.84924406,0.0000019191916,0.000080952545,0.000007748953,0.014091996,0.0000023516475,0.0001133291,0.0011073234,0.0002475331,0.13466166],"study_design_scores_gemma":[0.00021891436,0.00013354531,0.9597335,0.00009437176,0.00003134816,0.0000038333515,0.03638928,0.00020765902,0.0000025406569,0.0010265815,0.0020846042,0.000073847106],"about_ca_topic_score_codex":0.00018694773,"about_ca_topic_score_gemma":0.00038017845,"teacher_disagreement_score":0.13458782,"about_ca_system_score_codex":0.00044958587,"about_ca_system_score_gemma":0.00082517386,"threshold_uncertainty_score":0.9997804},"labels":[],"label_agreement":null},{"id":"W4398216268","doi":"10.1177/14782103241255855","title":"International trends in the implementation of assessment for learning <i>revisited</i> : Implications for policy and practice in a post-COVID world","year":2024,"lang":"en","type":"article","venue":"Policy Futures in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Queen's University; Brock University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Summative assessment; Globe; Political science; Coronavirus disease 2019 (COVID-19); Pandemic; Public administration; Formative assessment; Economic growth; Sociology; Public relations; Pedagogy; Psychology; Economics","score_opus":0.03391237724382954,"score_gpt":0.5307683282009764,"score_spread":0.49685595095714685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398216268","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13236861,0.001072024,0.0005240548,0.7865745,0.00097004947,0.0026054576,0.00012166822,0.000046136767,0.07571752],"genre_scores_gemma":[0.99378186,0.0004281219,0.001806899,0.001268523,0.0013569102,0.0007597032,0.0001827744,0.000008429273,0.00040674853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9990102,0.00020350692,0.00027029763,0.0001800788,0.0001550758,0.00018084572],"domain_scores_gemma":[0.9983395,0.0013554991,0.00011001446,0.000075106596,0.00009432378,0.000025607827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014198652,0.00007335541,0.00008788989,0.0011575383,0.00012873895,0.00015598089,0.00018310893,0.000036770278,0.000019808287],"category_scores_gemma":[0.0007191413,0.000066406166,0.000040390205,0.0013249294,0.00004625839,0.00037669498,0.000022179034,0.000110733956,2.564989e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019609559,0.00013292892,0.02740911,0.000025821995,0.000012896312,4.659744e-8,0.07115876,0.000010260759,0.00015784158,0.5746742,0.0018108444,0.32458767],"study_design_scores_gemma":[0.0004001952,0.00004749547,0.5488528,0.000033829114,0.000018931936,9.998881e-7,0.10206514,0.000051783456,0.0000045209067,0.012906099,0.33553046,0.00008774435],"about_ca_topic_score_codex":0.013847614,"about_ca_topic_score_gemma":0.02699265,"teacher_disagreement_score":0.8614133,"about_ca_system_score_codex":0.00052622973,"about_ca_system_score_gemma":0.0011608872,"threshold_uncertainty_score":0.99271923},"labels":[],"label_agreement":null},{"id":"W4399561197","doi":"10.61871/mj.v46n4-19","title":"Past, Present, and Future of Language Assessment: An Interview with Dr. Hossein Farhady","year":2023,"lang":"en","type":"article","venue":"Mextesol journal.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Linguistics; Philosophy","score_opus":0.031010176548061298,"score_gpt":0.37809221575371943,"score_spread":0.3470820392056581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399561197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91521883,0.0028111385,0.00038178219,0.03854647,0.00084176514,0.00056045665,0.00001625,0.00018416917,0.04143916],"genre_scores_gemma":[0.9760288,0.0050821626,0.0016098091,0.00033716383,0.00727349,0.000024788145,0.00002178922,0.00005329441,0.009568731],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827534,0.0003819462,0.00023649221,0.00017376081,0.0006023799,0.00033005874],"domain_scores_gemma":[0.99925137,0.000083316634,0.00020280537,0.00015933249,0.00011823396,0.00018493294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014926217,0.00012750358,0.00023521013,0.00014182222,0.00037138347,0.0002280983,0.0003434355,0.00006634295,0.00033437784],"category_scores_gemma":[0.000007885996,0.00009433229,0.000059558013,0.00052210625,0.00014161125,0.00043452415,0.00007732548,0.00025274538,0.000014245609],"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":[0.00007433544,0.0005247622,0.21762215,0.00015592891,0.00047233936,0.00041594636,0.14518075,0.000013246813,0.0026657905,0.004592024,0.09448332,0.5337994],"study_design_scores_gemma":[0.0012428642,0.0004671311,0.24302937,0.00015849835,0.00010750925,0.000024244107,0.16352645,0.00012638934,0.000047400084,0.00064079795,0.59030765,0.00032165897],"about_ca_topic_score_codex":0.00010147494,"about_ca_topic_score_gemma":0.00016717236,"teacher_disagreement_score":0.5334777,"about_ca_system_score_codex":0.000036264908,"about_ca_system_score_gemma":0.00009290022,"threshold_uncertainty_score":0.3846759},"labels":[],"label_agreement":null},{"id":"W4399565789","doi":"10.29173/isot1532","title":"Conversations and Reflections on Authentic Assessment","year":2021,"lang":"en","type":"article","venue":"Imagining SoTL","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Epistemology; Sociology; Philosophy","score_opus":0.061162770415292445,"score_gpt":0.44456000084983166,"score_spread":0.3833972304345392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399565789","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13794835,0.00010614537,0.0010020258,0.04760139,0.0014413995,0.00015667832,0.000004559942,0.00020452085,0.81153494],"genre_scores_gemma":[0.9889771,0.000058077632,0.0023478523,0.0004543494,0.00015888346,0.000010718638,0.0000054533984,0.0000065073473,0.007981064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992529,0.000096348806,0.000085340274,0.00016481515,0.00023560478,0.00016498253],"domain_scores_gemma":[0.9995863,0.00014487597,0.000032906642,0.00009718465,0.000075189055,0.0000635428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022390933,0.00005588978,0.00007087202,0.000045536854,0.0005881537,0.00018799161,0.000062350184,0.000026683929,0.00052623445],"category_scores_gemma":[0.00008143371,0.00006136977,0.000029344495,0.00021010193,0.0001310941,0.00013381048,0.000031248244,0.0001102091,0.000052477026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060259686,0.00021956937,0.12923265,0.000008605328,0.0001003283,0.000032851516,0.07103013,0.000006415553,0.0016035184,0.78420925,0.0076418947,0.005908783],"study_design_scores_gemma":[0.0012718454,0.000112245005,0.25955763,0.00008357382,0.00013904268,0.0000061222204,0.15559356,0.00033211132,0.00031657875,0.01132385,0.57077664,0.00048679663],"about_ca_topic_score_codex":0.0002184273,"about_ca_topic_score_gemma":0.00035335714,"teacher_disagreement_score":0.85102874,"about_ca_system_score_codex":0.00007191242,"about_ca_system_score_gemma":0.00020970368,"threshold_uncertainty_score":0.5761898},"labels":[],"label_agreement":null},{"id":"W4399626674","doi":"10.4300/jgme-d-23-00526.1","title":"Exploring the Use of Natural Language Processing to Understand Emotions of Trainees and Faculty Regarding Entrustable Professional Activity Assessments","year":2024,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Medical education; Psychology; Natural (archaeology); Medicine; Biology","score_opus":0.3044004809950062,"score_gpt":0.47787551308450965,"score_spread":0.17347503208950343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399626674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98693603,0.00026481343,0.0006594301,0.010497124,0.0013533859,0.00012841134,0.000002137284,0.0000063019274,0.00015237162],"genre_scores_gemma":[0.99837077,0.00015062881,0.0007085698,0.000045215358,0.00027340418,0.0000029905812,0.0000017158154,0.0000046902182,0.00044198884],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99843687,0.00013807112,0.00025307678,0.0000788493,0.00097460434,0.0001185344],"domain_scores_gemma":[0.9992386,0.00023302018,0.0001723042,0.000041083025,0.00019985509,0.00011511795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010755481,0.000060120132,0.00014136845,0.00012385887,0.00018188795,0.000095578005,0.00012318132,0.000029144987,0.000026391042],"category_scores_gemma":[0.0008009966,0.000037485268,0.00005290953,0.0003553699,0.0001234275,0.00083031337,0.00003037026,0.00025797368,2.3465913e-7],"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":[0.00011821899,0.0007117043,0.008029604,0.0004517887,0.0002053481,0.000008208391,0.3524771,0.000019772988,0.0032556835,0.0034392034,0.010004302,0.62127906],"study_design_scores_gemma":[0.0007741938,0.00024185775,0.24874942,0.0050234953,0.00027080998,0.00002575759,0.7338409,0.0027103154,0.0008038823,0.00086800713,0.0064215623,0.0002698123],"about_ca_topic_score_codex":0.00015924756,"about_ca_topic_score_gemma":0.00006997959,"teacher_disagreement_score":0.62100923,"about_ca_system_score_codex":0.000111522626,"about_ca_system_score_gemma":0.0012763742,"threshold_uncertainty_score":0.22642331},"labels":[],"label_agreement":null},{"id":"W4399879453","doi":"10.55016/ojs/ajer.v49i4.55029","title":"What Do Teacher Candidates Know About Large-Scale Assessments? What Should They Know?","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Need to know; Psychology; Scale (ratio); Educational research; Mathematics education; Pedagogy; Computer science; Geography","score_opus":0.0798291492930633,"score_gpt":0.47919424289482,"score_spread":0.3993650936017567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399879453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5903554,0.02800289,0.000006679169,0.054417137,0.0043041967,0.00049914484,0.000002506623,0.0000026666664,0.32240942],"genre_scores_gemma":[0.6643486,0.052051634,0.0003168661,0.00030453835,0.0016157895,0.00003478406,0.000011736528,0.000032419775,0.28128365],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99489146,0.0012470441,0.00050131965,0.00028640043,0.00224119,0.0008325777],"domain_scores_gemma":[0.99027103,0.007556763,0.00024786007,0.00026226364,0.0012163846,0.00044568683],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005450157,0.0001696351,0.00027102794,0.00037072683,0.001021569,0.0021168976,0.0008588791,0.00015940247,0.03961875],"category_scores_gemma":[0.00333588,0.00014200891,0.00017424421,0.0006096102,0.0002921443,0.003524776,0.00008523727,0.00082001364,0.00056563545],"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":[0.00013783998,0.002641207,0.60797715,0.000028597638,0.00038224284,0.0000040709774,0.054475624,0.000009680168,0.0001947208,0.14811254,0.1786108,0.007425528],"study_design_scores_gemma":[0.0005741806,0.0001359426,0.021631498,0.00041852772,0.000036728765,0.000011270341,0.12909256,0.0000077648965,0.000049502578,0.0048199473,0.84301436,0.00020773466],"about_ca_topic_score_codex":0.0013632355,"about_ca_topic_score_gemma":0.014567095,"teacher_disagreement_score":0.66440356,"about_ca_system_score_codex":0.0005100336,"about_ca_system_score_gemma":0.0029778231,"threshold_uncertainty_score":0.998919},"labels":[],"label_agreement":null},{"id":"W4399879966","doi":"10.55016/ojs/ajer.v49i3.54986","title":"Differential Validity and Utility of Successive and Simultaneous Approaches to the Development of Equivalent Achievement Tests in French and English","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Differential (mechanical device); Psychology; Multiculturalism; Socioeconomic status; Mathematics education; Multilingualism; Pedagogy; Sociology","score_opus":0.25212667805119937,"score_gpt":0.430524562775349,"score_spread":0.17839788472414964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399879966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99155223,0.00023750155,0.0000069032867,0.002202498,0.00009600021,0.00023880911,0.0000013304855,1.3208296e-7,0.005664585],"genre_scores_gemma":[0.99875575,0.000100613855,0.00029352852,0.0000051222437,0.000076064396,0.000007884905,8.787443e-7,0.0000027529866,0.0007573719],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99819225,0.00037399866,0.000363692,0.00012946663,0.0007411181,0.00019949122],"domain_scores_gemma":[0.98975396,0.009519937,0.0001405005,0.00006988693,0.00038329393,0.00013241182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021697213,0.000065937136,0.0001586609,0.0001391126,0.0002229942,0.000048788683,0.00019635103,0.000037072838,0.00039229644],"category_scores_gemma":[0.0081307795,0.000047086956,0.000019398107,0.00024034287,0.00031370064,0.0000970589,0.00010068654,0.00017574412,4.6795617e-7],"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":[0.0000379818,0.0004188618,0.9364279,0.00003342224,0.00003166797,1.376707e-7,0.056296706,0.0000026985988,0.000065523534,0.0052484362,0.00014191028,0.0012947605],"study_design_scores_gemma":[0.00035803442,0.00012477225,0.9811452,0.00006667062,0.00001295172,9.246214e-7,0.015364264,0.000023750068,0.00028447184,0.0007737788,0.0017783885,0.000066807304],"about_ca_topic_score_codex":0.00078353815,"about_ca_topic_score_gemma":0.009446729,"teacher_disagreement_score":0.044717293,"about_ca_system_score_codex":0.000058989415,"about_ca_system_score_gemma":0.00075107673,"threshold_uncertainty_score":0.97338897},"labels":[],"label_agreement":null},{"id":"W4400440977","doi":"10.55016/ojs/ajer.v53i1.55195","title":"Factors Affecting Teachers’ Grading and Assessment Practices","year":2007,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; Pedagogy; Engineering","score_opus":0.2729481972337564,"score_gpt":0.5720544857102489,"score_spread":0.29910628847649245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400440977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80457705,0.00025347518,0.0000049304595,0.008473429,0.00034012814,0.00009421898,1.1051572e-7,4.795263e-7,0.18625616],"genre_scores_gemma":[0.98601884,0.00018580584,0.0005858932,0.000022145388,0.00090930035,9.817772e-7,0.0000010046197,0.0000071879185,0.012268866],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99766093,0.00040554124,0.00027343346,0.00012312346,0.0011542948,0.00038265344],"domain_scores_gemma":[0.9573922,0.041455332,0.00041211187,0.000062985055,0.00043369966,0.00024364964],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008342218,0.00007110175,0.00012231845,0.0003225982,0.0008482348,0.00024726198,0.00028235582,0.000058231046,0.0020529232],"category_scores_gemma":[0.017409824,0.00005798895,0.000052561085,0.0004196439,0.00022380902,0.00065962464,0.000051548148,0.0005876735,0.00001200785],"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":[0.00000985947,0.00013664294,0.94172674,0.0000048149955,0.000050942213,4.791697e-7,0.033853382,2.320174e-7,0.00027767167,0.020733578,0.0022067307,0.0009988941],"study_design_scores_gemma":[0.00015324607,0.000085274405,0.8581464,0.000036481615,0.000016343447,0.000004075446,0.102124386,0.0000011127462,0.00004175077,0.0005896594,0.0387331,0.00006812252],"about_ca_topic_score_codex":0.0038833523,"about_ca_topic_score_gemma":0.0063446905,"teacher_disagreement_score":0.18144174,"about_ca_system_score_codex":0.00032923272,"about_ca_system_score_gemma":0.0010766892,"threshold_uncertainty_score":0.99885935},"labels":[],"label_agreement":null},{"id":"W4400804946","doi":"10.1177/00049441241258496","title":"Creating and enacting culturally responsive assessment for First Nations students in higher education settings","year":2024,"lang":"en","type":"article","venue":"Australian Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pedagogy; Higher education; Psychology; Cultural competence; Mathematics education; Sociology; Medical education; Political science; Engineering ethics; Medicine; Engineering","score_opus":0.05268109075650512,"score_gpt":0.4546815064927637,"score_spread":0.40200041573625855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400804946","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95409995,0.0003200324,0.000018384935,0.0334024,0.0031839136,0.0004348403,0.0000020927016,0.00001345278,0.008524918],"genre_scores_gemma":[0.9740731,0.00012212366,0.0037311297,0.0000940964,0.0010386074,0.000035091518,0.000007204301,0.000008387404,0.020890241],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989257,0.00009746922,0.00035106056,0.00013058295,0.00033579246,0.00015941024],"domain_scores_gemma":[0.9987683,0.0005445084,0.0002304982,0.00004450673,0.0003280307,0.00008413113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010800305,0.00008272985,0.000113397626,0.00030964427,0.00040406812,0.00047636023,0.0001542305,0.000058198035,0.00012621592],"category_scores_gemma":[0.0003437819,0.00007675388,0.00005320812,0.00038290164,0.000040217375,0.00076682627,0.00001364645,0.00016442135,0.0000021703743],"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":[0.00007306067,0.00106083,0.6096832,0.00041305425,0.00022435372,0.0000054760435,0.20515434,0.00002942527,0.001724098,0.10200229,0.052475125,0.027154727],"study_design_scores_gemma":[0.0003617705,0.00012729093,0.6881924,0.0015374254,0.00010530193,0.000008713821,0.15573928,0.0000054974803,0.000048955797,0.0025645318,0.15111972,0.00018909507],"about_ca_topic_score_codex":0.00014305756,"about_ca_topic_score_gemma":0.0003668865,"teacher_disagreement_score":0.09943776,"about_ca_system_score_codex":0.00045710284,"about_ca_system_score_gemma":0.001185705,"threshold_uncertainty_score":0.45935526},"labels":[],"label_agreement":null},{"id":"W4400898293","doi":"10.55016/ojs/pplt.v3y2019.53345","title":"A Study of Authentic Assessment in an Internship Course","year":2019,"lang":"en","type":"article","venue":"Papers on postsecondary learning and teaching.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Internship; Authentic learning; Medical education; Pedagogy; Authentic assessment; Psychology; Medicine; Curriculum","score_opus":0.018702050589538707,"score_gpt":0.3694773532151014,"score_spread":0.35077530262556267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400898293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8687108,0.000026995041,3.5540805e-7,0.00014230704,0.00017225891,0.00031550924,7.081268e-7,0.000039591996,0.13059148],"genre_scores_gemma":[0.9968669,0.000008954466,0.000034360924,0.000059278358,0.000037424394,0.000008107512,0.000004688121,0.000013456404,0.002966829],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99800026,0.00087626226,0.0002183714,0.00029735288,0.00036538427,0.00024235105],"domain_scores_gemma":[0.99939924,0.0002508368,0.00011652868,0.00012777983,0.000019545078,0.000086092885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015929827,0.0001253178,0.00023252948,0.00012667687,0.00025811928,0.00008779548,0.00018574117,0.00006041371,0.0005017234],"category_scores_gemma":[0.000056651403,0.00011833258,0.000036761692,0.00006779501,0.0000664483,0.00016501403,0.000051705716,0.00076154753,0.000015641543],"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":[0.000033471963,0.0007028218,0.8868338,0.000008321377,0.00002596984,0.000005944852,0.09728854,0.0000115625735,0.00015865148,0.0029523524,0.0000051041716,0.01197348],"study_design_scores_gemma":[0.0010209492,0.0013956008,0.7412657,0.000045434826,0.000015418469,3.673659e-7,0.25453144,0.00006096053,8.9031016e-7,0.000027950842,0.0015086683,0.00012661425],"about_ca_topic_score_codex":0.00085293356,"about_ca_topic_score_gemma":0.001548724,"teacher_disagreement_score":0.15724291,"about_ca_system_score_codex":0.000057241632,"about_ca_system_score_gemma":0.00007866126,"threshold_uncertainty_score":0.54935193},"labels":[],"label_agreement":null},{"id":"W4401063996","doi":"10.53761/1.20.5.13","title":"Exploring Faculty Mindsets in Equity-Oriented Assessment","year":2023,"lang":"en","type":"article","venue":"Journal of University Teaching and Learning Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Athabasca University","funders":"","keywords":"Rigour; Thematic analysis; Equity (law); Medical education; Psychology; Alternative assessment; Higher education; Qualitative property; Pedagogy; Data collection; Public relations; Qualitative research; Sociology; Political science; Social science; Medicine","score_opus":0.1606322251998828,"score_gpt":0.4301161781990955,"score_spread":0.2694839529992127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401063996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93267596,0.000018800189,0.00040576252,0.005587249,0.00031357576,0.00004848681,3.9476177e-7,0.000040807907,0.06090898],"genre_scores_gemma":[0.9915382,0.0005800902,0.0040617497,0.000037308022,0.00013562241,1.0718362e-7,0.0000018606979,0.0000050578874,0.003639959],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967271,0.0022807522,0.00015371742,0.00010608431,0.00051543594,0.00021689692],"domain_scores_gemma":[0.9977439,0.001681321,0.00033211088,0.000039565388,0.000102429854,0.00010065665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009934143,0.00006746042,0.00014511043,0.000332079,0.0010865876,0.000095581054,0.00016663686,0.000042473563,0.000012999852],"category_scores_gemma":[0.003280131,0.000070649025,0.000049865663,0.00038566106,0.00004917103,0.0018852766,0.00013489442,0.0015208162,0.000006225646],"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":[0.0006728065,0.0005792882,0.1877149,0.00004472536,0.00034452055,0.0018405283,0.6211989,0.0030297332,0.00085928285,0.019109827,0.0038041894,0.16080134],"study_design_scores_gemma":[0.0005973043,0.00009699657,0.08178871,0.000060190956,0.00004384601,0.0000070836463,0.3768281,0.00012394937,8.881753e-7,0.000011380879,0.54036176,0.00007979582],"about_ca_topic_score_codex":0.0011352815,"about_ca_topic_score_gemma":0.000064011954,"teacher_disagreement_score":0.53655756,"about_ca_system_score_codex":0.00023426968,"about_ca_system_score_gemma":0.00013929915,"threshold_uncertainty_score":0.83572626},"labels":[],"label_agreement":null},{"id":"W4401116136","doi":"10.1097/nne.0000000000001707","title":"Exam Wrappers in Nursing Education","year":2024,"lang":"en","type":"article","venue":"Nurse Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cooke Aquaculture (Canada)","funders":"","keywords":"Session (web analytics); Metacognition; Medical education; Psychology; Test (biology); Physical exam; Computer science; Medicine; Internal medicine; Cognition; World Wide Web","score_opus":0.0207929048151693,"score_gpt":0.43070026417597734,"score_spread":0.409907359360808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401116136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5267666,0.0014023441,0.0000032073272,0.007372597,0.009888324,0.00018509479,5.693016e-7,0.00009467284,0.45428658],"genre_scores_gemma":[0.9822633,0.00006712119,0.00017885238,0.0001388895,0.0015938386,0.000039155646,0.0000040676546,0.000012365217,0.015702356],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991295,0.00006873013,0.0001113103,0.00020286745,0.00023676157,0.0002508373],"domain_scores_gemma":[0.9997104,0.00006318133,0.000015455274,0.0000949104,0.000022608907,0.000093467126],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029452657,0.00007450378,0.00007597327,0.00018328306,0.00013165874,0.00017351631,0.00015443363,0.000064338776,0.00094132795],"category_scores_gemma":[0.00003740913,0.00007695766,0.000042278945,0.000547302,0.00013353949,0.00023725028,0.000003703852,0.00012512127,0.00040075489],"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":[0.0000071447635,0.0008281511,0.06261387,0.000020522577,0.000012478397,0.0000028900438,0.22863464,3.8577005e-7,0.00018994769,0.21160223,0.24456786,0.2515199],"study_design_scores_gemma":[0.00013348923,0.0000249083,0.102348424,0.0006519043,0.000029485791,0.0000013023325,0.41409525,0.000017419452,0.00005842356,0.006267334,0.4760809,0.00029115993],"about_ca_topic_score_codex":0.00045422633,"about_ca_topic_score_gemma":0.00014794727,"teacher_disagreement_score":0.45549676,"about_ca_system_score_codex":0.00038912226,"about_ca_system_score_gemma":0.0014509888,"threshold_uncertainty_score":0.9999719},"labels":[],"label_agreement":null},{"id":"W4401119677","doi":"10.1007/s11896-024-09696-5","title":"Investigating a Train-the-Trainer Model of Supervision and Peer Review for Child Interviewers in Canadian Police Services","year":2024,"lang":"en","type":"article","venue":"Journal of Police and Criminal Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Barrie Urology Group; Hospital for Sick Children","funders":"Australian Research Council; Griffith University; Government of Ontario","keywords":"Interview; Trainer; Psychology; Focus group; Qualitative research; Semi-structured interview; Medical education; Motivational interviewing; Intervention (counseling); Applied psychology; Medicine; Sociology","score_opus":0.08866103449901191,"score_gpt":0.4465185265585714,"score_spread":0.35785749205955947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401119677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88824666,0.01403277,0.00002575399,0.0884121,0.000237659,0.000230815,0.000013798162,0.000003966868,0.008796502],"genre_scores_gemma":[0.9827519,0.0081529245,0.00029890178,0.008343516,0.00028565948,0.000004178812,0.0000013288409,0.000008183909,0.0001534028],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99895126,0.0000979797,0.00036752986,0.00011461097,0.00022168571,0.00024695913],"domain_scores_gemma":[0.9993771,0.000113019036,0.000112355716,0.000059311627,0.00016683096,0.0001713864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018803908,0.00008676931,0.00023430426,0.00019633179,0.00011501016,0.000047729332,0.00021128547,0.000070302325,0.000018145887],"category_scores_gemma":[0.000048629718,0.00006176857,0.00007435036,0.00018454337,0.00018284023,0.00018362886,0.000017261205,0.00019869111,5.276592e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007174188,0.0001109131,0.01001987,0.00491914,0.0001844714,0.000007654201,0.8819908,0.000013630135,0.0012766378,0.023089772,0.030519089,0.047796268],"study_design_scores_gemma":[0.003876597,0.0016445079,0.13071421,0.021079523,0.0017098223,0.00051021314,0.44346666,0.0052444865,0.000029901226,0.015288576,0.37538794,0.0010475515],"about_ca_topic_score_codex":0.1577495,"about_ca_topic_score_gemma":0.35803208,"teacher_disagreement_score":0.43852413,"about_ca_system_score_codex":0.00002962956,"about_ca_system_score_gemma":0.00015709797,"threshold_uncertainty_score":0.8478591},"labels":[],"label_agreement":null},{"id":"W4401163052","doi":"10.1162/qss_a_00319/v1/review1","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Library science; Computer science; Mathematics; Combinatorics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163052","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28889334,0.5225206,0.00013366547,0.08197879,0.0032085616,0.086384915,0.00607388,0.00053728605,0.010268953],"genre_scores_gemma":[0.0064572752,0.35310176,0.000104868435,0.00016375748,0.00029630587,0.00016112854,0.0002819112,0.00003791179,0.6393951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812514,0.00047306248,0.00024649786,0.00036124274,0.00052432873,0.00026974073],"domain_scores_gemma":[0.99854064,0.00056803547,0.00020719341,0.0002569943,0.0003432569,0.00008388955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037566675,0.0001642435,0.0005349634,0.000027564656,0.0011044246,0.000086472646,0.0002531365,0.00009889404,0.00013968714],"category_scores_gemma":[0.00017562315,0.00010953279,0.00011007924,0.00031171727,0.0003151816,0.00013618116,0.0006299956,0.0001492593,0.0000146202265],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029912952,0.000085357846,0.0054888735,0.025639018,0.00017558105,0.0001028579,0.005856626,3.5819067e-8,2.5789979e-7,0.00009091254,0.958009,0.0045215525],"study_design_scores_gemma":[0.00084860664,0.00013790505,0.00531433,0.011608539,0.0008749019,0.000019667676,0.24603179,0.000015781468,6.8271305e-8,0.0000026481625,0.73488396,0.00026181646],"about_ca_topic_score_codex":0.020967713,"about_ca_topic_score_gemma":0.26057014,"teacher_disagreement_score":0.62912613,"about_ca_system_score_codex":0.00017428763,"about_ca_system_score_gemma":0.00010122614,"threshold_uncertainty_score":0.9855518},"labels":[],"label_agreement":null},{"id":"W4401163090","doi":"10.1162/qss_a_00319/v2/review2","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Geography; Library science; Data science; Sociology; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163090","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28889334,0.5225206,0.00013366547,0.08197879,0.0032085616,0.086384915,0.00607388,0.00053728605,0.010268953],"genre_scores_gemma":[0.0064572752,0.35310176,0.000104868435,0.00016375748,0.00029630587,0.00016112854,0.0002819112,0.00003791179,0.6393951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812514,0.00047306248,0.00024649786,0.00036124274,0.00052432873,0.00026974073],"domain_scores_gemma":[0.99854064,0.00056803547,0.00020719341,0.0002569943,0.0003432569,0.00008388955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037566675,0.0001642435,0.0005349634,0.000027564656,0.0011044246,0.000086472646,0.0002531365,0.00009889404,0.00013968714],"category_scores_gemma":[0.00017562315,0.00010953279,0.00011007924,0.00031171727,0.0003151816,0.00013618116,0.0006299956,0.0001492593,0.0000146202265],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029912952,0.000085357846,0.0054888735,0.025639018,0.00017558105,0.0001028579,0.005856626,3.5819067e-8,2.5789979e-7,0.00009091254,0.958009,0.0045215525],"study_design_scores_gemma":[0.00084860664,0.00013790505,0.00531433,0.011608539,0.0008749019,0.000019667676,0.24603179,0.000015781468,6.8271305e-8,0.0000026481625,0.73488396,0.00026181646],"about_ca_topic_score_codex":0.020967713,"about_ca_topic_score_gemma":0.26057014,"teacher_disagreement_score":0.62912613,"about_ca_system_score_codex":0.00017428763,"about_ca_system_score_gemma":0.00010122614,"threshold_uncertainty_score":0.9855518},"labels":[],"label_agreement":null},{"id":"W4401163117","doi":"10.1162/qss_a_00319/v3/review1","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Geography; Library science; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163117","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28889334,0.5225206,0.00013366547,0.08197879,0.0032085616,0.086384915,0.00607388,0.00053728605,0.010268953],"genre_scores_gemma":[0.0064572752,0.35310176,0.000104868435,0.00016375748,0.00029630587,0.00016112854,0.0002819112,0.00003791179,0.6393951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812514,0.00047306248,0.00024649786,0.00036124274,0.00052432873,0.00026974073],"domain_scores_gemma":[0.99854064,0.00056803547,0.00020719341,0.0002569943,0.0003432569,0.00008388955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037566675,0.0001642435,0.0005349634,0.000027564656,0.0011044246,0.000086472646,0.0002531365,0.00009889404,0.00013968714],"category_scores_gemma":[0.00017562315,0.00010953279,0.00011007924,0.00031171727,0.0003151816,0.00013618116,0.0006299956,0.0001492593,0.0000146202265],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029912952,0.000085357846,0.0054888735,0.025639018,0.00017558105,0.0001028579,0.005856626,3.5819067e-8,2.5789979e-7,0.00009091254,0.958009,0.0045215525],"study_design_scores_gemma":[0.00084860664,0.00013790505,0.00531433,0.011608539,0.0008749019,0.000019667676,0.24603179,0.000015781468,6.8271305e-8,0.0000026481625,0.73488396,0.00026181646],"about_ca_topic_score_codex":0.020967713,"about_ca_topic_score_gemma":0.26057014,"teacher_disagreement_score":0.62912613,"about_ca_system_score_codex":0.00017428763,"about_ca_system_score_gemma":0.00010122614,"threshold_uncertainty_score":0.9855518},"labels":[],"label_agreement":null},{"id":"W4401163120","doi":"10.1162/qss_a_00319/v1/review3","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Library science; Regional science; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163120","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28889334,0.5225206,0.00013366547,0.08197879,0.0032085616,0.086384915,0.00607388,0.00053728605,0.010268953],"genre_scores_gemma":[0.0064572752,0.35310176,0.000104868435,0.00016375748,0.00029630587,0.00016112854,0.0002819112,0.00003791179,0.6393951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812514,0.00047306248,0.00024649786,0.00036124274,0.00052432873,0.00026974073],"domain_scores_gemma":[0.99854064,0.00056803547,0.00020719341,0.0002569943,0.0003432569,0.00008388955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037566675,0.0001642435,0.0005349634,0.000027564656,0.0011044246,0.000086472646,0.0002531365,0.00009889404,0.00013968714],"category_scores_gemma":[0.00017562315,0.00010953279,0.00011007924,0.00031171727,0.0003151816,0.00013618116,0.0006299956,0.0001492593,0.0000146202265],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029912952,0.000085357846,0.0054888735,0.025639018,0.00017558105,0.0001028579,0.005856626,3.5819067e-8,2.5789979e-7,0.00009091254,0.958009,0.0045215525],"study_design_scores_gemma":[0.00084860664,0.00013790505,0.00531433,0.011608539,0.0008749019,0.000019667676,0.24603179,0.000015781468,6.8271305e-8,0.0000026481625,0.73488396,0.00026181646],"about_ca_topic_score_codex":0.020967713,"about_ca_topic_score_gemma":0.26057014,"teacher_disagreement_score":0.62912613,"about_ca_system_score_codex":0.00017428763,"about_ca_system_score_gemma":0.00010122614,"threshold_uncertainty_score":0.9855518},"labels":[],"label_agreement":null},{"id":"W4401163268","doi":"10.1162/qss_a_00319/v1/review2","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Psychology; Library science; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163268","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28889334,0.5225206,0.00013366547,0.08197879,0.0032085616,0.086384915,0.00607388,0.00053728605,0.010268953],"genre_scores_gemma":[0.0064572752,0.35310176,0.000104868435,0.00016375748,0.00029630587,0.00016112854,0.0002819112,0.00003791179,0.6393951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812514,0.00047306248,0.00024649786,0.00036124274,0.00052432873,0.00026974073],"domain_scores_gemma":[0.99854064,0.00056803547,0.00020719341,0.0002569943,0.0003432569,0.00008388955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037566675,0.0001642435,0.0005349634,0.000027564656,0.0011044246,0.000086472646,0.0002531365,0.00009889404,0.00013968714],"category_scores_gemma":[0.00017562315,0.00010953279,0.00011007924,0.00031171727,0.0003151816,0.00013618116,0.0006299956,0.0001492593,0.0000146202265],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029912952,0.000085357846,0.0054888735,0.025639018,0.00017558105,0.0001028579,0.005856626,3.5819067e-8,2.5789979e-7,0.00009091254,0.958009,0.0045215525],"study_design_scores_gemma":[0.00084860664,0.00013790505,0.00531433,0.011608539,0.0008749019,0.000019667676,0.24603179,0.000015781468,6.8271305e-8,0.0000026481625,0.73488396,0.00026181646],"about_ca_topic_score_codex":0.020967713,"about_ca_topic_score_gemma":0.26057014,"teacher_disagreement_score":0.62912613,"about_ca_system_score_codex":0.00017428763,"about_ca_system_score_gemma":0.00010122614,"threshold_uncertainty_score":0.9855518},"labels":[],"label_agreement":null},{"id":"W4401163547","doi":"10.1162/qss_a_00319/v2/review3","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Psychology; Sociology; Mathematics; Combinatorics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163547","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28889334,0.5225206,0.00013366547,0.08197879,0.0032085616,0.086384915,0.00607388,0.00053728605,0.010268953],"genre_scores_gemma":[0.0064572752,0.35310176,0.000104868435,0.00016375748,0.00029630587,0.00016112854,0.0002819112,0.00003791179,0.6393951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812514,0.00047306248,0.00024649786,0.00036124274,0.00052432873,0.00026974073],"domain_scores_gemma":[0.99854064,0.00056803547,0.00020719341,0.0002569943,0.0003432569,0.00008388955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037566675,0.0001642435,0.0005349634,0.000027564656,0.0011044246,0.000086472646,0.0002531365,0.00009889404,0.00013968714],"category_scores_gemma":[0.00017562315,0.00010953279,0.00011007924,0.00031171727,0.0003151816,0.00013618116,0.0006299956,0.0001492593,0.0000146202265],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029912952,0.000085357846,0.0054888735,0.025639018,0.00017558105,0.0001028579,0.005856626,3.5819067e-8,2.5789979e-7,0.00009091254,0.958009,0.0045215525],"study_design_scores_gemma":[0.00084860664,0.00013790505,0.00531433,0.011608539,0.0008749019,0.000019667676,0.24603179,0.000015781468,6.8271305e-8,0.0000026481625,0.73488396,0.00026181646],"about_ca_topic_score_codex":0.020967713,"about_ca_topic_score_gemma":0.26057014,"teacher_disagreement_score":0.62912613,"about_ca_system_score_codex":0.00017428763,"about_ca_system_score_gemma":0.00010122614,"threshold_uncertainty_score":0.9855518},"labels":[],"label_agreement":null},{"id":"W4401172997","doi":"10.55016/ojs/ajer.v70i2.79716","title":"Interests, Knowledge and Evaluation: Alternative Approaches to Curriculum Evaluation","year":2024,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Curriculum; Permission; Index (typography); Sociology; Mathematics education; Psychology; Engineering ethics; Pedagogy; Epistemology; Computer science; Philosophy; Engineering","score_opus":0.45716967945896014,"score_gpt":0.5623502702934415,"score_spread":0.10518059083448139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401172997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7051899,0.006309166,0.000007302825,0.041228134,0.0012650364,0.00054103154,8.124224e-7,8.3752485e-7,0.2454578],"genre_scores_gemma":[0.98463297,0.00022955298,0.00015138181,0.000020826406,0.0019521666,0.00006686029,0.000005095935,0.000008074585,0.012933049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964271,0.0010193312,0.0002678905,0.00019475771,0.0018520933,0.00023880095],"domain_scores_gemma":[0.99102503,0.007004171,0.000059739734,0.00008162049,0.0016110982,0.00021831387],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009072411,0.00007438621,0.00010713717,0.000491213,0.00032593793,0.00036153413,0.0003245114,0.0000449186,0.0077193016],"category_scores_gemma":[0.007593703,0.00006223749,0.000053471267,0.0007638368,0.00017376126,0.00047306335,0.000080641184,0.00028819323,0.00032970705],"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":[0.00005049772,0.00072790874,0.08051947,0.0000630255,0.00034428434,7.889476e-7,0.1462632,0.00006857129,0.00006519779,0.55329376,0.15155031,0.06705297],"study_design_scores_gemma":[0.0015159799,0.00091273006,0.21914831,0.0015164122,0.0004608957,0.000048416132,0.08973035,0.02073996,0.00010065321,0.08280741,0.5823671,0.0006517506],"about_ca_topic_score_codex":0.0009842712,"about_ca_topic_score_gemma":0.004076205,"teacher_disagreement_score":0.47048637,"about_ca_system_score_codex":0.0006124792,"about_ca_system_score_gemma":0.0030227026,"threshold_uncertainty_score":0.9931878},"labels":[],"label_agreement":null},{"id":"W4401285935","doi":"10.18260/1-2--46845","title":"Board 271: Evaluating the Effect of Multi-Attempt Digital Assessments on Student Performance in Foundation Engineering Courses","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation Cluster (Canada)","funders":"Directorate for STEM Education; National Science Foundation; National Institutes of Health; Ministry of Education, Science and Technology; University of Cincinnati; American Society for Engineering Education","keywords":"Foundation (evidence); Computer science; Engineering management; Engineering; Political science","score_opus":0.044307724525487306,"score_gpt":0.44155303277887287,"score_spread":0.39724530825338555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401285935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98751867,0.00004769418,0.00016667189,0.00017824439,0.00086229865,0.00047783132,8.2193867e-7,0.0000656197,0.010682129],"genre_scores_gemma":[0.99829865,0.000026136837,0.00008817625,0.000012236318,0.000103489176,0.00004488741,0.000003463876,0.000009436684,0.0014134995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99863094,0.000090632566,0.00019885758,0.00017018845,0.00071045914,0.00019893979],"domain_scores_gemma":[0.9991885,0.0006221544,0.000040202925,0.0000968043,0.000027200475,0.000025169842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013652463,0.000105479834,0.00012957939,0.00008827145,0.00012557786,0.000330239,0.00021568792,0.00003553114,0.00008002993],"category_scores_gemma":[0.00008813052,0.00006903858,0.000052535463,0.000295891,0.00004882864,0.000418521,0.000050375093,0.00012804529,0.00005338652],"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":[0.000022135488,0.000088441295,0.9518616,0.00006801624,0.00006855548,0.0000018809462,0.0064690025,0.0020090546,0.0003029163,0.0010224195,0.0000890896,0.03799685],"study_design_scores_gemma":[0.00097186037,0.0012577291,0.90997356,0.00043706447,0.00005033349,2.0531321e-7,0.0058392463,0.07907942,0.0003893299,0.000007692726,0.001748162,0.0002454164],"about_ca_topic_score_codex":0.000084061285,"about_ca_topic_score_gemma":0.000081114515,"teacher_disagreement_score":0.07707036,"about_ca_system_score_codex":0.00016212404,"about_ca_system_score_gemma":0.000058018533,"threshold_uncertainty_score":0.31845024},"labels":[],"label_agreement":null},{"id":"W4401394229","doi":"10.1111/medu.15487","title":"The pitfalls and perils of anonymous learner feedback","year":2024,"lang":"en","type":"letter","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medical education; Psychology; MEDLINE; Medicine; Computer science; Political science","score_opus":0.014215028337451533,"score_gpt":0.35567680161570403,"score_spread":0.3414617732782525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401394229","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00287153,0.004625095,0.0000022932572,0.93232906,0.0038208365,0.00023186141,0.0000019122726,0.000030228044,0.056087162],"genre_scores_gemma":[0.012094878,0.00989538,0.00008381517,0.6688433,0.022259971,0.00011491484,0.00010327837,0.00005497725,0.28654945],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978846,0.00020091266,0.00024260345,0.00022912405,0.0011858527,0.00025694305],"domain_scores_gemma":[0.99919814,0.00037049476,0.000104548446,0.00016091052,0.00009440738,0.00007150603],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00091352407,0.00012149202,0.00017599859,0.00005803863,0.00028445938,0.00017559904,0.00038050523,0.0005040893,0.0010078022],"category_scores_gemma":[0.00078258006,0.0000813263,0.00006883606,0.00018873696,0.0007329614,0.000055222397,0.000070589515,0.0008450583,0.000111964175],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015410377,0.000023327935,0.0003532061,0.000053154457,0.000024038485,0.0000025661927,0.005499767,3.7777617e-9,7.825827e-7,0.0014161629,0.96685374,0.025771689],"study_design_scores_gemma":[0.000047449164,0.000016871292,0.0008633915,0.00012090503,0.0000436796,0.0000012081341,0.0035025505,0.0000027027359,6.6597016e-7,0.00096047425,0.9943426,0.000097457196],"about_ca_topic_score_codex":0.00064739265,"about_ca_topic_score_gemma":0.00026852993,"teacher_disagreement_score":0.26348573,"about_ca_system_score_codex":0.00007604619,"about_ca_system_score_gemma":0.00219286,"threshold_uncertainty_score":0.9999054},"labels":[],"label_agreement":null},{"id":"W4401488009","doi":"10.37546/jalttlt48.5-1","title":"JALT2024 Plenary Speaker: Toward Justice-Affirming Language Teaching","year":2024,"lang":"en","type":"article","venue":"The Language Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Plenary session; Linguistics; Economic Justice; Sociology; Psychology; Political science; Computer science; Philosophy; Law; Library science","score_opus":0.03437048302652522,"score_gpt":0.3838888456095768,"score_spread":0.3495183625830516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401488009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59543866,0.008682797,0.00016613933,0.006322274,0.0013461779,0.00032075445,0.0000069205184,0.0007784203,0.38693786],"genre_scores_gemma":[0.91585547,0.00006487253,0.00030513777,0.0004277759,0.0031786931,0.000018726087,0.000010760886,0.00003983466,0.080098756],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9980151,0.00041534242,0.00019520937,0.00031140927,0.00055181404,0.0005110913],"domain_scores_gemma":[0.99921834,0.00031932374,0.00004107242,0.0003122356,0.000012291643,0.00009672982],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019958804,0.00018605111,0.00017369409,0.00008389793,0.00059473905,0.00044036892,0.0005063861,0.00010547696,0.002917869],"category_scores_gemma":[0.00019247617,0.00012894778,0.00014430219,0.00026719147,0.00017024127,0.00027266666,0.00016799729,0.00070833584,0.0011066453],"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":[0.000010779292,0.00006250706,0.0007744165,0.00007486873,0.000107715445,0.00034985886,0.9044192,0.0000026746266,0.0016342018,0.015331425,0.03035842,0.046873968],"study_design_scores_gemma":[0.00024261152,0.000034378183,0.0014655103,0.00016736025,0.00035979899,0.00001369088,0.7985085,0.0004925452,0.00007834172,0.00033521804,0.19786286,0.00043916987],"about_ca_topic_score_codex":0.0030324678,"about_ca_topic_score_gemma":0.0006373502,"teacher_disagreement_score":0.3204168,"about_ca_system_score_codex":0.00014315546,"about_ca_system_score_gemma":0.00009548416,"threshold_uncertainty_score":0.9996711},"labels":[],"label_agreement":null},{"id":"W4401490251","doi":"10.1186/s41239-024-00483-0","title":"Rethinking assessment strategies to improve authentic representations of learning: using blogs as a creative assessment alternative to develop professional skills","year":2024,"lang":"en","type":"article","venue":"International Journal of Educational Technology in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Higher education; Authentic learning; Psychology; Pedagogy; Mathematics education; Sociology; Knowledge management; Computer science; Political science","score_opus":0.03685730727687135,"score_gpt":0.4836799594142759,"score_spread":0.4468226521374045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401490251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.836302,0.00016343557,0.0006673809,0.14010322,0.0112504065,0.0005559285,0.000008536174,0.00002893009,0.010920205],"genre_scores_gemma":[0.9645275,0.000040709358,0.025250586,0.00017521794,0.00095979177,0.00012674025,0.000022256694,0.000019770969,0.008877412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99705905,0.00025477703,0.0008775672,0.0003516947,0.0012004258,0.00025648953],"domain_scores_gemma":[0.9958414,0.0006699674,0.000549472,0.00013259034,0.0026815506,0.000125047],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011200855,0.00018317849,0.0002674252,0.0021683045,0.00018734681,0.00022742583,0.0007457871,0.0001705531,0.0011984772],"category_scores_gemma":[0.0007689614,0.00018139408,0.00008658572,0.0017923904,0.00019100338,0.00072922115,0.0001568091,0.0006165941,0.00002155769],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003520977,0.0010625267,0.08076437,0.000017860515,0.00033315903,0.0000079517495,0.036337417,0.00094240234,0.0054085236,0.8724022,0.0010525524,0.001635817],"study_design_scores_gemma":[0.00044361403,0.0002736369,0.28249297,0.0013366999,0.000089546564,0.000027378974,0.058732126,0.00011634359,0.00060051336,0.64908147,0.0064758104,0.00032993668],"about_ca_topic_score_codex":0.0005413748,"about_ca_topic_score_gemma":0.000080725804,"teacher_disagreement_score":0.22332077,"about_ca_system_score_codex":0.0018241275,"about_ca_system_score_gemma":0.010456308,"threshold_uncertainty_score":0.99971455},"labels":[],"label_agreement":null},{"id":"W4401820437","doi":"10.1177/01614681200310507004","title":"<i>The Assessment Bridge: Positive Ways to Link tests to Learning, Standards, and Curriculum Improvement</i> Pearl G. Solomon. Thousand Oaks: Corwin Press, 2002, ISBN: 0761945946, 160 pp.","year":2003,"lang":"en","type":"article","venue":"Teachers College Record The Voice of Scholarship in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Learning Partnership","funders":"","keywords":"Pearl; Bridge (graph theory); Link (geometry); Curriculum; Engineering; Psychology; History; Pedagogy; Computer science; Archaeology; Medicine; Internal medicine","score_opus":0.017954572781727678,"score_gpt":0.348182233804585,"score_spread":0.33022766102285733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401820437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9384585,0.0029407612,0.00020672526,0.012385185,0.0023819662,0.0038372085,0.00004823112,0.000081177364,0.039660253],"genre_scores_gemma":[0.9820724,0.0024339508,0.0027119927,0.00043147022,0.00045018079,0.00041129004,0.000009207712,0.00004798125,0.011431515],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963456,0.0010666524,0.00052066107,0.0005049851,0.0009399777,0.0006221465],"domain_scores_gemma":[0.9977983,0.0006728363,0.0003381512,0.00036269598,0.0005537377,0.0002742309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070292414,0.00027544633,0.00030621907,0.00012061191,0.0012839609,0.00045037377,0.00063075195,0.00016678308,0.000066270244],"category_scores_gemma":[0.0020094544,0.00021718294,0.00007871326,0.000959139,0.00022833118,0.0005349689,0.00013047208,0.0008398042,0.000016939923],"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":[0.00027412115,0.0017922139,0.6480097,0.00007313384,0.00023307619,0.0000039590664,0.088485025,0.00005017784,0.002916507,0.017616104,0.121011496,0.11953445],"study_design_scores_gemma":[0.0010686272,0.00079842546,0.2483854,0.00034679376,0.000119830154,0.0000026543298,0.10076551,0.000028777888,0.00029811467,0.0012084424,0.64635175,0.0006256372],"about_ca_topic_score_codex":0.003459477,"about_ca_topic_score_gemma":0.006954564,"teacher_disagreement_score":0.52534026,"about_ca_system_score_codex":0.0008746506,"about_ca_system_score_gemma":0.0013869527,"threshold_uncertainty_score":0.9875319},"labels":[],"label_agreement":null},{"id":"W4401977588","doi":"10.26522/brocked.v33i3.1179","title":"The Role of Students’ Assessment Literacies in Navigating University Assessment, GenAI, and Academic Integrity","year":2024,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Academic integrity; Psychology; Pedagogy; Surface integrity; Mathematics education; Sociology; Engineering ethics; Social psychology; Engineering","score_opus":0.021832631080602738,"score_gpt":0.4204782449096844,"score_spread":0.39864561382908165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401977588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98635185,0.0027936865,0.000087414235,0.0025217019,0.00087501144,0.0001582179,0.0000017539815,0.000016664648,0.007193684],"genre_scores_gemma":[0.9938068,0.0035802505,0.00071178074,0.000029718609,0.00029813562,0.0000024370772,0.0000016931102,0.0000050083245,0.001564211],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99859595,0.00032988982,0.0002541043,0.00012899263,0.0005017502,0.00018928811],"domain_scores_gemma":[0.9992333,0.00031209557,0.00014059502,0.00006277748,0.00013931822,0.00011192524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010941522,0.000077102486,0.0000998668,0.00008957596,0.000694185,0.00042575825,0.00036222188,0.00006782821,0.000055394234],"category_scores_gemma":[0.00008701702,0.000062257925,0.00004563919,0.00037578525,0.000116981166,0.00052078784,0.000087122586,0.0010816071,0.0000020750294],"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":[0.0000047524777,0.000076174474,0.9146669,0.000013406385,0.000030235538,0.0000011858567,0.017338552,0.0000010628613,0.0004605095,0.023305042,0.00088335294,0.043218862],"study_design_scores_gemma":[0.0001420407,0.00002544335,0.6704834,0.00034860906,0.000024262417,0.0000074156724,0.25843257,0.00008528971,0.000014310841,0.007681855,0.06266101,0.00009378368],"about_ca_topic_score_codex":0.0002675551,"about_ca_topic_score_gemma":0.00018412247,"teacher_disagreement_score":0.24418347,"about_ca_system_score_codex":0.0003669189,"about_ca_system_score_gemma":0.0016620012,"threshold_uncertainty_score":0.53391796},"labels":[],"label_agreement":null},{"id":"W4401993837","doi":"10.4018/979-8-3693-1499-9.ch010","title":"(Re)Visiting the Efficacy of PBLA for Adult EAL Learners in College-Based Education in Canada","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Seneca Polytechnic; University of Manitoba","funders":"","keywords":"Medical education; Evaluation methods; Medicine; Engineering","score_opus":0.019556463771628847,"score_gpt":0.34717462499875557,"score_spread":0.3276181612271267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401993837","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03288701,0.030704735,0.0000012041062,0.03274095,0.016531615,0.0036601557,0.00004195145,0.00003346904,0.8833989],"genre_scores_gemma":[0.118436724,0.0020280173,0.000725354,0.0013647316,0.00025840136,0.000421055,0.00012552463,0.000026885951,0.8766133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853367,0.000056675985,0.00050658366,0.00029199725,0.00039815396,0.00021294355],"domain_scores_gemma":[0.99896973,0.0005194121,0.00022257575,0.00008365896,0.00015715542,0.000047449736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034367727,0.00019603442,0.00024602958,0.00020524654,0.00019108759,0.000023780045,0.00018612918,0.000118493685,0.00029913813],"category_scores_gemma":[0.00004481879,0.00016305866,0.000028625482,0.0001359777,0.00014154175,0.00032756774,0.00004126751,0.00025601522,0.0000023202956],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023552442,0.00017601188,0.042197764,0.00054640137,0.000023501596,0.0000015338766,0.015339068,0.000028120372,0.0000017957577,0.9113745,0.006556625,0.023519121],"study_design_scores_gemma":[0.00033224394,0.000012693117,0.04282325,0.0017570432,0.000008955813,1.0681484e-7,0.026184293,0.0000016711115,0.000009120789,0.00943043,0.9191964,0.00024376113],"about_ca_topic_score_codex":0.018826555,"about_ca_topic_score_gemma":0.67592394,"teacher_disagreement_score":0.9126398,"about_ca_system_score_codex":0.0008557163,"about_ca_system_score_gemma":0.019534852,"threshold_uncertainty_score":0.98770714},"labels":[],"label_agreement":null},{"id":"W4402109653","doi":"10.55016/ojs/jet.v44i2.52245","title":"Assessment Reform and the Case for Learning-Focused Accountability","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Accountability; Political science; Public administration; Psychology; Business; Law","score_opus":0.039596859012279245,"score_gpt":0.42432877390869944,"score_spread":0.3847319148964202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402109653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8988443,0.00023587234,0.00028366284,0.042842302,0.0019789007,0.00033767504,0.0000026735072,0.00000540339,0.05546922],"genre_scores_gemma":[0.98671156,0.000063110114,0.006828721,0.00015895822,0.0037963444,0.000013681893,8.004941e-7,0.0000051195307,0.0024216964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990159,0.00017957402,0.00027475716,0.00008515774,0.00030307533,0.00014150052],"domain_scores_gemma":[0.99743176,0.0014635819,0.00032071568,0.00007195903,0.0006386181,0.000073396695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032113404,0.00006316029,0.0001378279,0.000044672484,0.0008693001,0.00013948363,0.00017902828,0.000040189072,0.00035529144],"category_scores_gemma":[0.00068116456,0.00003823135,0.000089501365,0.00013919463,0.00052192237,0.00028757364,0.000025859648,0.00015394836,0.0000040094455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002390444,0.00022057559,0.054059573,0.000011115756,0.00010769453,0.0000025281058,0.015466228,0.0000011121031,0.000022358847,0.9193437,0.007180294,0.0033457766],"study_design_scores_gemma":[0.00505311,0.00057785044,0.27034488,0.000055623605,0.00022860964,0.00027562305,0.099228285,0.00013092528,0.000029087185,0.11115986,0.51261765,0.00029848702],"about_ca_topic_score_codex":0.00035062683,"about_ca_topic_score_gemma":0.0006211376,"teacher_disagreement_score":0.80818385,"about_ca_system_score_codex":0.0002735564,"about_ca_system_score_gemma":0.000651731,"threshold_uncertainty_score":0.66860414},"labels":[],"label_agreement":null},{"id":"W4402109725","doi":"10.55016/ojs/jet.v51i3.68273","title":"Exploring the Intersection Between Culturally Responsive Pedagogy and Academic Integrity Among EAL Students in Canadian Higher Education","year":2019,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Academic integrity; Intersection (aeronautics); Pedagogy; Sociology; Culturally sensitive; Psychology; Mathematics education; Social psychology; Geography","score_opus":0.11088557053978763,"score_gpt":0.44686615418647285,"score_spread":0.3359805836466852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402109725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688214,0.00017062666,4.0261745e-7,0.022484923,0.0030647551,0.00020051633,0.0000012210775,0.0000021151343,0.0052540377],"genre_scores_gemma":[0.98958325,0.00019053603,0.00011041918,0.00018383197,0.002166455,0.000012317996,0.0000033059277,0.0000057630523,0.007744139],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986111,0.00027888143,0.00031639184,0.00011337068,0.00046843858,0.00021179831],"domain_scores_gemma":[0.99880993,0.0004427925,0.00024236682,0.000063617685,0.0002631709,0.00017811244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013719667,0.00008303367,0.00013686156,0.0002098005,0.00020658103,0.00010751091,0.000359751,0.00007416992,0.00025183114],"category_scores_gemma":[0.00023730892,0.00006138762,0.000047488382,0.0003117292,0.000091819915,0.00092571037,0.00003210399,0.0006924125,0.00001862755],"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":[0.000017399907,0.00002778211,0.9685371,0.0000026443254,0.000021684275,2.297439e-7,0.014240928,0.0000013814788,0.000028364402,0.015249481,0.001067086,0.00080593023],"study_design_scores_gemma":[0.00014593378,0.000029912413,0.94923335,0.00008276596,0.000016850143,0.0000019524666,0.025339296,2.9756734e-7,0.000005526793,0.001682483,0.023393186,0.000068430156],"about_ca_topic_score_codex":0.06906751,"about_ca_topic_score_gemma":0.108420365,"teacher_disagreement_score":0.039352857,"about_ca_system_score_codex":0.000806632,"about_ca_system_score_gemma":0.0026504577,"threshold_uncertainty_score":0.93713164},"labels":[],"label_agreement":null},{"id":"W4402441614","doi":"10.1002/berj.4065","title":"From challenge to innovation: A grassroots study of teachers’ classroom assessment innovations","year":2024,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Winnipeg; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Grassroots; Sociology; Pedagogy; Mathematics education; Educational research; Psychology; Political science; Public relations","score_opus":0.17608076029473863,"score_gpt":0.5171086715530592,"score_spread":0.34102791125832055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402441614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91339475,0.0004347332,0.00016477752,0.045942403,0.0014103475,0.0006728558,0.000025024548,0.000024318622,0.037930813],"genre_scores_gemma":[0.98818296,0.0002103784,0.0012344971,0.000056697703,0.003432943,0.0001535222,0.000030168487,0.000019315778,0.006679515],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9951455,0.00061880983,0.00060799095,0.00033857612,0.0028168708,0.0004722569],"domain_scores_gemma":[0.99632937,0.0011041444,0.00009404157,0.00016047372,0.002099711,0.00021224996],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00474943,0.00010080408,0.00017593238,0.0009917119,0.0011351338,0.0013501358,0.0006114021,0.00008205396,0.0037443824],"category_scores_gemma":[0.0014703615,0.00012119286,0.000053283326,0.004280618,0.00017166999,0.00057846244,0.00013421009,0.0009571407,0.00008076233],"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":[0.000019791374,0.0047606668,0.15026736,0.000020255888,0.00044432573,0.00007049441,0.1049615,0.000009741741,0.00047743582,0.21127008,0.44414437,0.08355398],"study_design_scores_gemma":[0.0004742985,0.0003610779,0.7101516,0.00030516283,0.000018354234,0.000012241887,0.121139996,0.0000108714385,0.00000285631,0.04145266,0.12588328,0.00018757222],"about_ca_topic_score_codex":0.0057354057,"about_ca_topic_score_gemma":0.0045561786,"teacher_disagreement_score":0.55988425,"about_ca_system_score_codex":0.00076092256,"about_ca_system_score_gemma":0.0038970802,"threshold_uncertainty_score":0.99968654},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8896041,0.0006415185,0.000058434838,0.08524258,0.0061541144,0.0027050844,0.0000029512473,0.000093815266,0.015497406],"genre_scores_gemma":[0.9903855,0.00018152456,0.0009283224,0.0003360614,0.000891719,0.0004965505,0.00005191211,0.000026528327,0.00670192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9942298,0.0017463308,0.0005285681,0.00068745826,0.0023764533,0.0004313903],"domain_scores_gemma":[0.9980715,0.000673508,0.0005196324,0.00027659745,0.0003086214,0.00015016938],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009019918,0.00021948613,0.00028030275,0.00047899422,0.0002606064,0.002221458,0.00046027254,0.0001740526,0.0006111505],"category_scores_gemma":[0.00037594148,0.0002189967,0.000074570904,0.0011099642,0.000086821325,0.0015338789,0.00010074737,0.00038849848,0.000054196396],"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":[0.000027178205,0.0010510334,0.96253765,0.0000513131,0.000056099558,0.0000025271158,0.01423205,0.00005388881,0.00002129914,0.0075367154,0.006110632,0.0083196],"study_design_scores_gemma":[0.0007651558,0.00009047908,0.90904063,0.00048767915,0.000088551686,1.9586116e-7,0.06875982,0.0003584632,0.0000013886926,0.0018407118,0.018311245,0.00025564962],"about_ca_topic_score_codex":0.0002773158,"about_ca_topic_score_gemma":0.0027121753,"teacher_disagreement_score":0.10078136,"about_ca_system_score_codex":0.0021975574,"about_ca_system_score_gemma":0.0018963037,"threshold_uncertainty_score":0.99881434},"labels":[],"label_agreement":null},{"id":"W4402569962","doi":"10.1016/j.stueduc.2024.101403","title":"Students’ perceptions of online peer feedback in process-oriented L2 writing: A qualitative inquiry","year":2024,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Peer feedback; Perception; Mathematics education; Peer evaluation; Process (computing); Qualitative research; Psychology; Computer science; Pedagogy; Higher education; Sociology; Political science","score_opus":0.23009569155715098,"score_gpt":0.6111867833582557,"score_spread":0.38109109180110473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402569962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9827357,0.0017090138,0.000014077931,0.009389365,0.0015443044,0.00073184294,0.00001752447,0.000022088068,0.0038361081],"genre_scores_gemma":[0.9966377,0.00035502945,0.0005053199,0.00005231696,0.0006089288,0.00036545095,0.000148094,0.00000995379,0.0013171958],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9962819,0.0006463556,0.0005465794,0.00031750815,0.0019847318,0.0002229197],"domain_scores_gemma":[0.99737245,0.0009835773,0.00010810294,0.0000931884,0.001408244,0.000034453198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005441125,0.0001223373,0.00021273477,0.00039201285,0.00017689612,0.000044037817,0.00020441058,0.00006280413,0.00046279025],"category_scores_gemma":[0.0027702306,0.00012321843,0.000054149332,0.0013749416,0.0004947422,0.00037491476,0.000060106377,0.0001769045,0.000031532938],"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":[0.0000140699685,0.00066717016,0.18061171,0.00008253728,0.00007344085,3.2806832e-7,0.8027387,0.00010994683,0.00002114655,0.012573492,0.0018423027,0.0012651411],"study_design_scores_gemma":[0.00028190337,0.000023619767,0.39545518,0.00024172371,0.000029260043,1.2139775e-7,0.59188753,0.00014661196,9.921818e-7,0.011639823,0.00021001084,0.000083231644],"about_ca_topic_score_codex":0.00020868045,"about_ca_topic_score_gemma":0.0028360216,"teacher_disagreement_score":0.21484347,"about_ca_system_score_codex":0.00084633887,"about_ca_system_score_gemma":0.0011244292,"threshold_uncertainty_score":0.50672287},"labels":[],"label_agreement":null},{"id":"W4402676854","doi":"10.7202/1113588ar","title":"Flexible planning of assessment, a lever towards assessment for learning?","year":2022,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Lever; Assessment for learning; Computer science; Psychology; Engineering; Mathematics education; Formative assessment","score_opus":0.1283791028668994,"score_gpt":0.497807633715495,"score_spread":0.3694285308485956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402676854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6334174,0.00013558478,0.1547578,0.015644599,0.0039837956,0.00310557,0.00004896561,0.0003018388,0.1886044],"genre_scores_gemma":[0.98318744,0.000016416821,0.0087849805,0.00012775997,0.00018157918,0.00048297466,0.00030131044,0.000017729139,0.0068997876],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9951651,0.002834411,0.00033237317,0.00025970736,0.0011821304,0.00022628026],"domain_scores_gemma":[0.99864155,0.0005408573,0.00035247684,0.00013872616,0.0002848247,0.00004157427],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018046806,0.000110012305,0.00018145137,0.00017446854,0.00085655093,0.00007494799,0.00023983738,0.000056576064,0.0013104826],"category_scores_gemma":[0.0003936911,0.00012508966,0.000098173005,0.00041174135,0.000040814306,0.00030714978,0.00006979851,0.00023914444,0.0000032595672],"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":[0.00006817812,0.00080378016,0.3430253,0.000068572306,0.00018721334,4.6237557e-7,0.51140195,0.013595353,0.0026292063,0.07956571,0.025398748,0.02325552],"study_design_scores_gemma":[0.0008497456,0.0002308778,0.8617699,0.000014857772,0.000082778475,3.2147128e-7,0.053209245,0.0028092163,0.00010471847,0.0033770122,0.077347875,0.00020346363],"about_ca_topic_score_codex":0.00034079223,"about_ca_topic_score_gemma":0.00005619422,"teacher_disagreement_score":0.5187446,"about_ca_system_score_codex":0.0007373488,"about_ca_system_score_gemma":0.0023006129,"threshold_uncertainty_score":0.99960244},"labels":[],"label_agreement":null},{"id":"W4402746452","doi":"10.18357/otessac.2022.2.1.63","title":"“Students Feel More Dignified\": Alternative Grading and Self-Assessment in Online Courses","year":2023,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; Engineering","score_opus":0.05205153241904463,"score_gpt":0.43092948254411895,"score_spread":0.3788779501250743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402746452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9498709,0.00013727164,0.0000066164716,0.047657054,0.0003546192,0.0006758781,0.0000074927866,0.000096898984,0.0011932956],"genre_scores_gemma":[0.9914972,0.0059383633,0.00049027003,0.00052591274,0.00006698009,0.00017336466,0.000023144006,0.000008862043,0.001275909],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981317,0.0003534496,0.00029494293,0.00035093052,0.00050461217,0.00036434853],"domain_scores_gemma":[0.99883956,0.00046554068,0.00027097767,0.0001566591,0.00021128179,0.000055998273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035352889,0.00014171506,0.00023027475,0.00016969751,0.00072384556,0.0005862445,0.00083779765,0.00029194404,0.000022867876],"category_scores_gemma":[0.0003437835,0.00013281938,0.00003228393,0.0013145529,0.00020911638,0.00068612234,0.000395152,0.00071075227,0.0000075739104],"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":[0.0000028223872,0.00026613194,0.9203477,0.0000052239175,0.00003840096,5.1467873e-7,0.03129873,0.0000013986,0.000042130316,0.04524717,0.00041917275,0.0023306222],"study_design_scores_gemma":[0.0005319266,0.000016638409,0.8248856,0.00006238712,0.000017399154,2.9403563e-7,0.14535438,0.00013637416,0.000010729383,0.027611366,0.0012371667,0.00013575408],"about_ca_topic_score_codex":0.0007005855,"about_ca_topic_score_gemma":0.0016956785,"teacher_disagreement_score":0.11405564,"about_ca_system_score_codex":0.0007343289,"about_ca_system_score_gemma":0.00068895856,"threshold_uncertainty_score":0.565317},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86613864,0.00076284097,0.00015973777,0.0098765865,0.0081937285,0.002107327,0.000004345092,0.00010768058,0.112649135],"genre_scores_gemma":[0.98518676,0.000106212785,0.0021385744,0.00014955146,0.0006376542,0.0012285751,0.0001705372,0.000038655293,0.010343486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951348,0.0009686089,0.0007892225,0.0006196498,0.0020809537,0.00040678936],"domain_scores_gemma":[0.9983947,0.0003643012,0.00030643193,0.0003337024,0.00049588445,0.000104948944],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003671447,0.00026161992,0.0003158285,0.00080089155,0.00026579606,0.00046824574,0.0004209279,0.00017562449,0.0058099977],"category_scores_gemma":[0.00003322743,0.00026180787,0.000074778516,0.0019734967,0.00009748338,0.0011681685,0.000060987993,0.00042289976,0.000029194964],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017140175,0.0021997332,0.7342402,0.00010667238,0.0000713238,9.113738e-7,0.0075757294,0.00038741573,0.00034124692,0.23644115,0.0015240429,0.017094433],"study_design_scores_gemma":[0.0007089061,0.000088669294,0.9484112,0.00061993714,0.00015267977,5.0229784e-7,0.021160338,0.00041965878,0.000014683249,0.006377486,0.021731105,0.0003147954],"about_ca_topic_score_codex":0.0020853889,"about_ca_topic_score_gemma":0.0018798994,"teacher_disagreement_score":0.23006366,"about_ca_system_score_codex":0.002864198,"about_ca_system_score_gemma":0.0060352376,"threshold_uncertainty_score":0.99998343},"labels":[],"label_agreement":null},{"id":"W4403600135","doi":"10.1007/s44217-024-00258-9","title":"Improving teaching effectiveness: feedback preferences by teachers on a faculty facing dashboard","year":2024,"lang":"en","type":"article","venue":"Discover Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Dashboard; Mathematics education; Medical education; Computer science; Psychology; Data science; Medicine","score_opus":0.023699125449706617,"score_gpt":0.38396114107304335,"score_spread":0.36026201562333676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403600135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9360744,0.00033052496,0.0005252173,0.0006463545,0.0019002414,0.0004356623,0.000017970917,0.00018140954,0.05988824],"genre_scores_gemma":[0.99323446,0.000022617296,0.00014039828,0.000082339146,0.00045997568,0.000096657415,0.00011720168,0.000017509712,0.0058288514],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9984109,0.00030269538,0.000150903,0.000400387,0.0004488322,0.000286311],"domain_scores_gemma":[0.9994691,0.00023347129,0.00005930453,0.00012704772,0.000029431552,0.00008167034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008263724,0.00015938263,0.00013121372,0.00009537133,0.00050910853,0.0007887802,0.00022651083,0.00008637545,0.000076101605],"category_scores_gemma":[0.00016034293,0.00013856251,0.000082173916,0.00020712851,0.00007602443,0.00085020653,0.00003391775,0.0002896101,0.00014353993],"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":[0.000050599752,0.0008165569,0.14612557,0.00026138432,0.00019436503,0.0000013349386,0.22686914,0.000032550197,0.0119789345,0.046789475,0.053739976,0.51314014],"study_design_scores_gemma":[0.00092292065,0.00039535153,0.18942174,0.0021054377,0.000300951,0.000001147134,0.43966156,0.00040322295,0.003127851,0.0056688352,0.35618144,0.0018095345],"about_ca_topic_score_codex":0.004675735,"about_ca_topic_score_gemma":0.0001668124,"teacher_disagreement_score":0.5113306,"about_ca_system_score_codex":0.00043127168,"about_ca_system_score_gemma":0.00056002993,"threshold_uncertainty_score":0.76062256},"labels":[],"label_agreement":null},{"id":"W4403674160","doi":"10.20360/langandlit29724","title":"“What’s the Use?”: Undoing, Decolonizing, Liberating, and Righting Literacies Assessment in Turbulent Times","year":2024,"lang":"en","type":"article","venue":"Language and Literacy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Undoing; Literacy; Sociology; Psychology; Pedagogy; Psychoanalysis","score_opus":0.019767530958709707,"score_gpt":0.3585840405335926,"score_spread":0.3388165095748829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403674160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9692436,0.020295657,0.000014800804,0.0040810946,0.0004887749,0.00027624948,0.0000022352606,0.00009129733,0.0055063237],"genre_scores_gemma":[0.9739529,0.0014464362,0.0008839595,0.00063743914,0.0003737368,0.000026335914,0.000008132399,0.000013331862,0.022657719],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.998803,0.00018806,0.00021018415,0.00027041443,0.00023961104,0.00028872845],"domain_scores_gemma":[0.99908143,0.0006697709,0.000044824927,0.00011518574,0.000026950383,0.000061822895],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00059630466,0.00013297648,0.00013693568,0.00009371825,0.00042543572,0.004489354,0.00010440798,0.00005645454,0.0002278698],"category_scores_gemma":[0.000054584434,0.00008997395,0.00003885826,0.00023463347,0.00012041379,0.0017561952,0.000092411516,0.00024760398,0.000007729936],"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":[0.00000589731,0.000045737692,0.047618892,0.00006646145,0.000043490985,0.00028080083,0.87253124,0.0000019475683,0.00009077495,0.03940056,0.0019708977,0.037943274],"study_design_scores_gemma":[0.0005965356,0.00009407812,0.09361143,0.0013534713,0.00007198082,0.000026446338,0.11486461,0.003948799,0.000031305262,0.0027469064,0.7821008,0.0005536511],"about_ca_topic_score_codex":0.0010278253,"about_ca_topic_score_gemma":0.00082273653,"teacher_disagreement_score":0.7801299,"about_ca_system_score_codex":0.000046312784,"about_ca_system_score_gemma":0.00006123298,"threshold_uncertainty_score":0.99654406},"labels":[],"label_agreement":null},{"id":"W4403899111","doi":"10.5539/jel.v14n2p74","title":"Scoring Difficulty in Summary Writing Assessment: Toward the Reconstruction of Analytic Rubric","year":2024,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Rubric; Psychology; Mathematics education; Evaluation methods","score_opus":0.030654970869895302,"score_gpt":0.38441113039933944,"score_spread":0.3537561595294441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403899111","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9830742,0.001783599,0.00008527492,0.0020716772,0.00084233354,0.00004425856,6.382867e-8,0.0000054949696,0.012093135],"genre_scores_gemma":[0.9975076,0.0010231895,0.00035663968,0.000015564323,0.00041935837,9.479759e-7,3.8217374e-7,0.0000029327252,0.0006734333],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992026,0.00019553932,0.00026184472,0.00005893717,0.00019927422,0.00008176768],"domain_scores_gemma":[0.99940526,0.00028131733,0.00017610814,0.00002307246,0.00008350679,0.000030726358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016357842,0.00003919381,0.000094258634,0.00017520641,0.00015582371,0.00013592871,0.0000691813,0.000026215337,0.00006739669],"category_scores_gemma":[0.0001740094,0.000028747221,0.000044618562,0.00035124164,0.000054568576,0.00028658236,0.000011078913,0.00035829007,5.310278e-7],"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":[0.000005264519,0.000054851735,0.6850118,0.000048920956,0.000034487817,0.0000016509481,0.050056815,0.00010710063,0.00051621516,0.0032441367,0.00023066044,0.26068813],"study_design_scores_gemma":[0.00013196755,0.000044470322,0.6565338,0.00088758545,0.00004310839,0.000018549017,0.33622956,0.0007213951,0.00000832156,0.00035514467,0.004960407,0.00006571333],"about_ca_topic_score_codex":0.00012561643,"about_ca_topic_score_gemma":0.00003074279,"teacher_disagreement_score":0.28617275,"about_ca_system_score_codex":0.000093362185,"about_ca_system_score_gemma":0.0003551876,"threshold_uncertainty_score":0.15566121},"labels":[],"label_agreement":null},{"id":"W4403985536","doi":"10.1080/08841233.2024.2408317","title":"Peer Feedback for Teaching Communication Skills: Students’ Experiences in a BSW Interviewing Skills Course","year":2024,"lang":"en","type":"article","venue":"Journal of Teaching in Social Work","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Social work; Interview; Medical education; Psychology; Communication skills; Course (navigation); Pedagogy; Medicine; Sociology","score_opus":0.03471179257880846,"score_gpt":0.4289714118564918,"score_spread":0.3942596192776833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403985536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97914004,0.0018566083,0.00036671179,0.009156172,0.0017281391,0.00035266927,0.0000014954094,0.00003936089,0.007358788],"genre_scores_gemma":[0.99306124,0.00012567698,0.0030560463,0.0001450014,0.0012798916,0.000037431128,0.0000027896813,0.000023918437,0.002268005],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.996221,0.0011540883,0.0008358045,0.00019859806,0.001169574,0.00042094575],"domain_scores_gemma":[0.9982702,0.0010756976,0.0003555487,0.000114987866,0.00010551393,0.000078068115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013451238,0.00017218864,0.00042197472,0.00028481585,0.0011021377,0.00069217396,0.0011087543,0.00016163457,0.00005945236],"category_scores_gemma":[0.0010187585,0.00015952386,0.00028454282,0.0005338927,0.00019877862,0.0008453615,0.00015566578,0.0013794163,0.000005936896],"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":[0.000029378982,0.0006769434,0.13665916,0.000021813137,0.00007287935,0.000014377637,0.82068074,0.000019234203,0.0000098066985,0.004980043,0.0101787895,0.026656838],"study_design_scores_gemma":[0.0012869278,0.00011140991,0.09901518,0.0026116117,0.00008419918,0.0000030319084,0.76874584,0.00004733186,0.000002880937,0.0041341046,0.12355734,0.00040016155],"about_ca_topic_score_codex":0.00017011072,"about_ca_topic_score_gemma":0.00051733165,"teacher_disagreement_score":0.11337855,"about_ca_system_score_codex":0.00059687294,"about_ca_system_score_gemma":0.00016426637,"threshold_uncertainty_score":0.84768635},"labels":[],"label_agreement":null},{"id":"W4404136350","doi":"10.1080/10511253.2024.2422314","title":"Teacher Reflections on Assessing Indigenous Cultural Competency in a Criminal Justice Subject Through Interactive Oral Assessment","year":2024,"lang":"en","type":"article","venue":"Journal of Criminal Justice Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Charles Sturt University","keywords":"Indigenous; Subject (documents); Criminal justice; Criminology; Psychology; Political science; Sociology; Computer science; Library science","score_opus":0.11624800203147558,"score_gpt":0.512853261473025,"score_spread":0.39660525944154945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404136350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9150642,0.0006609755,0.0018795751,0.001788771,0.00978728,0.0002810351,0.0000017417851,0.000041507054,0.07049493],"genre_scores_gemma":[0.9868289,0.00038829946,0.00816046,0.00038212122,0.00333288,0.000017359884,0.000007894668,0.000022212056,0.00085987605],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99707234,0.0006742181,0.00065324875,0.00027577905,0.0009130695,0.00041135095],"domain_scores_gemma":[0.9979859,0.00075180875,0.0004084539,0.00011818919,0.0006003643,0.00013525524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015422984,0.00022416406,0.0003080848,0.00046727635,0.0006388178,0.0008634212,0.00034271998,0.00012880577,0.00019650949],"category_scores_gemma":[0.00063021167,0.00019462829,0.00016947942,0.00070952147,0.00013655788,0.0023866314,0.00003198857,0.0011036051,0.00003071321],"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":[0.00025921784,0.0028401269,0.0019182599,0.00085822743,0.00017376199,0.00014131129,0.9257863,0.00014072488,0.0018056944,0.028322488,0.0049243043,0.032829564],"study_design_scores_gemma":[0.00029550056,0.0004853764,0.031291645,0.00088349683,0.003660602,0.00009418541,0.95622087,0.000102314254,0.00005074805,0.0009363745,0.00570893,0.00026998963],"about_ca_topic_score_codex":0.0012260868,"about_ca_topic_score_gemma":0.00075407216,"teacher_disagreement_score":0.07176471,"about_ca_system_score_codex":0.0018649697,"about_ca_system_score_gemma":0.0038602422,"threshold_uncertainty_score":0.83259904},"labels":[],"label_agreement":null},{"id":"W4404173077","doi":"10.61669/001c.122484","title":"The Intersection of Student Assessment and Faculty Learning","year":2024,"lang":"en","type":"article","venue":"Intersection A Journal at the Intersection of Assessment and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Intersection (aeronautics); Mathematics education; Psychology; Medical education; Pedagogy; Engineering; Medicine; Transport engineering","score_opus":0.03403379402823651,"score_gpt":0.4174538805122966,"score_spread":0.38342008648406006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404173077","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9720598,0.00047457774,0.006264309,0.0017296919,0.0036069984,0.00030637832,0.0000013226987,0.00008537291,0.01547156],"genre_scores_gemma":[0.9924143,0.00077224505,0.00013581755,0.000025031151,0.0004495968,0.000020624724,0.0000040055447,0.000024755951,0.0061536552],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99656254,0.0011910667,0.0007255478,0.0003217943,0.00085769704,0.00034132603],"domain_scores_gemma":[0.9980405,0.0008370578,0.0005915926,0.00011149302,0.000301771,0.00011761355],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0042644553,0.00023987406,0.0002973376,0.00020703342,0.002682706,0.00078218227,0.00025326942,0.000118402575,0.0003446907],"category_scores_gemma":[0.00010764714,0.00015677187,0.00025265568,0.00039698623,0.00055292435,0.00054290745,0.00024594492,0.0017215658,0.0000053050967],"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":[0.0007402424,0.0003579948,0.46203977,0.00021810648,0.0029826253,0.00003344508,0.21489888,0.0021284812,0.023132892,0.033671368,0.0046103084,0.2551859],"study_design_scores_gemma":[0.0011746171,0.002052574,0.2588853,0.00088961056,0.00034326388,0.00027537497,0.6337125,0.008935686,0.0003261366,0.00077047304,0.09220189,0.00043258842],"about_ca_topic_score_codex":0.00058608426,"about_ca_topic_score_gemma":0.0010294701,"teacher_disagreement_score":0.4188136,"about_ca_system_score_codex":0.0012376198,"about_ca_system_score_gemma":0.00021198722,"threshold_uncertainty_score":0.9986157},"labels":[],"label_agreement":null},{"id":"W4404293607","doi":"10.36834/cmej.72320","title":"User experience of the Written Exam Question Quality tool to inform the writing of new written-exam questions","year":2024,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Task (project management); Perception; Quality (philosophy); Computer science; Test (biology); Psychology; Medical education; Medicine","score_opus":0.03389104683518359,"score_gpt":0.41162157544418665,"score_spread":0.3777305286090031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404293607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77700716,0.0005017848,0.00029823053,0.20267092,0.0039900197,0.0003814817,0.00000589892,0.000020408088,0.015124074],"genre_scores_gemma":[0.98893976,0.00012422647,0.0003957382,0.0048043528,0.0014886953,0.000016980483,0.0000017047213,0.000007069098,0.004221497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977817,0.00025055424,0.00050031766,0.00011352923,0.0010855003,0.00026840856],"domain_scores_gemma":[0.99774283,0.0002020445,0.00012618434,0.0001693714,0.00031384436,0.0014457512],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026609018,0.00007856933,0.00011981668,0.00012831987,0.00073575164,0.00019824263,0.00062875723,0.000107310116,0.0042264457],"category_scores_gemma":[0.0081671,0.000051727115,0.0000876223,0.0007837653,0.00029670066,0.0002929133,0.000031620646,0.00042324665,0.000017580873],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007758896,0.000089756875,0.05470614,0.00004330923,0.000056260724,0.000003925184,0.17598599,0.000008903828,0.000085844884,0.2847833,0.21254498,0.27168384],"study_design_scores_gemma":[0.00011117897,0.00002671001,0.2988453,0.00061601243,0.000029429719,0.000020423688,0.086931705,0.00003722298,0.000017555085,0.0015022634,0.6117234,0.00013878845],"about_ca_topic_score_codex":0.10280933,"about_ca_topic_score_gemma":0.09926599,"teacher_disagreement_score":0.39917845,"about_ca_system_score_codex":0.00036112402,"about_ca_system_score_gemma":0.02852395,"threshold_uncertainty_score":0.99668384},"labels":[],"label_agreement":null},{"id":"W4404331919","doi":"10.1111/jcal.13087","title":"The impact of frequency and stakes of formative assessment on student achievement in higher education: A learning analytics study","year":2024,"lang":"en","type":"article","venue":"Journal of Computer Assisted Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Formative assessment; Learning analytics; Mathematics education; Academic achievement; Analytics; Educational technology; Student achievement; Higher education; Educational research; Psychology; Computer science; Data science; Political science","score_opus":0.051717165546726666,"score_gpt":0.4235158600968853,"score_spread":0.3717986945501586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404331919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935675,0.00051236915,0.00035805904,0.00054161693,0.0005272876,0.00022033644,3.1993056e-7,0.000008865494,0.004263597],"genre_scores_gemma":[0.9987298,0.00013206895,0.0005577073,0.00000724366,0.00022795406,0.0000031032644,5.642052e-7,0.000008020022,0.0003335332],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99749553,0.0007473084,0.0006744582,0.000110610104,0.0007957462,0.00017631598],"domain_scores_gemma":[0.99832904,0.00066329766,0.00061647384,0.00007330581,0.0002542994,0.00006358486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023219367,0.00012193542,0.0003135822,0.00028692497,0.00024027732,0.00023739268,0.00024669248,0.000038941776,0.000047063044],"category_scores_gemma":[0.000032697877,0.00007833721,0.00014752024,0.00046506972,0.00008442193,0.0002579612,0.00006272495,0.00062971236,5.6144455e-7],"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":[0.000035404628,0.0011370222,0.8977341,0.000023395016,0.0006229079,0.000011422687,0.061518315,0.005743632,0.000053674168,0.0022546935,0.00010168444,0.03076372],"study_design_scores_gemma":[0.00044042713,0.0021377208,0.9514978,0.00030256045,0.00006238612,0.0000014195019,0.044069733,0.0008134888,0.0000013862011,0.00009204915,0.00050690584,0.00007413918],"about_ca_topic_score_codex":0.00015125434,"about_ca_topic_score_gemma":0.000042918742,"teacher_disagreement_score":0.053763654,"about_ca_system_score_codex":0.0003523601,"about_ca_system_score_gemma":0.00051528757,"threshold_uncertainty_score":0.31944984},"labels":[],"label_agreement":null},{"id":"W4404840547","doi":"10.32920/27931464.v1","title":"The Impact of Electronic Data to Capture Qualitative Comments in a Competency-Based Assessment System","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Data science; Computer science","score_opus":0.0878788296559014,"score_gpt":0.5045773296626463,"score_spread":0.41669850000674497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404840547","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4451108,0.0033184038,0.002510999,0.047948927,0.0037137002,0.012162185,0.0021193975,0.0005812529,0.48253435],"genre_scores_gemma":[0.99759823,0.000045455337,0.0009907522,0.00006337627,0.00009620647,0.0001310256,0.00019727145,0.000021159345,0.0008565155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9959275,0.0012838498,0.0005785978,0.00059639715,0.0009855109,0.0006281541],"domain_scores_gemma":[0.99760056,0.0008927673,0.00024733343,0.0009922899,0.0001523816,0.00011469302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048686923,0.00029131887,0.0005163107,0.00017421939,0.00022522414,0.00032101144,0.0023439627,0.00019929584,0.000080648904],"category_scores_gemma":[0.00008087729,0.00018522973,0.00020249115,0.00052803423,0.00015088548,0.00006040127,0.0020244329,0.0009159254,0.000031549505],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014417109,0.0005671197,0.019731978,0.0006180163,0.0015474431,0.00001683776,0.16670458,0.0015675544,0.00007362832,0.76446253,0.043995194,0.00057095755],"study_design_scores_gemma":[0.0016581897,0.0005684068,0.042541925,0.0027746637,0.00036244615,4.3911305e-7,0.8817599,0.027923167,0.000011104788,0.0362933,0.0046437555,0.0014627023],"about_ca_topic_score_codex":0.05498222,"about_ca_topic_score_gemma":0.055264287,"teacher_disagreement_score":0.7281692,"about_ca_system_score_codex":0.0023199792,"about_ca_system_score_gemma":0.0074631106,"threshold_uncertainty_score":0.99816364},"labels":[],"label_agreement":null},{"id":"W4404840942","doi":"10.32920/27931464","title":"The Impact of Electronic Data to Capture Qualitative Comments in a Competency-Based Assessment System","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Electronic data capture; Automatic identification and data capture; Qualitative property; Computer science; Data science; Psychology; Data collection; Sociology; Social science; Machine learning","score_opus":0.0878788296559014,"score_gpt":0.5045773296626463,"score_spread":0.41669850000674497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404840942","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4451108,0.0033184038,0.002510999,0.047948927,0.0037137002,0.012162185,0.0021193975,0.0005812529,0.48253435],"genre_scores_gemma":[0.99759823,0.000045455337,0.0009907522,0.00006337627,0.00009620647,0.0001310256,0.00019727145,0.000021159345,0.0008565155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9959275,0.0012838498,0.0005785978,0.00059639715,0.0009855109,0.0006281541],"domain_scores_gemma":[0.99760056,0.0008927673,0.00024733343,0.0009922899,0.0001523816,0.00011469302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048686923,0.00029131887,0.0005163107,0.00017421939,0.00022522414,0.00032101144,0.0023439627,0.00019929584,0.000080648904],"category_scores_gemma":[0.00008087729,0.00018522973,0.00020249115,0.00052803423,0.00015088548,0.00006040127,0.0020244329,0.0009159254,0.000031549505],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014417109,0.0005671197,0.019731978,0.0006180163,0.0015474431,0.00001683776,0.16670458,0.0015675544,0.00007362832,0.76446253,0.043995194,0.00057095755],"study_design_scores_gemma":[0.0016581897,0.0005684068,0.042541925,0.0027746637,0.00036244615,4.3911305e-7,0.8817599,0.027923167,0.000011104788,0.0362933,0.0046437555,0.0014627023],"about_ca_topic_score_codex":0.05498222,"about_ca_topic_score_gemma":0.055264287,"teacher_disagreement_score":0.7281692,"about_ca_system_score_codex":0.0023199792,"about_ca_system_score_gemma":0.0074631106,"threshold_uncertainty_score":0.99816364},"labels":[],"label_agreement":null},{"id":"W4404910374","doi":"10.1145/3649409.3691071","title":"Developing a Playbook of Equitable Grading Practices","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; The Scarborough Hospital; University of Toronto","funders":"Universitas Brawijaya","keywords":"Grading (engineering); Computer science; Business; Engineering","score_opus":0.13536100550904578,"score_gpt":0.4583071248508491,"score_spread":0.32294611934180334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404910374","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05297483,0.0007763815,0.002076455,0.003348169,0.0006748583,0.00014501355,5.005612e-7,0.00015082155,0.93985295],"genre_scores_gemma":[0.9637529,0.00019593029,0.005235666,0.00007920616,0.00020338528,0.0000063346365,6.764822e-7,0.00000536383,0.0305205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.999271,0.00003598252,0.00011042115,0.00011256118,0.00027102238,0.00019905878],"domain_scores_gemma":[0.9995373,0.00029675703,0.00006138243,0.00004501222,0.00003237045,0.00002716545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007607683,0.000043104308,0.00007241349,0.00006173257,0.00017485957,0.00015667954,0.00014157956,0.00003141368,0.0006358192],"category_scores_gemma":[0.00012872112,0.000036724687,0.000031274354,0.00029058842,0.00005357432,0.00046505666,0.00005234286,0.000050394865,0.000080620244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019929662,0.00000869278,0.008580074,0.000033122316,0.00003414592,0.0000037567565,0.007937793,4.6526642e-7,0.0004333986,0.9748637,0.005752271,0.0023505914],"study_design_scores_gemma":[0.00013740994,0.00003460022,0.0021583675,0.00021889519,0.000049598504,9.683251e-7,0.049462702,0.00022317455,0.0013710734,0.016287858,0.9298071,0.00024822514],"about_ca_topic_score_codex":0.0010688138,"about_ca_topic_score_gemma":0.0006668101,"teacher_disagreement_score":0.95857584,"about_ca_system_score_codex":0.000065419175,"about_ca_system_score_gemma":0.00026396906,"threshold_uncertainty_score":0.6961775},"labels":[],"label_agreement":null},{"id":"W4404940578","doi":"10.1080/14703297.2024.2436046","title":"Investigating how students’ perceptions of peer comments and edits affect academic writing performance","year":2024,"lang":"en","type":"article","venue":"Innovations in Education and Teaching International","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Affect (linguistics); Perception; Psychology; Academic achievement; Higher education; Mathematics education; Peer influence; Pedagogy; Social psychology; Communication","score_opus":0.03747358532231683,"score_gpt":0.43688187095494374,"score_spread":0.3994082856326269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404940578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.973221,0.00007958915,0.00013420601,0.014296912,0.0015440735,0.00013923214,0.000005054717,0.000035348006,0.010544565],"genre_scores_gemma":[0.99467075,0.00012373613,0.001424905,0.00022679837,0.0005058803,0.000034678273,0.000045472858,0.0000065575464,0.002961213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99894994,0.00009873707,0.00022607383,0.00015710105,0.00046256618,0.000105564555],"domain_scores_gemma":[0.99948364,0.0001974247,0.00007416248,0.000045932138,0.00016767428,0.000031185227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001686344,0.00007056735,0.00007219987,0.00038819658,0.0003609728,0.00025901696,0.00017141027,0.000059457037,0.00004661938],"category_scores_gemma":[0.0005467139,0.00007593631,0.000013458845,0.00024897224,0.0001353215,0.0006159117,0.00006988387,0.00046051358,0.0000029934956],"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":[4.665629e-7,0.00006138123,0.8644405,0.000018044666,0.000014777252,5.9223392e-8,0.019975865,0.0000014574723,0.0002247923,0.09104733,0.0026782022,0.02153711],"study_design_scores_gemma":[0.00014356046,0.000011903049,0.9445712,0.00037498624,0.000008399148,0.0000020844357,0.036911473,0.00085575104,0.0000074585737,0.0008508128,0.016166084,0.00009626806],"about_ca_topic_score_codex":0.00014240223,"about_ca_topic_score_gemma":0.000033498476,"teacher_disagreement_score":0.09019652,"about_ca_system_score_codex":0.00012027911,"about_ca_system_score_gemma":0.00014684153,"threshold_uncertainty_score":0.30965927},"labels":[],"label_agreement":null},{"id":"W4404993933","doi":"10.21428/cb6ab371.584102f8","title":"Teacher Reflections on Assessing Indigenous Cultural Competency in a Criminal Justice Subject Through Interactive Oral Assessment","year":2024,"lang":"en","type":"preprint","venue":"CrimRxiv","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Subject (documents); Criminal justice; Economic Justice; Criminology; Psychology; Sociology; Pedagogy; Political science; Law; Library science; Computer science","score_opus":0.1738148616393724,"score_gpt":0.5105462522940751,"score_spread":0.3367313906547027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404993933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6573164,0.00034979984,0.00019479192,0.00085375947,0.0052712327,0.0007994656,0.00001222596,0.00025644706,0.33494586],"genre_scores_gemma":[0.9917588,0.0003164273,0.003506151,0.000339287,0.0014544508,0.0002279337,0.00006429982,0.00005896111,0.0022736606],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9957509,0.00084299233,0.00060067244,0.0010389455,0.00095195236,0.0008145206],"domain_scores_gemma":[0.99854153,0.00038152433,0.00029554567,0.0004072125,0.00024306733,0.0001311395],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001001543,0.00053490227,0.000625454,0.0003690014,0.0009424371,0.001543077,0.0007570893,0.00050057314,0.0003441808],"category_scores_gemma":[0.00022112453,0.00049789395,0.00032557943,0.00064256496,0.0003229837,0.0005259283,0.0007662628,0.0032486664,0.00016943172],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013780911,0.002150947,0.017053854,0.001000378,0.00059306197,0.00043008686,0.9128515,0.00024409975,0.00054191466,0.054988455,0.0056906696,0.0043171863],"study_design_scores_gemma":[0.00112688,0.00042931264,0.11318883,0.0027317437,0.0029641646,0.000011901648,0.8228497,0.00034017971,0.00008348708,0.038225632,0.0157843,0.002263902],"about_ca_topic_score_codex":0.010738017,"about_ca_topic_score_gemma":0.0078018,"teacher_disagreement_score":0.33444244,"about_ca_system_score_codex":0.0023634583,"about_ca_system_score_gemma":0.0018957683,"threshold_uncertainty_score":0.9997473},"labels":[],"label_agreement":null},{"id":"W4405015817","doi":"10.1007/s40670-024-02197-4","title":"The Predictive Power of Short Answer Questions in Undergraduate Medical Education Progress Difficulty","year":2024,"lang":"en","type":"article","venue":"Medical Science Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Formative assessment; Logistic regression; Odds; Medical education; Predictive power; Referral; Psychology; Medicine; Mathematics education; Family medicine; Internal medicine","score_opus":0.01476621263406066,"score_gpt":0.40068161397087415,"score_spread":0.3859154013368135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405015817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8271158,0.0019424508,0.00009146461,0.1376122,0.01045476,0.00057335646,0.000002910582,0.00010612719,0.022100948],"genre_scores_gemma":[0.99794024,0.0003633618,0.000061345105,0.00017515727,0.00052608503,0.000104213694,0.0000019101474,0.00000600422,0.0008216641],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9951572,0.00017774818,0.00032273863,0.00036368292,0.0034839946,0.0004946636],"domain_scores_gemma":[0.998613,0.00040978708,0.000035749214,0.00018024286,0.00016581785,0.000595387],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0042171683,0.000102651255,0.00013146803,0.0001512817,0.0006038258,0.00021405458,0.0010767281,0.00012479795,0.00055151863],"category_scores_gemma":[0.0034240535,0.00006362227,0.000056925386,0.0019818577,0.00514395,0.00033966053,0.00012233602,0.00035587643,0.000027985436],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020916606,0.0020077545,0.33090794,0.00003450269,0.000039452698,0.000018285753,0.0497055,4.9343845e-7,0.00004409982,0.3957878,0.04725529,0.17417797],"study_design_scores_gemma":[0.00025676817,0.00019380107,0.649101,0.001193204,0.000040521456,0.000009089805,0.080704674,0.000991024,0.000053147924,0.008516166,0.25850502,0.00043559002],"about_ca_topic_score_codex":0.00051443756,"about_ca_topic_score_gemma":0.0017170957,"teacher_disagreement_score":0.38727164,"about_ca_system_score_codex":0.00032727874,"about_ca_system_score_gemma":0.016988588,"threshold_uncertainty_score":0.9975635},"labels":[],"label_agreement":null},{"id":"W4405343076","doi":"10.1177/17577438241265462","title":"Re-imagining teacher assessment: How teachers are encouraged (or not) to pursue ongoing professional learning in New Brunswick","year":2024,"lang":"en","type":"article","venue":"Power and Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Pedagogy; Professional development; Sociology; Professional learning community; Mathematics education; Teacher education; Faculty development; Psychology","score_opus":0.028399564590299294,"score_gpt":0.4001026426598453,"score_spread":0.371703078069546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405343076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8770448,0.00037813478,0.00017206071,0.059134014,0.0026624156,0.0004219129,3.499396e-7,0.00014172714,0.06004461],"genre_scores_gemma":[0.8881833,0.000042690444,0.00070336874,0.0003091849,0.00052386854,0.000016059263,0.0000063670673,0.000014656863,0.11020049],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987245,0.00018718847,0.00013980294,0.00030386652,0.00035547043,0.00028915252],"domain_scores_gemma":[0.9995249,0.00015161886,0.00005119076,0.00007426645,0.000036188296,0.00016186794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009787442,0.000116931384,0.00012564193,0.00019061091,0.00032128347,0.0005043644,0.00012893046,0.00007824243,0.00047071482],"category_scores_gemma":[0.00024250803,0.00010368818,0.00003224822,0.00041949155,0.000037423284,0.0005208728,0.0000450666,0.00041465592,0.000027366386],"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":[0.000023560906,0.00012569744,0.4695985,0.000026981452,0.000020500944,0.0000051000807,0.44681606,0.000004549364,0.00017701813,0.002374688,0.02574004,0.055087324],"study_design_scores_gemma":[0.00014951885,0.000031601718,0.4869576,0.0003263964,0.000014268647,5.959863e-7,0.4219858,0.00006200826,0.0000072005473,0.00013253187,0.09015501,0.00017745268],"about_ca_topic_score_codex":0.0022902775,"about_ca_topic_score_gemma":0.005171196,"teacher_disagreement_score":0.06441498,"about_ca_system_score_codex":0.0002569862,"about_ca_system_score_gemma":0.0028817628,"threshold_uncertainty_score":0.51539975},"labels":[],"label_agreement":null},{"id":"W4405795202","doi":"10.56380/mjer.si.2024.04","title":"Educational Development through the Lens of Curriculum: A Holistic and Systemic Approach","year":2024,"lang":"en","type":"article","venue":"БОЛОВСРОЛЫН СУДАЛГААНЫ МОНГОЛЫН СЭТГҮҮЛ","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Curriculum; Transformative learning; Engineering ethics; Curriculum theory; Pedagogy; Holistic education; Presentation (obstetrics); Sociology; Curriculum development; Philosophy of education; Emergent curriculum; Personal development; Curriculum mapping; Political science; Higher education; Engineering; Medicine","score_opus":0.061610088329893564,"score_gpt":0.36920759791918895,"score_spread":0.3075975095892954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405795202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56064075,0.026114188,0.004000242,0.010455154,0.0042870604,0.0026885963,0.000044430126,0.00047375404,0.39129585],"genre_scores_gemma":[0.9899713,0.0007048478,0.0025263156,0.00013150721,0.0005945771,0.0001559229,0.000026193971,0.000027747148,0.0058616376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99752104,0.00020260352,0.00048383253,0.00047166704,0.0008414838,0.000479344],"domain_scores_gemma":[0.99893177,0.0004295087,0.00012799742,0.00026498214,0.00015286893,0.00009289228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090765517,0.00024517457,0.00030102854,0.00011406874,0.0007011583,0.00028476777,0.0005099076,0.00013532086,0.00022976079],"category_scores_gemma":[0.00013219056,0.0001749407,0.000109754255,0.0007273594,0.0005685759,0.00042136223,0.00015215146,0.00026110763,0.00011849413],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011121253,0.00037895626,0.01983759,0.0005518733,0.00032360983,0.0000053408244,0.11913573,0.000027106276,0.00015120847,0.83497167,0.017669603,0.0069362223],"study_design_scores_gemma":[0.00095294806,0.00011360984,0.04624906,0.0011461313,0.0004077395,0.00007233046,0.11108031,0.0007984317,0.00006823845,0.012587042,0.8251615,0.0013626538],"about_ca_topic_score_codex":0.0007678447,"about_ca_topic_score_gemma":0.00014837697,"teacher_disagreement_score":0.8223846,"about_ca_system_score_codex":0.00018969219,"about_ca_system_score_gemma":0.00089207286,"threshold_uncertainty_score":0.7133874},"labels":[],"label_agreement":null},{"id":"W4405940634","doi":"10.18554/rt.v17i3.7450","title":"CONCEPTIONS OF ASSESSMENT IN HIGHER EDUCATION","year":2024,"lang":"en","type":"article","venue":"Revista Triângulo","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Universidade do Minho; International Council for Canadian Studies","keywords":"Mathematics education; Psychology; Pedagogy; Medical education; Medicine","score_opus":0.06498206847688327,"score_gpt":0.43897680006160134,"score_spread":0.3739947315847181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405940634","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25902268,0.0064742337,0.000102614766,0.0073585343,0.0023564163,0.00074406905,0.000010862603,0.00013716724,0.72379345],"genre_scores_gemma":[0.9717584,0.00038670682,0.00031817838,0.000047787962,0.00031333583,0.000029170973,0.00000795234,0.000006121434,0.02713232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991609,0.000107794156,0.00020396242,0.0001388462,0.00025651013,0.0001320262],"domain_scores_gemma":[0.9996758,0.000104195286,0.000038496208,0.000098884884,0.00004363552,0.000039003928],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044252345,0.00005778316,0.0001223332,0.00011273013,0.00006082147,0.00011420805,0.00012978533,0.00004604078,0.002590162],"category_scores_gemma":[0.000018121444,0.000055091616,0.000059550144,0.00055938005,0.00008590571,0.00014817275,0.000018134177,0.000101268204,0.000053978172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018694226,0.000115928444,0.026158435,0.00006765399,0.000013717235,0.00000154666,0.0024727592,7.435225e-7,0.00027725683,0.95021445,0.0072037983,0.013471816],"study_design_scores_gemma":[0.00012112642,0.000021234659,0.15386161,0.00021630207,0.000023909748,1.1735693e-7,0.0031731904,0.000011798452,0.0000070707893,0.0014343943,0.84102887,0.00010040555],"about_ca_topic_score_codex":0.0003055155,"about_ca_topic_score_gemma":0.00007488793,"teacher_disagreement_score":0.94878006,"about_ca_system_score_codex":0.00018701992,"about_ca_system_score_gemma":0.0006203537,"threshold_uncertainty_score":0.9983216},"labels":[],"label_agreement":null},{"id":"W4406043859","doi":"10.1080/15427587.2024.2448815","title":"The impact of TOEFL iBT preparation on Chinese test-takers’ perceptions of integrated speaking and writing design","year":2025,"lang":"en","type":"article","venue":"Critical Inquiry in Language Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Test (biology); Test of English as a Foreign Language; Psychology; Perception; Context (archaeology); Construct validity; Language assessment; Test design; Applied psychology; Social psychology; Medical education; Mathematics education; Developmental psychology; Psychometrics; Test method; Medicine","score_opus":0.07430071452784202,"score_gpt":0.5133190650981386,"score_spread":0.4390183505702966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406043859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99170613,0.0015548356,0.00040228976,0.0007245645,0.00013661353,0.00022537367,0.0000048131014,0.000018998488,0.005226367],"genre_scores_gemma":[0.999185,0.00032544203,0.00027926767,0.000028534621,0.000080598686,0.000017091243,0.0000011413963,0.0000033179622,0.00007958908],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9990401,0.00022907126,0.00025767935,0.0001306611,0.00016052622,0.00018192033],"domain_scores_gemma":[0.9958986,0.0037764015,0.0000422503,0.00009429566,0.00016682307,0.000021640655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008256972,0.00009164995,0.00020307038,0.00007910805,0.00031220148,0.00004297737,0.00010987477,0.000043518885,0.00002475936],"category_scores_gemma":[0.005196708,0.00005726878,0.000054805198,0.00038588388,0.0012308795,0.00010993149,0.0000561479,0.000106195825,9.153274e-7],"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":[0.0001379447,0.0004282598,0.35286093,0.00009498596,0.00019674725,0.000008546194,0.60438186,0.000070412156,0.0061539263,0.02647927,0.0011230472,0.008064075],"study_design_scores_gemma":[0.0002545956,0.0002291378,0.3198544,0.00029034066,0.000028911212,2.195348e-7,0.6764436,0.00023516678,0.00011072279,0.0024550098,0.000008190116,0.00008972862],"about_ca_topic_score_codex":0.0003781908,"about_ca_topic_score_gemma":0.00038786256,"teacher_disagreement_score":0.07206172,"about_ca_system_score_codex":0.000090961476,"about_ca_system_score_gemma":0.000063911015,"threshold_uncertainty_score":0.622132},"labels":[],"label_agreement":null},{"id":"W4406293560","doi":"10.21432/cjlt28759","title":"Technological Tool for Formative Assessment in Higher Education: ZipGrade","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Higher education; Mathematics education; Technological literacy; Technology integration; Pedagogy; Qualitative research; Psychology; Teaching method; Computer science; Sociology; Political science; Social science","score_opus":0.020358299633339568,"score_gpt":0.35352175307328504,"score_spread":0.33316345343994547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406293560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7704189,0.0028026444,0.0008975894,0.16446775,0.0012687483,0.00045544014,0.0000017260716,0.000067258574,0.059619993],"genre_scores_gemma":[0.99364424,0.000084301944,0.0014835888,0.00006832212,0.000046025536,0.000015821885,6.109374e-7,0.0000027027595,0.0046543865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993871,0.000049352402,0.00019552064,0.00007921184,0.000065922526,0.00022289225],"domain_scores_gemma":[0.9995624,0.00009892087,0.00010799318,0.000039782462,0.00012767072,0.000063248954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051932584,0.000057884405,0.00015068686,0.0008169608,0.00031830877,0.00005010384,0.00018100611,0.00019721164,0.000079892],"category_scores_gemma":[0.0002551699,0.000053619766,0.000027678889,0.0005933211,0.00041188873,0.00008682932,0.000013607912,0.00044541326,7.622613e-7],"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":[0.000002735925,0.000015468224,0.42688686,0.0000056647737,0.000016994592,0.0000048740176,0.0005010896,0.0000011591708,0.00002130828,0.5282618,0.0011405897,0.043141466],"study_design_scores_gemma":[0.0004947372,0.00014204638,0.031817418,0.00010693271,0.00001903177,0.000005369454,0.0326945,0.000007677453,0.000022505099,0.04149383,0.8930955,0.000100454534],"about_ca_topic_score_codex":0.00019708657,"about_ca_topic_score_gemma":0.002394728,"teacher_disagreement_score":0.8919549,"about_ca_system_score_codex":0.00021379178,"about_ca_system_score_gemma":0.0017694056,"threshold_uncertainty_score":0.31388494},"labels":[],"label_agreement":null},{"id":"W4406716639","doi":"10.1007/978-3-031-47411-8_44-1","title":"Teaching Within Social Justice and Diversity Frameworks: A (White) Teacher’s Approach","year":2024,"lang":"en","type":"book-chapter","venue":"Springer international handbooks of education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Diversity (politics); Social justice; White (mutation); Economic Justice; Sociology; Pedagogy; Social psychology; Psychology; Criminology; Political science; Anthropology; Law; Biology","score_opus":0.03701825137104098,"score_gpt":0.34711474001636106,"score_spread":0.3100964886453201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406716639","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002358265,0.0005278809,0.00020229323,0.0012947002,0.0036449884,0.00026211,0.000017336632,0.000058565947,0.99163383],"genre_scores_gemma":[0.197533,0.00011448545,0.0017553398,0.00013450602,0.0032671385,0.000010346957,0.00004861486,0.000030360317,0.7971062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841934,0.00002659783,0.0002905903,0.00037612347,0.00074149447,0.00014582647],"domain_scores_gemma":[0.99925077,0.00005810006,0.0003005806,0.00010773102,0.00021165612,0.000071179784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061748916,0.00020471896,0.00022011533,0.00025835825,0.0005953447,0.00016700897,0.000423456,0.0004650905,0.00030825887],"category_scores_gemma":[0.00005916257,0.00022457719,0.00012662384,0.00002346732,0.00026705232,0.00018609724,0.00042027544,0.00090895133,0.000021834989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021004636,0.00009024468,0.0014749957,0.00012826157,0.00021843376,6.781306e-7,0.054206878,9.678145e-7,0.0000075659627,0.93418884,0.005100329,0.004561806],"study_design_scores_gemma":[0.0006389228,0.00008334013,0.0047341175,0.0021948935,0.0023610871,0.000005011305,0.051975258,0.00023107012,0.000011660991,0.32936567,0.6069284,0.0014705823],"about_ca_topic_score_codex":0.00048332577,"about_ca_topic_score_gemma":0.000098468714,"teacher_disagreement_score":0.6048232,"about_ca_system_score_codex":0.000307697,"about_ca_system_score_gemma":0.0002721642,"threshold_uncertainty_score":0.9157992},"labels":[],"label_agreement":null},{"id":"W4407090464","doi":"10.1007/s42330-024-00341-1","title":"Communities of Practice for Canadian University Mathematics Instructors","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Science education; Mathematics education; Sociology; Pedagogy; Psychology","score_opus":0.02116335119734801,"score_gpt":0.3197334815633598,"score_spread":0.29857013036601177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407090464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96850145,0.0005120338,0.00040647184,0.011714692,0.0010093027,0.00024395567,0.000011840426,0.000011925849,0.017588355],"genre_scores_gemma":[0.9685268,0.00012667441,0.031041255,0.000019247063,0.000035063807,8.2381905e-7,4.853872e-7,0.0000039615343,0.00024569264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9994236,0.0000106712,0.00017126235,0.000053422642,0.00014778234,0.00019322993],"domain_scores_gemma":[0.9986984,0.0001708766,0.00014931551,0.00009065019,0.0006492233,0.00024150769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011277663,0.000050310533,0.0001094608,0.0013887798,0.0006889228,0.00011589561,0.00041414006,0.00007232063,0.00002177159],"category_scores_gemma":[0.0005466858,0.000049098802,0.000022799086,0.0010104901,0.0018724476,0.00042763536,0.0000112068365,0.00011463058,9.379099e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5604373e-7,0.000022860737,0.0014715072,0.00005313048,0.000015787773,0.0000019716047,0.061675437,3.031809e-7,0.00006483318,0.930743,0.00047161573,0.005479218],"study_design_scores_gemma":[0.00006872941,0.000074262076,0.00028591158,0.00027080037,0.000070533555,0.000046871326,0.8610419,0.00016986764,0.00008271971,0.05893543,0.078859694,0.000093266186],"about_ca_topic_score_codex":0.06898408,"about_ca_topic_score_gemma":0.42076117,"teacher_disagreement_score":0.8718076,"about_ca_system_score_codex":0.0003363236,"about_ca_system_score_gemma":0.01485018,"threshold_uncertainty_score":0.9907347},"labels":[],"label_agreement":null},{"id":"W4407944763","doi":"10.18552/joaw.v15is1.1036","title":"Being and Becoming: Addressing Equity, Diversity and Inclusion Issues in Learning Academic Writing through an Academic Integrity Socialisation Process","year":2025,"lang":"en","type":"article","venue":"Journal of Academic Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Equity (law); Inclusion (mineral); Academic integrity; Diversity (politics); Process (computing); Sociology; Psychology; Pedagogy; Engineering ethics; Political science; Social science; Social psychology; Anthropology; Computer science; Engineering","score_opus":0.12376111737684485,"score_gpt":0.4784814084030815,"score_spread":0.35472029102623664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407944763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98584974,0.003535732,0.00018950221,0.007551693,0.0001946197,0.0001956825,7.1387905e-7,0.000044600696,0.0024377075],"genre_scores_gemma":[0.9889023,0.008995702,0.0005577731,0.0003828244,0.0010811888,0.0000019063423,0.0000016111095,0.000013067085,0.0000636511],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99647117,0.00067628815,0.0010298111,0.0003214098,0.0009711183,0.0005302311],"domain_scores_gemma":[0.99788857,0.0007974482,0.000891807,0.000049957867,0.00023473782,0.00013749389],"candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0100764595,0.00020464708,0.00047772538,0.0003521239,0.0064671114,0.00013217905,0.0006541357,0.00076155283,0.000008710776],"category_scores_gemma":[0.002093391,0.0002186334,0.00006265222,0.0005594192,0.00033249086,0.0036377092,0.0053645773,0.0059907986,2.3636903e-7],"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":[0.000031142496,0.000012917515,0.7703057,0.00009316062,0.000016275282,0.0000057736843,0.20790997,0.000014328408,0.0025906,0.0038327517,0.000024910663,0.0151625],"study_design_scores_gemma":[0.0022845832,0.0001134902,0.3251246,0.0071687684,0.00019564477,0.000021529719,0.53502226,0.0011408725,0.0008534005,0.12678906,0.0006861673,0.0005996175],"about_ca_topic_score_codex":0.00047540275,"about_ca_topic_score_gemma":0.00007272881,"teacher_disagreement_score":0.44518107,"about_ca_system_score_codex":0.00042053996,"about_ca_system_score_gemma":0.0002634887,"threshold_uncertainty_score":0.9963024},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9792331,0.0002961981,0.00005870659,0.0039882,0.001201815,0.0009705766,0.0000057092807,0.00001423138,0.01423148],"genre_scores_gemma":[0.99663484,0.000058791065,0.00042442128,0.00013312936,0.00014464316,0.00008417249,0.000052888558,0.000008691559,0.0024584348],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972959,0.00049681606,0.0005790443,0.00026113057,0.0011648891,0.00020218661],"domain_scores_gemma":[0.9978659,0.00047022867,0.00039309348,0.00026212947,0.00097041676,0.000038242782],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002363922,0.00014878636,0.00026094905,0.0002338015,0.00024567952,0.00008624493,0.00028708755,0.00012289212,0.0010055809],"category_scores_gemma":[0.00021942731,0.00011661757,0.000051116094,0.0009868171,0.00021792972,0.0004477041,0.00006857739,0.00015374256,0.0000010104732],"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":[0.000032735523,0.00040305246,0.78573704,0.00010938087,0.00007255455,4.722954e-8,0.008328027,0.00010976548,0.0026676161,0.19364256,0.0009346095,0.007962586],"study_design_scores_gemma":[0.0006179263,0.000021576247,0.9642157,0.0001597776,0.00013209369,1.08123174e-7,0.016296698,0.000070713315,0.00094266154,0.015874553,0.0015504136,0.0001177659],"about_ca_topic_score_codex":0.0021561747,"about_ca_topic_score_gemma":0.0021649667,"teacher_disagreement_score":0.17847864,"about_ca_system_score_codex":0.00028596475,"about_ca_system_score_gemma":0.0016851535,"threshold_uncertainty_score":0.9999076},"labels":[],"label_agreement":null},{"id":"W4408090665","doi":"10.1007/s10459-025-10419-6","title":"Correction to: Can all roads lead to competency? School levels effects in licensing examinations scores","year":2025,"lang":"en","type":"erratum","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McMaster University; Laurentian University; Thunder Bay Regional Health Sciences Centre; Medical Council of Canada; NOSM University; London Health Sciences Centre; Queen's University; University of Toronto; Western University; The Wilson Centre; Bruyère; University of Ottawa","funders":"","keywords":"Medical education; Psychology; Lead (geology); Mathematics education; Medicine","score_opus":0.02945443184243357,"score_gpt":0.4407449427705345,"score_spread":0.4112905109281009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408090665","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01311595,0.020846771,0.0013682403,0.052665405,0.502505,0.009424676,0.000026091817,0.00027599762,0.39977187],"genre_scores_gemma":[0.45079058,0.02804723,0.027611129,0.027775843,0.009278701,0.0024549218,0.00032577448,0.00009263993,0.45362318],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956059,0.00068068603,0.00077023817,0.0009440485,0.0010598514,0.0009393035],"domain_scores_gemma":[0.99777985,0.00093291,0.00040168237,0.0002724098,0.00025346447,0.00035967608],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027671298,0.00030374742,0.00049823336,0.0018289956,0.0010267118,0.0003103827,0.0008728642,0.00019376498,0.000032059554],"category_scores_gemma":[0.0030762444,0.00033389637,0.000054497676,0.004881657,0.00027884904,0.0008871919,0.000113031645,0.00070212426,0.000038326867],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014893289,0.00046568795,0.13348347,0.00058783026,0.000008006838,0.0000015736902,0.048662357,0.0014356546,0.000011247123,0.011040888,0.54328257,0.26100582],"study_design_scores_gemma":[0.00019775421,0.00034647872,0.39537737,0.00641593,0.000010875807,6.3194466e-7,0.021624573,0.00033434824,0.0000069312314,0.002871991,0.57222265,0.00059047557],"about_ca_topic_score_codex":0.04642366,"about_ca_topic_score_gemma":0.41309604,"teacher_disagreement_score":0.49322632,"about_ca_system_score_codex":0.0029104638,"about_ca_system_score_gemma":0.013858888,"threshold_uncertainty_score":0.9999113},"labels":[],"label_agreement":null},{"id":"W4408156977","doi":"10.1080/02188791.2025.2465296","title":"Advancing e-assessment for learning in the primary EFL writing classroom: the role of collaborative teacher professional learning","year":2025,"lang":"en","type":"article","venue":"Asia Pacific Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Hubei Provincial Department of Education","keywords":"Psychology; Mathematics education; Professional learning community; Professional development; Pedagogy; Collaborative learning; Assessment for learning; Formative assessment","score_opus":0.009083673617588496,"score_gpt":0.369719841353591,"score_spread":0.3606361677360025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408156977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70979315,0.0019935598,0.0009363428,0.019660642,0.001559454,0.0010793942,7.562705e-7,0.000011738814,0.26496494],"genre_scores_gemma":[0.9948729,0.00011483231,0.0016191272,0.00005097938,0.00030816544,0.00004222761,0.0000040367463,0.0000053970743,0.0029823182],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9980444,0.0008196981,0.00042559783,0.00009383669,0.00042730363,0.00018920876],"domain_scores_gemma":[0.9978518,0.0010213788,0.00058799994,0.00006464026,0.00045048617,0.000023716817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043719485,0.00007745558,0.0001641495,0.00013689618,0.00062485755,0.00008187155,0.0002695528,0.000056078767,0.00002287042],"category_scores_gemma":[0.0005056361,0.000050046092,0.00007254479,0.0005758103,0.00008522023,0.000261296,0.000021954602,0.00052482384,4.989935e-7],"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":[0.000078235105,0.00049405266,0.7507637,0.000034252516,0.00006620778,4.3664681e-7,0.11278242,0.00015454557,0.0026167966,0.027814146,0.0035700498,0.10162517],"study_design_scores_gemma":[0.00025716051,0.000077323726,0.13377017,0.00022068429,0.00003360304,9.105182e-7,0.80826265,0.00005886969,0.00004434724,0.0029766138,0.054246023,0.00005162439],"about_ca_topic_score_codex":0.000027650787,"about_ca_topic_score_gemma":0.000042663843,"teacher_disagreement_score":0.6954802,"about_ca_system_score_codex":0.00027463923,"about_ca_system_score_gemma":0.002529369,"threshold_uncertainty_score":0.4805962},"labels":[],"label_agreement":null},{"id":"W4408329028","doi":"10.18060/28006","title":"Assessment in Higher Education and Student Affairs Graduate Education","year":2024,"lang":"en","type":"article","venue":"Journal of Student Affairs Inquiry Improvement and Impact","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Student affairs; Higher education; Graduate education; Pedagogy; Political science; Graduate students; Medical education; Mathematics education; Sociology; Psychology; Medicine; Law","score_opus":0.07429800249368668,"score_gpt":0.44500567858384954,"score_spread":0.37070767609016286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408329028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9672796,0.0048662163,0.000020123673,0.0036402617,0.006580287,0.00066319166,0.0000023151424,0.00003063776,0.016917352],"genre_scores_gemma":[0.9913893,0.004283904,0.00019144699,0.00011841437,0.0018898755,0.000034539364,0.000004682113,0.000024914798,0.002062924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970244,0.00016668689,0.0007722474,0.0003330054,0.0012625047,0.00044111226],"domain_scores_gemma":[0.9988423,0.00013034084,0.00035204896,0.00014594509,0.00021545007,0.00031389436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018630725,0.00029549326,0.00040823693,0.00062458584,0.00024029138,0.00094534986,0.00032375296,0.00011102943,0.00025412024],"category_scores_gemma":[0.000019695346,0.00023493283,0.00015974934,0.00047842317,0.00021821572,0.0012341044,0.00015565417,0.0004735572,0.0000052547853],"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":[0.00010360492,0.004521396,0.62505543,0.00023167815,0.0009110404,0.000041686624,0.13302457,0.000014319576,0.0037478218,0.023649076,0.020873914,0.18782544],"study_design_scores_gemma":[0.00071161817,0.00084895233,0.75684935,0.00035086315,0.00014700717,0.0000067216474,0.23548166,0.000009595094,0.000014474182,0.0010513078,0.004263403,0.00026504396],"about_ca_topic_score_codex":0.00018284406,"about_ca_topic_score_gemma":0.000087851244,"teacher_disagreement_score":0.1875604,"about_ca_system_score_codex":0.0009195497,"about_ca_system_score_gemma":0.0013729446,"threshold_uncertainty_score":0.9580283},"labels":[],"label_agreement":null},{"id":"W4408534011","doi":"10.5430/wjel.v15n4p327","title":"Comparative Analysis of Feedback Practices and Perspectives in Online Academic Writing Assessments at Two Regional Tertiary Institutions","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Academic writing; Tertiary level; Tertiary care; Mathematics education; Political science; Psychology; Medicine","score_opus":0.08060432853243352,"score_gpt":0.4593552918058232,"score_spread":0.37875096327338964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408534011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96225685,0.004166159,0.0000154681,0.00090643,0.00017337511,0.00010010862,0.000010314399,0.000008018711,0.032363247],"genre_scores_gemma":[0.9972209,0.0006213819,0.00084117777,0.00010609409,0.00027837502,0.0000017036639,0.000007741605,0.0000024765745,0.00092014903],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985276,0.0002771109,0.00048530177,0.00014592409,0.00039383364,0.00017026866],"domain_scores_gemma":[0.99803835,0.0006163746,0.0008157167,0.00007590195,0.00039080824,0.000062862404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009901744,0.00009724332,0.00039315948,0.0009924882,0.00017647265,0.000047513793,0.00024247666,0.00004690736,0.00010079436],"category_scores_gemma":[0.0006721731,0.000089290384,0.00011978371,0.0017275119,0.00027416882,0.0005889018,0.00008634141,0.0004282449,2.9491585e-7],"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":[0.00008448005,0.00026614504,0.81430924,0.000011159374,0.00085838593,0.000018746188,0.17202853,0.0001602274,0.0005887265,0.010654403,0.00053363043,0.000486357],"study_design_scores_gemma":[0.0008086364,0.00001886249,0.57288516,0.00018011946,0.0004925178,5.118788e-7,0.42190197,0.00007873266,0.00003197817,0.000051718016,0.0034625167,0.000087313245],"about_ca_topic_score_codex":0.00046506408,"about_ca_topic_score_gemma":0.016700685,"teacher_disagreement_score":0.24987343,"about_ca_system_score_codex":0.00024841103,"about_ca_system_score_gemma":0.00023825819,"threshold_uncertainty_score":0.9319374},"labels":[],"label_agreement":null},{"id":"W4408596861","doi":"10.5539/jel.v14n4p241","title":"Errors in Chinese Post Graduate Students’ Writing in an International Program at a Thai Public University","year":2025,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Graduate students; Mathematics education; Public university; Statistical analysis; Medical education; Pedagogy; Political science; Statistics; Medicine; Mathematics","score_opus":0.03677948400717187,"score_gpt":0.4250899526048032,"score_spread":0.38831046859763135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408596861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9871488,0.000040513183,0.0000026516668,0.004266654,0.00040142395,0.000076806355,8.370821e-8,0.000006453961,0.008056604],"genre_scores_gemma":[0.99738705,0.00011440994,0.0002162458,0.00007118558,0.00009502915,7.1217215e-7,0.0000024175379,0.000001786438,0.0021111586],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99918705,0.0002459705,0.00016161658,0.00007117451,0.00023665631,0.00009750706],"domain_scores_gemma":[0.99955755,0.00006982421,0.00014246018,0.000023054195,0.00015619671,0.000050922063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011253029,0.000041450323,0.00007882301,0.0003873911,0.00019809896,0.00015042898,0.00019036481,0.000028722141,0.00005523415],"category_scores_gemma":[0.00028706228,0.0000403119,0.000023951894,0.00038625288,0.00003690581,0.0005723963,0.000045011715,0.00026545336,8.212562e-7],"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":[0.000018146777,0.00030647469,0.95689625,0.0000024003577,0.000007782643,0.0000022922018,0.02365541,0.000008309243,0.00001760571,0.0005490656,0.00002412652,0.018512128],"study_design_scores_gemma":[0.00033291383,0.000033543616,0.8607139,0.000045906858,0.000003059374,9.0045296e-7,0.13284628,0.0000407046,1.4712857e-7,0.000036559886,0.005913441,0.00003266938],"about_ca_topic_score_codex":0.00029257612,"about_ca_topic_score_gemma":0.0023111918,"teacher_disagreement_score":0.109190874,"about_ca_system_score_codex":0.00023876657,"about_ca_system_score_gemma":0.00026673658,"threshold_uncertainty_score":0.16438715},"labels":[],"label_agreement":null},{"id":"W4408741152","doi":"10.1080/13562517.2025.2468598","title":"The multiplicity of authenticity in higher education assessment","year":2025,"lang":"en","type":"article","venue":"Teaching in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Higher education; Mathematics education; Multiplicity (mathematics); Pedagogy; Psychology; Sociology; Mathematics; Political science","score_opus":0.047747205810736326,"score_gpt":0.4288700821852897,"score_spread":0.3811228763745534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408741152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7898162,0.0002067743,0.000010790146,0.01229605,0.004205088,0.00040953525,5.0029655e-7,0.00002705546,0.19302802],"genre_scores_gemma":[0.95290005,0.000028537255,0.0005044246,0.0002216548,0.00023852216,0.00011525263,0.000007659967,0.0000055861597,0.045978285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984651,0.0004971493,0.0003353644,0.00019750724,0.00028836343,0.00021647156],"domain_scores_gemma":[0.9992002,0.00035482302,0.0001445443,0.00021654095,0.00005316762,0.000030693816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015671997,0.000094568575,0.00013236684,0.00018359494,0.00035599165,0.0000884231,0.00033645288,0.00008663074,0.00017221352],"category_scores_gemma":[0.000070368194,0.00008181955,0.000041432122,0.00044091273,0.000101823745,0.00018958216,0.000049543793,0.00030846297,0.0000045034335],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056306467,0.000680553,0.6410243,0.000012478431,0.000006668548,2.5269813e-8,0.006097639,0.0000046047467,0.000097701726,0.3419157,0.0018023775,0.008352312],"study_design_scores_gemma":[0.00015648761,0.0000064480328,0.93279326,0.000092724375,0.000010370473,1.075719e-8,0.004821569,0.000019008188,0.0000071287527,0.008869981,0.053148467,0.00007453882],"about_ca_topic_score_codex":0.009247896,"about_ca_topic_score_gemma":0.0028070481,"teacher_disagreement_score":0.33304572,"about_ca_system_score_codex":0.0006394504,"about_ca_system_score_gemma":0.00089876045,"threshold_uncertainty_score":0.9973496},"labels":[],"label_agreement":null},{"id":"W4408961082","doi":"10.1080/00131911.2025.2475829","title":"An interdisciplinary review of learning through failure in higher education","year":2025,"lang":"en","type":"article","venue":"Educational Review","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Higher education; Mathematics education; Engineering ethics; Pedagogy; Psychology; Sociology; Engineering; Economic growth; Economics","score_opus":0.04710432301078445,"score_gpt":0.48620981867136687,"score_spread":0.43910549566058243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408961082","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076981774,0.5292183,0.0000059878075,0.16680379,0.00091329095,0.0006153538,7.506716e-7,0.00001367207,0.30165905],"genre_scores_gemma":[0.12123399,0.8002166,0.0020108065,0.010763528,0.0006969233,0.00039340864,0.00016366846,0.000012351881,0.0645087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998832,0.0003025453,0.00033897985,0.00016673307,0.0002455912,0.00011418589],"domain_scores_gemma":[0.99937207,0.00013273959,0.00014286906,0.0001469539,0.00017416978,0.000031183776],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007767383,0.00007557113,0.00023126189,0.000053840376,0.0001361812,0.000015295387,0.00027042307,0.00003360741,0.0052012317],"category_scores_gemma":[0.00019967573,0.00007109651,0.00006961567,0.00074187655,0.000065967164,0.00028082656,0.000049704075,0.00012557957,0.0000476969],"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":[0.000002911861,0.00076954154,0.039226327,0.020847427,0.000024925588,1.3469771e-7,0.003494797,6.8426755e-7,0.000011463584,0.6132605,0.2772845,0.045076806],"study_design_scores_gemma":[0.000045075674,0.000015078521,0.04659695,0.063291624,0.000042917043,1.3730129e-7,0.0018272197,2.0493421e-7,5.399574e-7,0.007869236,0.8802208,0.00009022162],"about_ca_topic_score_codex":0.000098412595,"about_ca_topic_score_gemma":0.00008957788,"teacher_disagreement_score":0.60539126,"about_ca_system_score_codex":0.00013579904,"about_ca_system_score_gemma":0.0012644574,"threshold_uncertainty_score":0.99570817},"labels":[],"label_agreement":null},{"id":"W4408998993","doi":"10.3390/educsci15040438","title":"Formative Assessment in Upper Secondary Schools: Ideas, Concepts, and Strategies","year":2025,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Mathematics education; Computer science; Pedagogy; Psychology","score_opus":0.02534208960626211,"score_gpt":0.4571228579096512,"score_spread":0.4317807683033891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408998993","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49397823,0.0008870053,0.00009690982,0.007951587,0.00090353086,0.00023005246,0.0000010935942,0.000023257355,0.49592832],"genre_scores_gemma":[0.994646,0.0002485543,0.0016380893,0.00041800854,0.000059490267,0.000047585738,0.0000018788407,0.000001341666,0.0029390582],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99894524,0.0001487356,0.00018082916,0.00020706112,0.00031197,0.00020614201],"domain_scores_gemma":[0.9995963,0.00014369462,0.00006794545,0.00006580418,0.00007719169,0.00004907043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009988935,0.00007205889,0.00009979591,0.00021466332,0.00062826707,0.0005664243,0.000258569,0.000040317304,0.00027283037],"category_scores_gemma":[0.00007753419,0.00006417769,0.00001866777,0.00078800967,0.00055576774,0.0014228423,0.00004630354,0.00015587044,0.000010803226],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011970578,0.00006338762,0.26241788,0.000008343099,0.0000045318643,9.8331085e-8,0.024426622,0.0000017512717,0.000023392153,0.69199824,0.004171673,0.016882878],"study_design_scores_gemma":[0.000119827375,0.000016063019,0.40553653,0.00006355761,0.0000032320397,8.358376e-8,0.53638566,0.000020466174,0.000009883163,0.037689645,0.020077668,0.00007737121],"about_ca_topic_score_codex":0.0013809045,"about_ca_topic_score_gemma":0.001157068,"teacher_disagreement_score":0.6543086,"about_ca_system_score_codex":0.00011694846,"about_ca_system_score_gemma":0.005063883,"threshold_uncertainty_score":0.8983111},"labels":[],"label_agreement":null},{"id":"W4409046326","doi":"10.1016/b978-0-323-95504-1.00418-x","title":"Learning-Oriented Assessment (LOA)","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; McGill University","funders":"","keywords":"Loa loa; Computer science; Psychology; Biology; Zoology","score_opus":0.01721180118315386,"score_gpt":0.3258029582369012,"score_spread":0.30859115705374734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409046326","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040687795,0.00038211935,0.000009893074,0.0004053481,0.001616275,0.0007983477,0.00001053516,0.00025633455,0.99648046],"genre_scores_gemma":[0.0009847938,0.0005671862,0.0004212636,0.00024619952,0.00084916933,0.000052374937,0.000048238428,0.00005154606,0.9967792],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971306,0.00014157874,0.0004635319,0.0005984648,0.0011353372,0.0005304885],"domain_scores_gemma":[0.9986558,0.00019940926,0.00032980324,0.0003830631,0.00024475015,0.00018716391],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080125453,0.00043661695,0.00058878266,0.00018669046,0.0008749945,0.00018072328,0.00057054346,0.0005251289,0.0020693254],"category_scores_gemma":[0.000057846646,0.00045414836,0.00036721036,0.000045162345,0.0003645386,0.00006894428,0.00026827096,0.0010142366,0.0003244186],"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":[0.000006575877,0.000014613438,0.000395064,0.000028486877,0.00016828357,0.000017688744,0.0015924063,2.6331296e-7,0.0000018841212,0.22038993,0.0026900724,0.77469474],"study_design_scores_gemma":[0.00027960297,0.00006847789,0.00018547424,0.0002964396,0.00017151966,2.790047e-7,0.00053580885,0.0000049163486,8.7161595e-7,0.004203957,0.99380314,0.00044949428],"about_ca_topic_score_codex":0.0000115475095,"about_ca_topic_score_gemma":0.00019884534,"teacher_disagreement_score":0.99111307,"about_ca_system_score_codex":0.00045062415,"about_ca_system_score_gemma":0.00091678597,"threshold_uncertainty_score":0.999791},"labels":[],"label_agreement":null},{"id":"W4409147234","doi":"10.1080/10400419.2025.2485887","title":"Supporting Creative Thinking Using Online Peer Assessment: Student Perceptions and Team Processes in Higher Education","year":2025,"lang":"en","type":"article","venue":"Creativity Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto; Queen's University","funders":"","keywords":"Creativity; Psychology; Perception; Peer assessment; Higher education; Peer evaluation; Creative thinking; Pedagogy; Mathematics education; Applied psychology; Social psychology","score_opus":0.16585881592418503,"score_gpt":0.570853872350848,"score_spread":0.4049950564266629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409147234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8667167,0.00037800803,0.00015885447,0.006439624,0.00022184332,0.00042424208,0.000003866571,0.000020449317,0.12563643],"genre_scores_gemma":[0.96285164,0.00056225935,0.002025864,0.000073631556,0.00050324365,0.000023510398,0.0000073320693,0.00000960767,0.0339429],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99599195,0.0011510878,0.00034920455,0.00028020516,0.0016236953,0.0006038766],"domain_scores_gemma":[0.99753666,0.0006523937,0.00014306881,0.00010784197,0.0013926423,0.00016738816],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0068740556,0.00012829543,0.00023044356,0.00063358224,0.002420642,0.0010829952,0.00035949142,0.000099855424,0.00085133826],"category_scores_gemma":[0.0011710294,0.00011725754,0.000043858534,0.0013385089,0.00044785038,0.0008918252,0.00022414874,0.0010541612,0.0000025539964],"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":[0.000016051259,0.00087745395,0.95597893,0.00003938227,0.000043423483,0.0000062817794,0.031373873,0.0000087738845,0.00029391347,0.0058702915,0.0015783266,0.003913313],"study_design_scores_gemma":[0.00038825706,0.000051467272,0.80124545,0.0004128382,0.000024650206,0.000003177498,0.18464051,0.0000545256,0.000006698654,0.007296712,0.0057614245,0.000114282644],"about_ca_topic_score_codex":0.001228164,"about_ca_topic_score_gemma":0.0018218105,"teacher_disagreement_score":0.15473346,"about_ca_system_score_codex":0.0009902117,"about_ca_system_score_gemma":0.0039071343,"threshold_uncertainty_score":0.999954},"labels":[],"label_agreement":null},{"id":"W4409225263","doi":"10.1111/medu.15706","title":"Untangling feedback: Mapping the patterns behind the practice","year":2025,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research; Royal College of Physicians and Surgeons of Canada","keywords":"Coaching; Divergence (linguistics); Computer science; Audit; Diversity (politics); Perspective (graphical); Convergence (economics); Psychology; Data science; Cognitive psychology; Artificial intelligence","score_opus":0.022511260621877003,"score_gpt":0.3949465201244899,"score_spread":0.37243525950261286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409225263","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10665981,0.0006984302,0.0013167608,0.65957093,0.0045030667,0.0004372702,4.473784e-7,0.000049525683,0.22676378],"genre_scores_gemma":[0.96477044,0.00033687594,0.00009971686,0.024728874,0.0012463963,0.00005927752,0.00000511951,0.000004072264,0.008749211],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998597,0.00030680004,0.00014512637,0.00011990431,0.00065680366,0.00017432607],"domain_scores_gemma":[0.9987751,0.0008514829,0.00006917033,0.0001541586,0.000106528016,0.000043528602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020803958,0.000054529566,0.000055935212,0.00003210497,0.00088991417,0.00015820906,0.0004640504,0.00006831932,0.0006683944],"category_scores_gemma":[0.0036438545,0.0000314755,0.000034092634,0.00028366572,0.00017221128,0.00014726658,0.00006019463,0.00024351373,0.000047704936],"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":[0.000012903149,0.0004910439,0.10655283,0.000024946099,0.00009467943,0.0000016761253,0.17870787,0.0000011470391,0.000007981623,0.11043218,0.23399836,0.36967438],"study_design_scores_gemma":[0.0000848196,0.000003374282,0.049462315,0.00007356821,0.000027502338,4.5892256e-7,0.16210938,0.00003937983,0.0000025749257,0.0007520493,0.7873999,0.000044674704],"about_ca_topic_score_codex":0.0022049723,"about_ca_topic_score_gemma":0.0011801696,"teacher_disagreement_score":0.85811067,"about_ca_system_score_codex":0.00010006857,"about_ca_system_score_gemma":0.0014923458,"threshold_uncertainty_score":0.73184496},"labels":[],"label_agreement":null},{"id":"W4409835544","doi":"10.59944/postaxial.v3i1.416","title":"Rethinking Assessment and Evaluation: Towards a Holistic Approach to Measuring Student Success","year":2025,"lang":"en","type":"article","venue":"International Journal of Post Axial Futuristic Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Holistic education; Engineering ethics; Psychology; Mathematics education; Pedagogy; Management science; Sociology; Medical education; Engineering; Medicine","score_opus":0.05991971905779656,"score_gpt":0.43043897238728857,"score_spread":0.370519253329492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409835544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93346524,0.00036948314,0.0159264,0.003833147,0.0023732274,0.00020090133,0.0000013971876,0.000025777033,0.043804396],"genre_scores_gemma":[0.99254227,0.000045696666,0.005391629,0.00021632454,0.0013163799,0.0000057288908,0.0000037657414,0.000007932646,0.0004702692],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966741,0.0010245448,0.0004142782,0.00020516786,0.0014904555,0.00019145518],"domain_scores_gemma":[0.9983797,0.00045144805,0.00026840353,0.000055115826,0.000718882,0.00012642329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007934259,0.00012861217,0.00022661405,0.00034514596,0.00094702665,0.00068754936,0.0004062229,0.00006627039,0.000024796065],"category_scores_gemma":[0.0019162928,0.00011843511,0.00006432262,0.00010668903,0.000075658034,0.00025769277,0.00017531817,0.0010088674,7.618642e-7],"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":[0.00027789935,0.00042973747,0.22911382,0.000060523224,0.0009510552,0.00005009962,0.27379277,0.0027285072,0.00043083582,0.09657983,0.00046333048,0.3951216],"study_design_scores_gemma":[0.0019837257,0.00021893968,0.9068031,0.0006571277,0.00033303307,0.00003904482,0.069259495,0.0032851254,0.0000032323478,0.0026425633,0.014435725,0.00033894146],"about_ca_topic_score_codex":0.00063797977,"about_ca_topic_score_gemma":0.00005195467,"teacher_disagreement_score":0.67768925,"about_ca_system_score_codex":0.00040531496,"about_ca_system_score_gemma":0.00039105304,"threshold_uncertainty_score":0.72838587},"labels":[],"label_agreement":null},{"id":"W4409835840","doi":"10.59944/postaxial.v3i2.442","title":"Culturally Responsive Assessment and Evaluation Practices in Multilingual Classrooms","year":2025,"lang":"en","type":"article","venue":"International Journal of Post Axial Futuristic Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Linguistics; Psychology; Computer science; Mathematics education; Natural language processing","score_opus":0.03007877792885581,"score_gpt":0.4561858292430154,"score_spread":0.42610705131415955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409835840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9827156,0.00037292796,0.00030920224,0.007186826,0.0013051148,0.00010633382,8.6372194e-7,0.000009457471,0.007993664],"genre_scores_gemma":[0.9963513,0.00015734875,0.0020111613,0.00011916318,0.0006603254,0.0000018316642,0.0000040673185,0.0000037200075,0.00069105806],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972317,0.0014621915,0.0003430274,0.00013391513,0.00070432294,0.00012482786],"domain_scores_gemma":[0.99729544,0.0014804922,0.00057927024,0.0000286036,0.00056660024,0.00004959315],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006199029,0.00008369664,0.0001451556,0.00027960446,0.00042812794,0.00031080004,0.00018370688,0.00006437182,0.000042534695],"category_scores_gemma":[0.009009758,0.000073155825,0.000038629565,0.00006768323,0.00008245584,0.00038912118,0.00006221256,0.0009925389,6.3828196e-7],"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":[0.00075413554,0.00020700064,0.3648422,0.000016563385,0.00032069616,0.00009491884,0.115020916,0.00048831385,0.0018683723,0.021531375,0.00023634413,0.49461916],"study_design_scores_gemma":[0.0022586943,0.00020180011,0.8015314,0.0003751755,0.00011937648,0.00002470669,0.15821064,0.003758901,0.0000038441194,0.0011271248,0.03222048,0.00016787126],"about_ca_topic_score_codex":0.000995397,"about_ca_topic_score_gemma":0.00041785958,"teacher_disagreement_score":0.49445128,"about_ca_system_score_codex":0.00025172133,"about_ca_system_score_gemma":0.00040797325,"threshold_uncertainty_score":0.9993378},"labels":[],"label_agreement":null},{"id":"W4409954575","doi":"10.1002/berj.4181","title":"Preservice teachers' assessment decisions: Exploring the role of fairness conceptions","year":2025,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Psychology; Mathematics education; Pedagogy; Educational research; Sociology","score_opus":0.16526556795964736,"score_gpt":0.5029873425817295,"score_spread":0.33772177462208214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409954575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61201537,0.0028610737,0.00021760569,0.030097073,0.0011544855,0.0005363143,0.000010152948,0.000012137762,0.35309577],"genre_scores_gemma":[0.9819327,0.0031858168,0.0009764956,0.000057568068,0.00066267216,0.00019843125,0.0000048838538,0.000006439113,0.012975005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99644446,0.00088159903,0.00032077616,0.00016462029,0.001776484,0.00041205855],"domain_scores_gemma":[0.9946849,0.0035949394,0.000081471895,0.00016527686,0.0013214339,0.0001519742],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047622374,0.00006163505,0.00011443407,0.00021000711,0.0026141217,0.00073367497,0.0010185651,0.000045267505,0.0020928574],"category_scores_gemma":[0.0030913472,0.000059338618,0.000091100046,0.0009866614,0.0005323822,0.0005577697,0.00018710934,0.00070137734,0.000020022078],"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":[0.000022611215,0.00083249714,0.28161108,0.000008919408,0.00016616567,0.0000035037274,0.016623741,0.000031924366,0.00027285237,0.46051988,0.092186816,0.14772],"study_design_scores_gemma":[0.00020934317,0.000019389472,0.6215304,0.00025267826,0.000010633595,0.0000071520903,0.10785473,0.000015754806,0.000010755182,0.084750816,0.18527618,0.00006213071],"about_ca_topic_score_codex":0.00324822,"about_ca_topic_score_gemma":0.0024075196,"teacher_disagreement_score":0.37576905,"about_ca_system_score_codex":0.00039166288,"about_ca_system_score_gemma":0.0035877875,"threshold_uncertainty_score":0.99881935},"labels":[],"label_agreement":null},{"id":"W4410015948","doi":"10.1080/15434303.2025.2497818","title":"On the Interplay Between Conceptions of Assessment and Assessment Agency: Perspectives of Iranian EFL Preservice Teachers","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics education; Pedagogy; Agency (philosophy); Psychology; Alternative assessment; Semi-structured interview; Qualitative research; Sociology; Social science","score_opus":0.017476476578897192,"score_gpt":0.4119940254646767,"score_spread":0.39451754888577956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410015948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8479688,0.00022318623,0.0020148205,0.0038874864,0.00021555899,0.00094161415,0.000051983712,0.00006195569,0.1446346],"genre_scores_gemma":[0.9957344,0.00006212567,0.0021840308,0.00014146756,0.00011399222,0.00009997735,0.00002124134,0.00001787504,0.0016248949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966862,0.00090709626,0.000596832,0.00046377914,0.0008885299,0.0004575244],"domain_scores_gemma":[0.9974739,0.0012755727,0.00039100883,0.00056113536,0.00019313155,0.000105253974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017433671,0.00028250107,0.000517161,0.00023046279,0.0004996376,0.0001572197,0.0007528146,0.00014336954,0.0006956308],"category_scores_gemma":[0.00004457453,0.0002212195,0.00018469631,0.000578091,0.0005743835,0.00029499936,0.00011437288,0.0004928942,0.0000034877862],"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":[0.000024332732,0.0007222304,0.22937746,0.00009805688,0.0007415653,0.0000065674963,0.3489155,0.000004347066,0.0035698793,0.39210847,0.0012569814,0.023174599],"study_design_scores_gemma":[0.0007276802,0.00052838074,0.56086797,0.00017533246,0.00017187085,1.4438429e-7,0.43417472,0.00007823697,0.00004469846,0.002535828,0.00050051307,0.00019466419],"about_ca_topic_score_codex":0.0022795077,"about_ca_topic_score_gemma":0.0009944428,"teacher_disagreement_score":0.38957265,"about_ca_system_score_codex":0.000330875,"about_ca_system_score_gemma":0.0005849473,"threshold_uncertainty_score":0.9021069},"labels":[],"label_agreement":null},{"id":"W4410019844","doi":"10.36834/cmej.81477","title":"Embracing the next frontier in assessment","year":2025,"lang":"en","type":"editorial","venue":"Canadian Medical Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Frontier; Computer science; Data science; Computational biology; Biology; Geography; Archaeology","score_opus":0.014186935595631762,"score_gpt":0.3787503147277961,"score_spread":0.3645633791321643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410019844","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004130124,0.0008779409,0.000010363705,0.06209691,0.7478029,0.00018651105,0.0000051425277,0.000006672064,0.18897222],"genre_scores_gemma":[0.0009346984,0.0015724279,0.000121051664,0.0066161393,0.95787615,0.000043234068,0.000052028896,0.000015901973,0.03276838],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99567217,0.00060832506,0.00048193944,0.00023025375,0.0024094551,0.00059784204],"domain_scores_gemma":[0.9952316,0.0006481306,0.00020959746,0.00019241213,0.00045369225,0.003264512],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004047531,0.00017249318,0.00026884142,0.00048392505,0.0010995669,0.0007808611,0.0011991683,0.00086482085,0.018217403],"category_scores_gemma":[0.022981606,0.00013823525,0.00011349925,0.0005129087,0.00023283328,0.0002288259,0.00003559601,0.0032463097,0.00003537827],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018855153,0.000034275585,0.00029664705,0.000007840281,0.000024669336,0.000014649229,0.0032740065,3.1911466e-7,1.9606444e-8,0.0018611281,0.9734012,0.02108338],"study_design_scores_gemma":[0.00019023623,0.0000072336375,0.0009526012,0.0003758112,0.000028011584,0.0000013534781,0.016296312,0.000007836675,9.784456e-9,0.001209764,0.9807904,0.00014042451],"about_ca_topic_score_codex":0.14125876,"about_ca_topic_score_gemma":0.6148044,"teacher_disagreement_score":0.47354564,"about_ca_system_score_codex":0.0029642503,"about_ca_system_score_gemma":0.36967286,"threshold_uncertainty_score":0.99905324},"labels":[],"label_agreement":null},{"id":"W4410358712","doi":"10.1080/29984475.2025.2501997","title":"Protocol for a Systematic Review of the Impact of Test Preparation Practices on L2 Test Performance and Language Proficiency","year":2025,"lang":"en","type":"review","venue":"Research Synthesis in Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Western University","funders":"","keywords":"Protocol (science); Test (biology); Computer science; Test preparation; Medicine; Engineering; Biology; Manufacturing engineering","score_opus":0.16362987987667385,"score_gpt":0.5843519821444451,"score_spread":0.4207221022677712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410358712","genre_codex":"protocol","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004204814,0.36832547,0.0000016132643,0.000021598978,0.00004647377,0.50388443,0.00011050719,0.000019251005,0.12758645],"genre_scores_gemma":[0.0010295697,0.724506,0.0001471219,0.0000025275183,0.00014165585,0.27376735,0.0000031990223,0.000016269745,0.0003862702],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9965168,0.00076767016,0.0009783136,0.0003235291,0.001060788,0.00035285298],"domain_scores_gemma":[0.9687243,0.028541842,0.0016688459,0.0005252584,0.00049265247,0.000047112087],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009082586,0.00022771244,0.0014097459,0.00026975822,0.00026224062,0.00006652352,0.0008169725,0.00017907696,0.000014221426],"category_scores_gemma":[0.21116042,0.00013143709,0.00022036367,0.0011455031,0.00032595068,0.000016957505,0.0001560413,0.00037344,0.0000026754271],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014980643,0.00033788197,0.00014972176,0.99077195,0.000038141876,2.6885408e-7,0.0005941041,2.677456e-7,0.0000010329403,0.0019640091,0.00026530266,0.0058623184],"study_design_scores_gemma":[0.00011618027,0.00021206097,0.00002724522,0.9758402,0.0003254426,1.7224895e-7,0.00054014014,0.00004329642,0.000020015203,0.00004216559,0.022670226,0.00016286051],"about_ca_topic_score_codex":0.000106649684,"about_ca_topic_score_gemma":0.000029033876,"teacher_disagreement_score":0.35618058,"about_ca_system_score_codex":0.00031233663,"about_ca_system_score_gemma":0.0020427718,"threshold_uncertainty_score":0.7954843},"labels":[],"label_agreement":null},{"id":"W4410373832","doi":"10.53761/7jj6at39","title":"Online Student Peer-Assessment in Higher Education: A Systematic Review of the Literature","year":2025,"lang":"en","type":"review","venue":"Journal of University Teaching and Learning Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Peer evaluation; Higher education; Psychology; Multimethodology; Mathematics education; Pedagogy; Medical education; Medicine; Political science","score_opus":0.03655516409390172,"score_gpt":0.4290288710822172,"score_spread":0.3924737069883155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410373832","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011334595,0.9737013,0.0000027488645,0.006575467,0.0005734106,0.0004627778,0.0000016729247,0.000004708811,0.018666573],"genre_scores_gemma":[0.000051738745,0.9488183,0.00052864203,0.00018831683,0.00014626347,5.1604866e-7,0.000003455615,0.000004885162,0.050257884],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.98717684,0.01127325,0.00054883707,0.00012472346,0.0007658848,0.000110465095],"domain_scores_gemma":[0.9937742,0.0032289082,0.002366632,0.00014022342,0.00043862034,0.00005145933],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009672244,0.00014792493,0.0010790495,0.0002504969,0.0004928609,0.00010403633,0.00058034394,0.0001285103,0.000020529364],"category_scores_gemma":[0.0047605494,0.00010063941,0.00031064925,0.0005629035,0.000046765992,0.00040535032,0.0001444417,0.0033015963,3.6864873e-7],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001101651,0.0009520595,0.00022500723,0.93841136,0.0005481347,0.000040364688,0.018987427,0.0000017461705,2.1720952e-8,0.0059957244,0.002777982,0.032049134],"study_design_scores_gemma":[0.00006486533,0.000021221764,0.000083540675,0.4344257,0.0017284697,0.0000104070705,0.016149933,6.51204e-8,1.528233e-10,0.0000013558733,0.5474648,0.00004968217],"about_ca_topic_score_codex":0.00011722827,"about_ca_topic_score_gemma":0.000013057835,"teacher_disagreement_score":0.5446868,"about_ca_system_score_codex":0.0004292511,"about_ca_system_score_gemma":0.0017391737,"threshold_uncertainty_score":0.9989978},"labels":[],"label_agreement":null},{"id":"W4410839902","doi":"10.1038/s41598-025-03753-7","title":"A phenomenographic study on Chinese EFL teachers’ cognitions of positive and negative educational, social, and psychological consequences of high-stake tests","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Phenomenography; Psychology; Cognition; Social psychology; Developmental psychology; Clinical psychology; Mathematics education; Psychiatry","score_opus":0.05859291485390382,"score_gpt":0.4162507589408014,"score_spread":0.35765784408689755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410839902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836236,0.000092633374,0.000002055933,0.0013594134,0.00076007086,0.00061346684,0.0000114579125,0.000013165549,0.013524104],"genre_scores_gemma":[0.9988479,0.000013539596,0.00009194514,0.000025833971,0.000028750275,0.000035618643,0.000009765814,0.000002611221,0.0009440522],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998409,0.00021555509,0.0003437499,0.0004383971,0.0004422427,0.0001510973],"domain_scores_gemma":[0.99873406,0.00048014527,0.00030577753,0.00014120624,0.00028598876,0.00005282803],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012028019,0.00010182994,0.00023099656,0.00025314858,0.00076975435,0.000123559,0.00009643796,0.000051908435,0.000065523585],"category_scores_gemma":[0.0005122192,0.00008326335,0.000042338976,0.0010328556,0.002958379,0.00012337785,0.000047355377,0.000085868895,5.839491e-7],"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":[0.000018940505,0.001489877,0.9193406,0.0000093623985,0.000098831995,0.000008495133,0.06511841,2.122244e-7,0.0023007086,0.009884165,0.0010480249,0.00068234873],"study_design_scores_gemma":[0.00023247542,0.00014214433,0.89848614,0.000036944617,0.000044501863,0.0000013488419,0.038884543,1.3590672e-7,0.00007047363,0.06198713,0.000041266976,0.00007290293],"about_ca_topic_score_codex":0.0005411753,"about_ca_topic_score_gemma":0.0004611305,"teacher_disagreement_score":0.052102968,"about_ca_system_score_codex":0.000022534656,"about_ca_system_score_gemma":0.00018391736,"threshold_uncertainty_score":0.999755},"labels":[],"label_agreement":null},{"id":"W4410870169","doi":"10.1007/978-3-031-76485-1_44","title":"Teaching Within Social Justice and Diversity Frameworks: A (White) Teacher’s Approach","year":2025,"lang":"en","type":"book-chapter","venue":"Springer international handbooks of education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Social justice; Diversity (politics); White (mutation); Sociology; Pedagogy; Economic Justice; Political science; Criminology; Anthropology; Biology; Law","score_opus":0.03255359092607509,"score_gpt":0.3448269454730962,"score_spread":0.31227335454702115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410870169","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014742758,0.00026205336,0.00058622187,0.0011643276,0.0025935112,0.00028808997,0.000015615447,0.000040516672,0.9935754],"genre_scores_gemma":[0.12915774,0.0001200737,0.0035077806,0.00024626436,0.0021105788,0.000011456139,0.000059323505,0.000017999715,0.8647688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850625,0.000042301388,0.00029705418,0.00034618913,0.0006653788,0.0001428475],"domain_scores_gemma":[0.9990645,0.0000822486,0.0003878994,0.00011896146,0.0002856293,0.000060753595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060824194,0.00019575772,0.00023718932,0.00026864413,0.0007752346,0.000110878056,0.000481389,0.00047985118,0.00024793492],"category_scores_gemma":[0.000116006915,0.00022465788,0.00011528151,0.000024391575,0.00025216726,0.00017815961,0.00042043714,0.0007681856,0.0000051743696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034751167,0.00014152842,0.0045405207,0.000116679,0.00022382873,3.3004991e-7,0.0393029,0.0000010334346,0.0000059586723,0.93339247,0.0105270455,0.011712948],"study_design_scores_gemma":[0.0014814426,0.00010336532,0.017075103,0.0030515897,0.0028469893,0.0000028644329,0.060901087,0.00026138412,0.000020259751,0.17664689,0.7355756,0.0020333761],"about_ca_topic_score_codex":0.00060293864,"about_ca_topic_score_gemma":0.00010913746,"teacher_disagreement_score":0.7567456,"about_ca_system_score_codex":0.00030186388,"about_ca_system_score_gemma":0.0004230342,"threshold_uncertainty_score":0.9161282},"labels":[],"label_agreement":null},{"id":"W4410967522","doi":"10.21083/ajote.v14i1.8038","title":"Teachers’ conceptualization of validity and reliability in classroom assessment in Ghana","year":2025,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conceptualization; Psychology; Reliability (semiconductor); Validity; Test validity; Mathematics education; Construct validity; Psychometrics; Computer science; Developmental psychology; Artificial intelligence; Physics","score_opus":0.030491168946546555,"score_gpt":0.389104163268703,"score_spread":0.35861299432215643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410967522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97535664,0.00016650303,0.00028380693,0.0030823466,0.00036656985,0.00016386526,3.5494776e-7,0.0000033080696,0.020576606],"genre_scores_gemma":[0.99778426,0.000067723304,0.0014748605,0.000034241817,0.00007199199,0.0000052975065,0.0000012180813,0.0000029338203,0.0005574769],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984099,0.00062532205,0.00046574208,0.00010809878,0.00027170512,0.000119209646],"domain_scores_gemma":[0.9992044,0.0001642455,0.00033288889,0.00008397005,0.00016961912,0.000044857567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025819214,0.0000644688,0.0001980446,0.00026425198,0.000047327143,0.000027678421,0.00015750782,0.00006737364,0.000054352222],"category_scores_gemma":[0.00043648892,0.00006274004,0.000038103182,0.0005590813,0.00015062006,0.00026139314,0.000021209025,0.00023090653,2.3815328e-7],"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":[0.000011140259,0.00049178983,0.94345593,0.000008499434,0.000004947393,2.024189e-7,0.04605026,0.0000057019465,0.00007418186,0.0043677413,0.000568062,0.0049615153],"study_design_scores_gemma":[0.00031993436,0.00004320687,0.80385697,0.000072139475,0.000017615128,1.5961274e-7,0.19150378,0.000014386308,0.000016841315,0.0024260725,0.0016809469,0.00004793404],"about_ca_topic_score_codex":0.0012436977,"about_ca_topic_score_gemma":0.0006170639,"teacher_disagreement_score":0.14545351,"about_ca_system_score_codex":0.0005025077,"about_ca_system_score_gemma":0.0012384523,"threshold_uncertainty_score":0.25584644},"labels":[],"label_agreement":null},{"id":"W4411069075","doi":"10.1080/07294360.2025.2505136","title":"From emotion to action: investigating the role of affective rhetorical moves in peer feedback implementation in university classrooms","year":2025,"lang":"en","type":"article","venue":"Higher Education Research & Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Nanyang Technological University","keywords":"Peer feedback; Rhetorical question; Action (physics); Psychology; Higher education; Peer evaluation; Social psychology; Mathematics education; Political science; Linguistics","score_opus":0.06444782108709217,"score_gpt":0.4504747937903455,"score_spread":0.3860269727032533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411069075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9684019,0.0000484363,0.000020540347,0.0118826935,0.00042611297,0.0006407416,0.0000012611465,0.000010941476,0.018567333],"genre_scores_gemma":[0.99099547,0.000024701478,0.0009167848,0.00007151517,0.00010409607,0.000053907428,0.000020139581,0.0000035128994,0.0078098574],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99788177,0.0006520577,0.00020574837,0.0002267084,0.0007778362,0.00025585073],"domain_scores_gemma":[0.99905825,0.0003496574,0.000054042168,0.000101415055,0.00037012706,0.00006648516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001679818,0.00006795597,0.000096163596,0.00040006512,0.00032592204,0.00006296872,0.00025617608,0.00006122727,0.00040574814],"category_scores_gemma":[0.00012686332,0.0000650609,0.000016513432,0.0020516173,0.000098762386,0.00019389944,0.00011294791,0.00021353994,0.000022374772],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002676477,0.00022886554,0.8301717,0.000007666396,0.000020879035,2.337935e-7,0.08288778,0.000010169534,0.000824394,0.034954622,0.005833087,0.045033816],"study_design_scores_gemma":[0.00016803568,0.000008203303,0.7295299,0.000042519354,0.00000172067,5.4118203e-9,0.18367429,0.0000026680223,0.00053660263,0.0035677778,0.08242166,0.000046616547],"about_ca_topic_score_codex":0.017385384,"about_ca_topic_score_gemma":0.012135815,"teacher_disagreement_score":0.10078651,"about_ca_system_score_codex":0.0017574928,"about_ca_system_score_gemma":0.0019948182,"threshold_uncertainty_score":0.9891579},"labels":[],"label_agreement":null},{"id":"W4411166761","doi":"10.31542/869t8m43","title":"Greater Realism in Authentic Assessments Promotes Student Motivation and Engagement","year":2025,"lang":"en","type":"article","venue":"Pedagogical Inquiry and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Realism; Student engagement; Psychology; Mathematics education; Epistemology; Philosophy","score_opus":0.39954958497718773,"score_gpt":0.5491930691161431,"score_spread":0.14964348413895534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411166761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91993034,0.00025141207,0.00034110626,0.008745149,0.0003567564,0.00049886276,8.6462023e-7,0.000038550945,0.06983698],"genre_scores_gemma":[0.994076,0.0008712538,0.0004779479,0.0006770921,0.00012257352,0.000042418138,0.000004104052,0.0000039983984,0.0037246067],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99797213,0.00093859487,0.00022385233,0.00029905888,0.0003380898,0.00022829896],"domain_scores_gemma":[0.99826837,0.0014224212,0.00008589729,0.00009522831,0.00006124546,0.00006685676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025407316,0.00011164615,0.0001486199,0.00009489162,0.00038402813,0.00028195797,0.000115790564,0.00009294855,0.000116164556],"category_scores_gemma":[0.0009943775,0.00009571022,0.000018822333,0.00023850187,0.0002077564,0.00063517824,0.00016142381,0.00021908747,0.0000056509543],"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":[0.00025365895,0.00086801074,0.5525533,0.00007491839,0.00013299407,0.000045000146,0.24904014,0.0000017620104,0.00016960628,0.18024482,0.000728778,0.015887046],"study_design_scores_gemma":[0.000912006,0.00012819064,0.7862668,0.000073366435,0.00011441322,0.0000016679528,0.13982975,0.000027312311,0.00001222758,0.0043317927,0.068110675,0.00019180693],"about_ca_topic_score_codex":0.00035310793,"about_ca_topic_score_gemma":0.000078999714,"teacher_disagreement_score":0.23371352,"about_ca_system_score_codex":0.000060973216,"about_ca_system_score_gemma":0.000053494936,"threshold_uncertainty_score":0.39029494},"labels":[],"label_agreement":null},{"id":"W4411260555","doi":"10.1016/j.ijedudev.2025.103336","title":"Understanding the diverse ways teachers approach classroom assessment in an examination-oriented educational system","year":2025,"lang":"en","type":"article","venue":"International Journal of Educational Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Queen's University; York University","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Computer science; Sociology","score_opus":0.08503189697839836,"score_gpt":0.38751702237792957,"score_spread":0.3024851253995312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411260555","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6284162,0.00022057719,0.049680803,0.047849048,0.0145516815,0.0009114325,0.000010716906,0.000029670677,0.2583299],"genre_scores_gemma":[0.98729193,0.00002282932,0.009401959,0.00019331317,0.00063056627,0.000046624897,0.000056165783,0.000007363991,0.0023492305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99711466,0.0002976036,0.00069185474,0.00020567229,0.001467376,0.00022284861],"domain_scores_gemma":[0.997912,0.0006458335,0.00041211746,0.00010245496,0.0008284863,0.000099089455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023504246,0.00014105781,0.00016269034,0.00060591026,0.0004964263,0.00024690968,0.00089847454,0.0000741262,0.00027986715],"category_scores_gemma":[0.00022554945,0.0001178078,0.00007696159,0.0004741677,0.00015139556,0.00059404137,0.00008225683,0.00031043662,0.000009327126],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019845755,0.0006395436,0.27073425,0.0000071822697,0.00018779802,0.0000015148638,0.022553688,0.00023233,0.000017875986,0.7018226,0.0025056372,0.0012777747],"study_design_scores_gemma":[0.00069885893,0.000015109787,0.86150163,0.0001603209,0.000023560644,0.0000053818544,0.12358,0.0001755851,0.000005213917,0.0041712513,0.0095186075,0.00014448736],"about_ca_topic_score_codex":0.00008016699,"about_ca_topic_score_gemma":0.0003008722,"teacher_disagreement_score":0.6976513,"about_ca_system_score_codex":0.005716486,"about_ca_system_score_gemma":0.005072748,"threshold_uncertainty_score":0.9981004},"labels":[],"label_agreement":null},{"id":"W4411307838","doi":"10.1080/20004508.2025.2519831","title":"Do students perceive assessment differently? Exploring the diverse ways students conceive assessment and its impact on their assessment experiences and engagement","year":2025,"lang":"en","type":"article","venue":"Education Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Pedagogy; Mathematics education","score_opus":0.1503994172707718,"score_gpt":0.4960694933686223,"score_spread":0.3456700760978505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411307838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9828255,0.00031716694,0.00012246863,0.0013097792,0.004956578,0.0017411421,0.000008688942,0.0000727584,0.008645873],"genre_scores_gemma":[0.99424505,0.0018942944,0.00014728666,0.0005046385,0.0005571421,0.0016622293,0.000018429319,0.000018748964,0.00095219916],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99573463,0.0008588046,0.00046664246,0.00074782496,0.0016338853,0.00055821944],"domain_scores_gemma":[0.99815124,0.0007232173,0.0002501027,0.00040528094,0.00022618934,0.00024394778],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019748947,0.0004292689,0.0003977385,0.0002545525,0.002350388,0.0013664019,0.0009943254,0.00009501734,0.00041422286],"category_scores_gemma":[0.00006154302,0.00029513426,0.00011806211,0.00043529968,0.00047835323,0.0006952894,0.0006637718,0.0004872488,0.000009661934],"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":[0.000025007574,0.0010797293,0.69246274,0.000022328115,0.00029463833,0.000001392458,0.2715144,0.0000066387474,0.00007360846,0.024450418,0.0020976716,0.007971415],"study_design_scores_gemma":[0.00047070024,0.00012774566,0.5729339,0.000107690954,0.00005609902,2.0074751e-7,0.424657,0.00001903496,0.000013478501,0.0002885778,0.001142935,0.000182632],"about_ca_topic_score_codex":0.00023273044,"about_ca_topic_score_gemma":0.000042749565,"teacher_disagreement_score":0.1531426,"about_ca_system_score_codex":0.0011781576,"about_ca_system_score_gemma":0.0009819944,"threshold_uncertainty_score":0.99995005},"labels":[],"label_agreement":null},{"id":"W4411445047","doi":"10.7202/1118375ar","title":"Analysis of the Emotions and Emotional Skills of University Students in Processing Distance Formative Feedback","year":2023,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Affect (linguistics); Social psychology; Applied psychology; Mathematics education; Communication","score_opus":0.03795279578834834,"score_gpt":0.3911984893591588,"score_spread":0.3532456935708105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411445047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99570477,0.000008118801,0.0008870135,0.0014733613,0.000101128775,0.00021487627,0.000011846075,0.00001084532,0.0015880663],"genre_scores_gemma":[0.9989344,0.00006351367,0.00008397381,0.000009568614,0.000010439482,0.0000021253913,0.00003985737,0.0000020450195,0.00085408764],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99793607,0.0011439181,0.00017200147,0.000101343925,0.0005699492,0.00007672083],"domain_scores_gemma":[0.99924135,0.00027226956,0.00020243012,0.00007315025,0.00019639985,0.000014386711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004890209,0.000044884775,0.00011025089,0.00025320612,0.00016806056,0.000019592708,0.00014773848,0.00003760495,0.000036911446],"category_scores_gemma":[0.0003013646,0.000040527062,0.000045246856,0.0024003773,0.00009074288,0.00030110832,0.000037380712,0.000050072074,0.0000016720958],"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":[0.000003529758,0.00008419188,0.74893516,0.000009612438,0.000045336878,2.1220224e-8,0.24786127,0.0005995063,0.000031908705,0.0015305515,0.000057138546,0.0008417514],"study_design_scores_gemma":[0.00018894247,0.000004797726,0.9635262,0.000040500283,0.00010619569,1.18107115e-8,0.034329068,0.0013562737,0.000008348836,0.00033814769,0.000065129876,0.00003641454],"about_ca_topic_score_codex":0.00017695347,"about_ca_topic_score_gemma":0.0031336134,"teacher_disagreement_score":0.214591,"about_ca_system_score_codex":0.00014360125,"about_ca_system_score_gemma":0.0002459369,"threshold_uncertainty_score":0.17486298},"labels":[],"label_agreement":null},{"id":"W4411475719","doi":"10.25071/1916-4467.40814","title":"A Call for Change in Summative Assessment: Ideas Generated by Students During the COVID-19 Pandemic","year":2025,"lang":"en","type":"article","venue":"Journal of the Canadian Association for Curriculum Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Acadia University; St. Francis Xavier University","funders":"","keywords":"Summative assessment; Agency (philosophy); Coronavirus disease 2019 (COVID-19); Curriculum; Pandemic; Medical education; Psychology; Formative assessment; Mathematics education; Pedagogy; Sociology; Medicine; Social science; Internal medicine","score_opus":0.061140568603317354,"score_gpt":0.4328354853042999,"score_spread":0.37169491670098254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411475719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8820975,0.0031523346,0.000040881958,0.104195386,0.0039818226,0.00405288,0.00074935786,0.000026809641,0.001703054],"genre_scores_gemma":[0.98784846,0.0006090771,0.000041086776,0.002366838,0.00037061053,0.00032056036,0.000008850709,0.000008904796,0.008425604],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980631,0.00037982903,0.00043404324,0.000125771,0.00058731873,0.00040997894],"domain_scores_gemma":[0.9974858,0.00085632707,0.0007615548,0.00007605656,0.0006844988,0.00013577167],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0032567023,0.00012423085,0.00030381736,0.00017890733,0.001970909,0.00017562273,0.0005946608,0.0001038697,0.00001496859],"category_scores_gemma":[0.0035161213,0.00008051114,0.00020247241,0.000611522,0.00008000563,0.00018900032,0.000060716182,0.00022487705,6.3270573e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063819743,0.00003698479,0.8283575,0.000019036812,0.00040855113,5.4562304e-7,0.009521737,0.000010121946,0.0000050085837,0.0010001711,0.16060159,0.000032322652],"study_design_scores_gemma":[0.0032953836,0.000056545417,0.58828163,0.00014764808,0.0002699187,7.046876e-7,0.036689427,0.00007960327,0.0000031558675,0.0027878273,0.36814985,0.00023830139],"about_ca_topic_score_codex":0.033911593,"about_ca_topic_score_gemma":0.7851626,"teacher_disagreement_score":0.75125104,"about_ca_system_score_codex":0.010287306,"about_ca_system_score_gemma":0.0011249491,"threshold_uncertainty_score":0.9993284},"labels":[],"label_agreement":null},{"id":"W4411475738","doi":"10.25071/1916-4467.40823","title":"High-Stakes Tests and Applied Learners: The (Dis)connections Between Curriculum Expectations and Exam Notions of “Literacy”","year":2025,"lang":"en","type":"article","venue":"Journal of the Canadian Association for Curriculum Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Curriculum; Literacy; Test (biology); Mathematics education; Pedagogy; Psychology; Thematic analysis; Sociology; Qualitative research","score_opus":0.023528646522270817,"score_gpt":0.3394058327517759,"score_spread":0.31587718622950506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411475738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.945537,0.0017903295,0.00003763011,0.046510566,0.001345923,0.0006979953,0.00007167732,0.000013097097,0.0039957846],"genre_scores_gemma":[0.9977877,0.0001996578,0.00018472834,0.00010350776,0.00028308868,0.00002753526,0.0000019521417,0.0000048863103,0.0014069143],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988296,0.0001496694,0.00037881278,0.00010478449,0.00031155726,0.00022559066],"domain_scores_gemma":[0.99754894,0.00092687615,0.000620958,0.00008094343,0.0007368494,0.000085444924],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009561975,0.00010093081,0.00027215225,0.00019594748,0.0022429815,0.00014842236,0.00020981424,0.0000731582,0.0000048935676],"category_scores_gemma":[0.0018470042,0.00006536756,0.000119800876,0.00058279437,0.00021292207,0.00019880006,0.000041042196,0.0001778717,5.986248e-7],"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":[0.000001841673,0.000052770192,0.876029,0.000020510664,0.0008165997,1.6084739e-7,0.032074157,0.000022679167,0.000009718158,0.06498715,0.025314562,0.0006708218],"study_design_scores_gemma":[0.0007758771,0.00004996985,0.7147391,0.00011744603,0.0006548611,5.934579e-7,0.25501573,0.00001306516,0.000013108885,0.008242005,0.020225067,0.00015317435],"about_ca_topic_score_codex":0.009257666,"about_ca_topic_score_gemma":0.2014547,"teacher_disagreement_score":0.22294156,"about_ca_system_score_codex":0.000637337,"about_ca_system_score_gemma":0.00031856855,"threshold_uncertainty_score":0.999056},"labels":[],"label_agreement":null},{"id":"W4411565602","doi":"10.1007/s11409-025-09430-4","title":"How do students self-assess? examining the metacognitive processes of student self-assessment","year":2025,"lang":"en","type":"article","venue":"Metacognition and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Metacognition; Psychology; Self-assessment; Self-concept; Developmental psychology; Self-control; Self-regulated learning; Self evaluation; Academic achievement; Cognition; Social psychology; Applied psychology","score_opus":0.04062015942691434,"score_gpt":0.37832243636529805,"score_spread":0.3377022769383837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411565602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9518278,0.0011347779,0.0010980092,0.001002316,0.00031657127,0.0008548786,0.0000026219548,0.0002263156,0.043536678],"genre_scores_gemma":[0.99472946,0.0016175007,0.0013820743,0.00020522428,0.00012153299,0.00014814144,0.0000087803355,0.000015300478,0.001771989],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99651617,0.0012445046,0.00033956105,0.00041162103,0.0011123224,0.0003758045],"domain_scores_gemma":[0.9976776,0.0011606105,0.00032532783,0.0001301189,0.0006214143,0.00008490534],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0027983543,0.0002337345,0.00038367978,0.00022459833,0.0015213926,0.0009589721,0.00042758958,0.0001030024,0.00008371904],"category_scores_gemma":[0.0002692919,0.00017962209,0.00008475147,0.00095944945,0.00017279113,0.00049986446,0.00023468643,0.00048996205,0.000005265349],"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":[0.000024481995,0.0007192894,0.9231105,0.00020238127,0.0012860755,0.0000062386507,0.054495793,0.0000050040726,0.00029183345,0.0059038014,0.00010449457,0.013850127],"study_design_scores_gemma":[0.0014850275,0.00017769494,0.6928441,0.00022117648,0.0010973102,7.7295715e-7,0.28973106,0.000027718539,0.00022235379,0.0004303948,0.013460038,0.0003023275],"about_ca_topic_score_codex":0.00003789748,"about_ca_topic_score_gemma":0.000051100822,"teacher_disagreement_score":0.23523527,"about_ca_system_score_codex":0.000101093196,"about_ca_system_score_gemma":0.0003352469,"threshold_uncertainty_score":0.9997785},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79778945,0.00057103613,0.000015314086,0.007047066,0.0007123656,0.0006962886,0.000002003636,0.00001606967,0.1931504],"genre_scores_gemma":[0.9967351,0.00013591564,0.0001916124,0.000006614732,0.000034772074,0.000050936185,0.000011111792,0.000004499231,0.0028294502],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982409,0.00043433785,0.0003429535,0.00022701464,0.00056676887,0.00018803349],"domain_scores_gemma":[0.9987124,0.00036372413,0.00025903867,0.00022239778,0.00041998,0.000022462806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017370684,0.0000935868,0.00016374444,0.00064958,0.00018595006,0.0000528939,0.00036377882,0.0000991389,0.0002252865],"category_scores_gemma":[0.000117662385,0.00009138804,0.000049026385,0.0018698239,0.00030045825,0.00036620733,0.00005930271,0.00015088065,0.0000018842925],"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":[0.0000070386723,0.00044266504,0.5181791,0.0000052576506,0.000017753255,2.6659682e-8,0.0040310114,0.000009446898,0.00011155532,0.4704014,0.000048084992,0.006746643],"study_design_scores_gemma":[0.00030978987,0.000019934289,0.69859797,0.00005164179,0.000035421206,1.8504936e-8,0.22888938,0.00009931581,0.000028510418,0.06774849,0.0041573653,0.00006216076],"about_ca_topic_score_codex":0.00052096753,"about_ca_topic_score_gemma":0.00033725597,"teacher_disagreement_score":0.40265292,"about_ca_system_score_codex":0.0011892088,"about_ca_system_score_gemma":0.003611867,"threshold_uncertainty_score":0.6407297},"labels":[],"label_agreement":null},{"id":"W4412395771","doi":"10.1007/978-981-96-5658-5_6","title":"Formative Assessment in DGBL: A Qualitative Analysis of Players’ Perceptions of Game-Based Feedback in Complex Scenarios","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in educational technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Formative assessment; Qualitative analysis; Perception; Psychology; Game based learning; Computer science; Qualitative research; Mathematics education; Sociology; Neuroscience","score_opus":0.036582402176650375,"score_gpt":0.4207477439321418,"score_spread":0.38416534175549144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412395771","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.366093,0.0015283085,0.02711739,0.11026351,0.0012130848,0.006668892,0.0013775039,0.00016802471,0.48557028],"genre_scores_gemma":[0.99044776,0.00007928688,0.0069992486,0.00011972287,0.000027975228,0.000108820335,0.00039792072,0.000012379923,0.001806868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977326,0.00018952307,0.00087598833,0.00039905278,0.00050314394,0.00029968267],"domain_scores_gemma":[0.99672836,0.0020831795,0.00055823603,0.0002842158,0.00031605785,0.000029949535],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006564637,0.0002710917,0.00092986913,0.0052415472,0.000066968714,0.00001265338,0.0005442353,0.0007372964,0.0018479634],"category_scores_gemma":[0.00052666006,0.00029257193,0.00021840869,0.0023217488,0.0009154951,0.00007380415,0.00008704392,0.0008221002,0.0000048997335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057832294,0.0008039447,0.13011236,0.00010171385,0.00066711276,0.0000017623189,0.11322746,0.004044044,0.00013221326,0.74592143,0.00012465782,0.004805451],"study_design_scores_gemma":[0.0018937042,0.00028936446,0.3980276,0.0010790321,0.0006791633,3.4423886e-7,0.062350355,0.0026082844,0.00004061082,0.5300409,0.0020733047,0.0009173145],"about_ca_topic_score_codex":0.0016282401,"about_ca_topic_score_gemma":0.047451597,"teacher_disagreement_score":0.6243548,"about_ca_system_score_codex":0.0010692304,"about_ca_system_score_gemma":0.0018105503,"threshold_uncertainty_score":0.9999526},"labels":[],"label_agreement":null},{"id":"W4412676320","doi":"10.1177/02655322251359320","title":"Book review: Innovation in Learning-Oriented Language Assessment ChongS.ReindersH. (Eds.), Innovation in Learning-Oriented Language Assessment. Palgrave MacMillan, 2023. 333 pp. ISBN 978-3-031-18949-4 (hbk) US$169.99 ISBN 978-3-031-18952-4 (sbk) US$169.99 ISBN 978-3-031-18950-0 (ebk) US$129.99","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Psychology; Linguistics; Sociology; Philosophy","score_opus":0.01741045735498279,"score_gpt":0.3375408814479155,"score_spread":0.3201304240929327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412676320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75942755,0.09312202,0.0021636742,0.006341017,0.0031513004,0.008493182,0.00017245693,0.0028348654,0.12429394],"genre_scores_gemma":[0.9216686,0.013450223,0.009134124,0.011433268,0.002136762,0.0013032486,0.0050940053,0.0005349128,0.035244875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9835112,0.0026757766,0.004356312,0.0028642542,0.00338429,0.0032081516],"domain_scores_gemma":[0.99159396,0.0016749776,0.003065192,0.0015795608,0.0016819931,0.00040433253],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0079984935,0.001879939,0.002420376,0.0023528943,0.0016956516,0.000857047,0.0018746025,0.0011398356,0.0029819317],"category_scores_gemma":[0.00837872,0.0020229935,0.000453341,0.019530984,0.0006879977,0.0010191818,0.0012060003,0.004428082,0.00024966843],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026296757,0.0011216992,0.8396774,0.0020890946,0.00065975875,0.0016585835,0.030674106,0.0007213392,0.019346053,0.009898183,0.05337339,0.04051743],"study_design_scores_gemma":[0.019724227,0.001885326,0.44323745,0.017004244,0.0012561472,0.00009305384,0.18195847,0.017454697,0.0020459483,0.0006542268,0.3059624,0.008723797],"about_ca_topic_score_codex":0.018995095,"about_ca_topic_score_gemma":0.0045508286,"teacher_disagreement_score":0.39643994,"about_ca_system_score_codex":0.0025953478,"about_ca_system_score_gemma":0.0019041235,"threshold_uncertainty_score":0.99997413},"labels":[],"label_agreement":null},{"id":"W4413200584","doi":"10.3102/ip.25.2185450","title":"Student-Generated Questions and Goal Orientation in Literacy Assessment","year":2025,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Goal orientation; Orientation (vector space); Computer science; Literacy; Psychology; Human–computer interaction; Pedagogy; Social psychology","score_opus":0.01566195994059493,"score_gpt":0.4307261578120048,"score_spread":0.41506419787140986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413200584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83014506,0.00007197107,0.00071931275,0.0019202369,0.00036989228,0.0002579794,8.6205847e-7,0.00004926354,0.16646543],"genre_scores_gemma":[0.97982514,0.00014599126,0.0014673239,0.00022815989,0.000045580207,0.00003245519,0.0000082962715,0.0000022220977,0.018244805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99920166,0.00013194254,0.00015267408,0.00016073036,0.0002035645,0.00014944072],"domain_scores_gemma":[0.9997241,0.00008062201,0.000024870875,0.00006128656,0.000072546325,0.000036565805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000389185,0.000059274087,0.00008174404,0.00012728857,0.00023754395,0.00022674118,0.00009131522,0.000041632415,0.00018206029],"category_scores_gemma":[0.00002659979,0.000056693792,0.000014542537,0.00049638556,0.00005995589,0.00028240174,0.000043100325,0.000070820344,0.0000067390783],"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":[0.0000027741655,0.00010493299,0.7623551,0.000002327959,0.0000103250195,0.0000013825256,0.005499234,0.000003856599,0.00022494273,0.22710593,0.0006013094,0.0040879184],"study_design_scores_gemma":[0.0004898878,0.000015168377,0.9787757,0.000018876617,0.000010463181,3.952843e-8,0.010740719,0.00019159896,0.000013558761,0.0010802016,0.008589364,0.00007444371],"about_ca_topic_score_codex":0.0015335627,"about_ca_topic_score_gemma":0.003532661,"teacher_disagreement_score":0.22602573,"about_ca_system_score_codex":0.00012980447,"about_ca_system_score_gemma":0.00013903085,"threshold_uncertainty_score":0.23182982},"labels":[],"label_agreement":null},{"id":"W4413228388","doi":"10.5430/wjel.v15n8p162","title":"Functions and Focus of Supervisory Feedback on Undergraduate Students’ Theses Writing","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Supervisor; Directive; Focus (optics); Computer science; Process (computing); Peer feedback; Academic writing; Writing process; Focus group; Mathematics education; Psychology; Pedagogy; Management; Sociology","score_opus":0.02137497802591898,"score_gpt":0.3232372813041563,"score_spread":0.3018623032782373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413228388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7674227,0.001655082,0.000017383652,0.00094143715,0.00075265823,0.00009448907,0.000003117151,0.000016975044,0.2290962],"genre_scores_gemma":[0.99015373,0.00032213048,0.00009939516,0.00010211457,0.0005284837,0.0000014702376,5.7583975e-7,0.0000069155976,0.008785161],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99871457,0.00015571354,0.00034514035,0.000102810285,0.0004956497,0.00018609993],"domain_scores_gemma":[0.998865,0.0004677305,0.00019610404,0.000099931414,0.00030213333,0.00006909751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087173213,0.00009500258,0.00023194273,0.00032158638,0.00020979109,0.00011738891,0.0002945554,0.00003708023,0.0001133649],"category_scores_gemma":[0.00060506,0.000081378115,0.000108232976,0.00046744992,0.00013678426,0.000201293,0.00006778317,0.00022925503,0.0000023397934],"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":[0.00025078832,0.0008207852,0.71558344,0.000084555926,0.0006706281,0.00006451373,0.14749762,0.00002641727,0.00082278025,0.08142157,0.013587028,0.039169874],"study_design_scores_gemma":[0.0031687082,0.00030336072,0.22440697,0.0011013644,0.00032110052,0.0000014560113,0.70658535,0.000003946505,0.0006616931,0.0022512989,0.06084039,0.00035435456],"about_ca_topic_score_codex":0.00016042596,"about_ca_topic_score_gemma":0.0012388623,"teacher_disagreement_score":0.55908775,"about_ca_system_score_codex":0.000057658646,"about_ca_system_score_gemma":0.000081117985,"threshold_uncertainty_score":0.33185032},"labels":[],"label_agreement":null},{"id":"W4413563369","doi":"10.64628/aam.53avwyrpv","title":"STEM learning should engage students’ minds, hands and hearts","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Psychology; Mathematics education","score_opus":0.14451897737884709,"score_gpt":0.40942119993424797,"score_spread":0.26490222255540086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413563369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75652885,0.0006127975,0.00020528153,0.005602079,0.0010649405,0.0010025207,0.000003896796,0.0004283821,0.23455127],"genre_scores_gemma":[0.9583302,0.0006805331,0.00030304413,0.00031730888,0.0006747982,0.00003501805,0.000014615421,0.000024464867,0.039620005],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99721116,0.00044841255,0.00026553162,0.0005937798,0.0011027661,0.00037833568],"domain_scores_gemma":[0.99917763,0.00020942796,0.0001303034,0.00016894624,0.0000635255,0.0002501881],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011800264,0.0002548061,0.00039751295,0.000075225325,0.0007419259,0.00087832595,0.00056529837,0.00034329135,0.0006758572],"category_scores_gemma":[0.000060041904,0.00024527998,0.000117632255,0.00014115302,0.00016717013,0.00011086422,0.0014865159,0.0012068832,0.000078259865],"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":[0.000029338014,0.00011324373,0.8722524,0.0001026367,0.0002444548,0.000037728765,0.0974535,0.00001213958,0.000045974797,0.005088085,0.014931501,0.009688973],"study_design_scores_gemma":[0.0026837627,0.00040154043,0.26889157,0.00037843015,0.00037250284,0.0000015104649,0.22740261,0.00041470208,0.00011137515,0.0015326397,0.49571294,0.0020964018],"about_ca_topic_score_codex":0.0006946815,"about_ca_topic_score_gemma":0.00054278446,"teacher_disagreement_score":0.60336083,"about_ca_system_score_codex":0.00008000331,"about_ca_system_score_gemma":0.00015576159,"threshold_uncertainty_score":0.99999994},"labels":[],"label_agreement":null},{"id":"W4413589329","doi":"10.64628/aam.vjwdv7phn","title":"Why Ontario’s ‘Right to Read Inquiry’ needs to broaden its recommendations","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University of Windsor","funders":"","keywords":"Political science; Psychology; Sociology","score_opus":0.09904579181292285,"score_gpt":0.40561022692810267,"score_spread":0.30656443511517983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413589329","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02769683,0.000032556432,0.000690313,0.18036485,0.008333951,0.0020627913,0.00004073377,0.00032173755,0.78045624],"genre_scores_gemma":[0.041142393,0.00012747558,0.008107793,0.024872279,0.0021254732,0.0011801652,0.00037673465,0.000065423825,0.92200226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997132,0.00026680296,0.00042599475,0.00062203925,0.0009803679,0.0005728098],"domain_scores_gemma":[0.99858946,0.00014328928,0.00013105004,0.00052718126,0.00017703832,0.00043199546],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009013509,0.00029585624,0.00037897847,0.00052420923,0.0009803567,0.0005045731,0.0014957646,0.00023754865,0.1475382],"category_scores_gemma":[0.00011091236,0.0003092786,0.00018210338,0.00090015196,0.00006827034,0.00018390939,0.0026306522,0.00071579154,0.0009570185],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014504446,0.000101818354,0.004383473,0.0000062856448,0.00007633461,0.000003330045,0.17543496,0.000057386544,0.000007965384,0.018822249,0.7997383,0.0013534192],"study_design_scores_gemma":[0.000115120034,0.000054549557,0.0037393009,0.00003160894,0.000039742135,1.5040689e-7,0.043813765,0.0000014927039,0.000008918286,0.00065701647,0.95111346,0.00042489826],"about_ca_topic_score_codex":0.26068434,"about_ca_topic_score_gemma":0.6573059,"teacher_disagreement_score":0.39662158,"about_ca_system_score_codex":0.0017303057,"about_ca_system_score_gemma":0.000847098,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W4413846339","doi":"10.1080/09575146.2025.2552415","title":"Challenges, struggles and needs in assessment: voices of early childhood teachers","year":2025,"lang":"en","type":"article","venue":"Early Years Journal of International Research and Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Early childhood; Psychology; Pedagogy; Sociology; Political science; Developmental psychology","score_opus":0.06789655495680331,"score_gpt":0.4245258210491768,"score_spread":0.3566292660923735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413846339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9673073,0.0017854422,0.000017119484,0.0013033587,0.00016010937,0.00009929525,9.325498e-7,0.0000025863649,0.029323857],"genre_scores_gemma":[0.99262387,0.004653693,0.0015838441,0.000012205817,0.0000667776,0.0000034191175,6.31032e-7,0.0000035205842,0.0010520271],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981485,0.00014365178,0.0003439003,0.000104030296,0.001054324,0.00020560538],"domain_scores_gemma":[0.99912065,0.00027043594,0.0001212091,0.000042575648,0.00035276177,0.000092344504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026514113,0.00006377509,0.00015256777,0.0008482067,0.00010175255,0.00013721932,0.0003125724,0.00005607158,0.000041337393],"category_scores_gemma":[0.0001824664,0.000059076578,0.000022554963,0.00026404214,0.00020409212,0.00030282713,0.00013335605,0.00032366088,0.000001521281],"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":[0.00006623126,0.00021831278,0.7561084,0.000010366465,0.0001930968,0.000013726206,0.09450251,6.924474e-7,0.00007801251,0.023189632,0.00024626637,0.12537277],"study_design_scores_gemma":[0.0006390671,0.00011629701,0.9671271,0.00017541724,0.00000205286,8.0471494e-7,0.019885179,5.9409194e-7,0.00003354376,0.0016902977,0.010280971,0.000048720987],"about_ca_topic_score_codex":0.00029257988,"about_ca_topic_score_gemma":0.000307329,"teacher_disagreement_score":0.21101867,"about_ca_system_score_codex":0.00014634167,"about_ca_system_score_gemma":0.00075809733,"threshold_uncertainty_score":0.2409073},"labels":[],"label_agreement":null},{"id":"W4413927455","doi":"10.7870/cjcmh-2025-006","title":"Asynchronous Innovation to Support Well-being Through Mindfulness and Feedback Literacy in Higher Education","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Community Mental Health","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Mindfulness; Asynchronous communication; Literacy; Psychology; Computer science; Psychotherapist; Pedagogy","score_opus":0.042513688755462554,"score_gpt":0.40101260230982544,"score_spread":0.35849891355436286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413927455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9163231,0.00023253252,0.00003428455,0.038613968,0.0013016851,0.00026502967,0.0000032211824,0.0000034987056,0.04322265],"genre_scores_gemma":[0.991029,0.00001756547,0.00027127372,0.0070724874,0.00010477587,0.0000043963337,0.000014756534,0.00000518174,0.0014805562],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858403,0.0004903503,0.00041916195,0.000054508364,0.00016368323,0.00028824355],"domain_scores_gemma":[0.9992159,0.00007920234,0.00017360669,0.00010523753,0.00017014811,0.00025590762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014744169,0.00008175206,0.0001862329,0.00051752425,0.0009961907,0.00013531928,0.00029164387,0.00005235716,0.00026884847],"category_scores_gemma":[0.000037814298,0.00009118251,0.000021471544,0.0010011425,0.00007816549,0.00045477183,0.00002982251,0.00040081155,0.000005603991],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060227474,0.00031043027,0.15090922,0.00013247672,0.000037637652,0.000005434218,0.34084648,0.0000033722076,0.000009162693,0.2248114,0.038534507,0.24433966],"study_design_scores_gemma":[0.0011000695,0.00043814012,0.4314356,0.00082271744,0.000011467077,0.000008451842,0.10508238,0.0000014341796,0.00009160314,0.025699299,0.4350743,0.00023451485],"about_ca_topic_score_codex":0.107232645,"about_ca_topic_score_gemma":0.21112573,"teacher_disagreement_score":0.3965398,"about_ca_system_score_codex":0.0013923695,"about_ca_system_score_gemma":0.005531765,"threshold_uncertainty_score":0.9813114},"labels":[],"label_agreement":null},{"id":"W4413982879","doi":"10.3390/higheredu4030048","title":"Learning with Peers in Higher Education: Exploring Strengths and Weaknesses of Formative Assessment","year":2025,"lang":"en","type":"article","venue":"Trends in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"Università degli Studi di Genova","keywords":"Formative assessment; Strengths and weaknesses; Peer assessment; Psychology; Assessment for learning; Mathematics education; Higher education; Pedagogy; Peer evaluation; Political science; Social psychology","score_opus":0.05943047214718355,"score_gpt":0.4132873053782435,"score_spread":0.35385683323105993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413982879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74157304,0.00027142497,0.0000021874052,0.004870499,0.0012809618,0.00011927365,4.728151e-7,0.000022153612,0.25186],"genre_scores_gemma":[0.95284474,0.00014895554,0.0006052769,0.00004729054,0.00012698799,0.00018241313,0.000017388093,0.0000063964103,0.04602055],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990093,0.0001309806,0.00023760699,0.00019304697,0.00024788248,0.00018118403],"domain_scores_gemma":[0.9994767,0.00017837224,0.00012299941,0.00009835065,0.000086486885,0.000037118567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002713768,0.00010978243,0.00016506553,0.000500805,0.00012326987,0.000060658644,0.00012389338,0.00005411515,0.0007453738],"category_scores_gemma":[0.000014240284,0.000104938765,0.000018727684,0.0011692314,0.00009978044,0.0005580712,0.000030064564,0.00016744342,0.000001273684],"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":[0.00001986191,0.000458045,0.80237824,0.0000427842,0.00002041482,1.7248132e-7,0.027911862,0.000036047924,0.000020765376,0.09742789,0.00070267817,0.070981234],"study_design_scores_gemma":[0.00032167495,0.00004107875,0.91773283,0.00019923944,0.000018018622,5.7817083e-8,0.0510385,0.0000036081824,0.00001649366,0.0005787076,0.029939035,0.00011074884],"about_ca_topic_score_codex":0.0010919551,"about_ca_topic_score_gemma":0.00066150783,"teacher_disagreement_score":0.21127172,"about_ca_system_score_codex":0.00028420662,"about_ca_system_score_gemma":0.00056134403,"threshold_uncertainty_score":0.816132},"labels":[],"label_agreement":null},{"id":"W4414298304","doi":"10.1002/tesq.70032","title":"Automated Diagnostic Feedback vs. Self‐Assessment: Rethinking Feedback Mechanisms on Academic Writing Development","year":2025,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto; Educational Testing Service","keywords":"Academic writing; Peer feedback; Vocabulary; Task (project management); Graduate students; Second language writing; Higher education; Corrective feedback","score_opus":0.018631390327964244,"score_gpt":0.3371814660702979,"score_spread":0.3185500757423337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414298304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80913067,0.000266818,0.0040980508,0.0091626905,0.0032804268,0.0027908133,0.000012841728,0.0070548956,0.16420281],"genre_scores_gemma":[0.9862862,0.0000662896,0.0094561335,0.001553128,0.00028992762,0.0001741876,0.000030514131,0.000045309116,0.0020982774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9954358,0.00043906795,0.00086887646,0.0007666904,0.0012465256,0.0012430486],"domain_scores_gemma":[0.99710166,0.0017767947,0.0003095967,0.00038573283,0.00019875994,0.00022744233],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0020048106,0.00045045555,0.000505634,0.00036388912,0.0019107081,0.00045913088,0.0009924336,0.00046130823,0.0003120214],"category_scores_gemma":[0.00019134492,0.00047129425,0.00014430773,0.0010472923,0.00015440822,0.00045548065,0.000110626635,0.0008866962,0.0004738582],"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":[0.00013921164,0.0012071681,0.06644334,0.00032450628,0.00081382686,0.00012094173,0.22779383,0.000045264067,0.0020031023,0.5872651,0.031210857,0.08263291],"study_design_scores_gemma":[0.00988844,0.0023688388,0.69225454,0.0053113033,0.00071636616,0.000008212278,0.12629303,0.00813132,0.0015462537,0.10116389,0.047518373,0.0047994214],"about_ca_topic_score_codex":0.00018518559,"about_ca_topic_score_gemma":0.00021480497,"teacher_disagreement_score":0.6258112,"about_ca_system_score_codex":0.00092968537,"about_ca_system_score_gemma":0.000911129,"threshold_uncertainty_score":0.99977386},"labels":[],"label_agreement":null},{"id":"W4414502288","doi":"10.37213/cjal.2025.34455","title":"Written corrective feedback at university","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agència de Gestió d'Ajuts Universitaris i de Recerca; Generalitat de Catalunya","keywords":"Corrective feedback; Spelling; Peer feedback; Metalinguistics; Higher education; Written language; Primary education; Error detection and correction","score_opus":0.012468651667480731,"score_gpt":0.26810295954232505,"score_spread":0.2556343078748443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414502288","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027815053,0.00007319628,0.00008528872,0.00037529742,0.002681367,0.00010273354,0.000009792323,0.000008597331,0.96884865],"genre_scores_gemma":[0.9880011,0.00003883293,0.00052198773,0.00022047859,0.0007413068,1.3934225e-7,0.0000015809699,0.0000052630176,0.010469298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992408,0.0000316668,0.0001683433,0.00009323474,0.00018757752,0.0002783909],"domain_scores_gemma":[0.99879044,0.00014162475,0.00014141544,0.00007527149,0.00046709407,0.0003841274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036059084,0.000078709774,0.0001646533,0.00025497674,0.00066652335,0.000057612655,0.00036116966,0.00009274388,0.00022052026],"category_scores_gemma":[0.0005486503,0.00008916868,0.000063559644,0.0004030841,0.00025943425,0.00001448026,0.000023213668,0.0001971597,0.000029476505],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011235294,0.00003036467,0.048140135,0.000011266967,0.00017607586,0.00020014528,0.020793084,0.00005039367,0.00002297477,0.79196846,0.13647021,0.0020245153],"study_design_scores_gemma":[0.00036266836,0.000017894954,0.009125302,0.000026187425,0.00007092178,5.171062e-7,0.014876581,0.000005166585,0.000024002738,0.0023088353,0.9730822,0.0000997552],"about_ca_topic_score_codex":0.0055071726,"about_ca_topic_score_gemma":0.10467719,"teacher_disagreement_score":0.96018606,"about_ca_system_score_codex":0.0009968351,"about_ca_system_score_gemma":0.002691656,"threshold_uncertainty_score":0.91166013},"labels":[],"label_agreement":null},{"id":"W4414502711","doi":"10.37213/cjal.2025.34396","title":"A comparison of EFL students and instructors’ written feedback preferences and reported practices at a Moroccan university","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Textuality; Perception; Applied linguistics; Study abroad; Higher education; Written language","score_opus":0.05836475130016532,"score_gpt":0.37724672825808925,"score_spread":0.3188819769579239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414502711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9252443,0.00021504663,0.0000044071685,0.00010963127,0.000401022,0.00012380217,0.000007629529,0.000003862369,0.07389035],"genre_scores_gemma":[0.9985377,0.00015219017,0.0007018775,0.000026889697,0.00014380288,1.9897848e-7,0.0000015486481,0.0000037301063,0.00043207154],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990095,0.000048817048,0.0003373618,0.00012783344,0.00028950616,0.00018701733],"domain_scores_gemma":[0.99820364,0.00018459206,0.0008727194,0.00008078399,0.00034067882,0.00031760725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000482088,0.00009157091,0.00028911603,0.00021796324,0.00039237054,0.00009632414,0.0002817208,0.000088962675,0.000026497251],"category_scores_gemma":[0.0009656231,0.000094571726,0.000026465294,0.00025162566,0.00040876254,0.00003438902,0.000056997487,0.0001743392,3.9068274e-7],"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":[0.000069301874,0.000024222218,0.97134006,0.000028225877,0.0001461391,0.00002407676,0.011068023,0.0000029379214,0.000030049448,0.015419786,0.0009429543,0.00090423384],"study_design_scores_gemma":[0.0012704941,0.0001242692,0.71307874,0.00016284642,0.00048351084,0.000003450481,0.083225444,0.000022811111,0.00008056995,0.0022409514,0.19908059,0.0002263158],"about_ca_topic_score_codex":0.009283022,"about_ca_topic_score_gemma":0.100494586,"teacher_disagreement_score":0.2582613,"about_ca_system_score_codex":0.00017568837,"about_ca_system_score_gemma":0.0011479943,"threshold_uncertainty_score":0.9973143},"labels":[],"label_agreement":null},{"id":"W4414503355","doi":"10.37213/cjal.2025.34475","title":"Collaboration in the revision of a piece of writing","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Process (computing); Natural (archaeology); Corrective feedback; Natural language; Phase (matter); Composition (language); Test (biology); Language acquisition","score_opus":0.016253375693617608,"score_gpt":0.34328282681194133,"score_spread":0.3270294511183237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414503355","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29626814,0.0006665024,0.000247804,0.0015094635,0.0012236856,0.000377037,0.000012108155,0.0000026054106,0.69969267],"genre_scores_gemma":[0.9984868,0.0000504316,0.0010529307,0.00009711163,0.00027292862,2.9676565e-7,6.80282e-7,0.0000019971487,0.00003678209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992375,0.000044191594,0.00036663012,0.00003938857,0.00020288643,0.00010945085],"domain_scores_gemma":[0.99895024,0.00021252326,0.00026135723,0.00006186537,0.00046069943,0.000053290994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012643063,0.000038081515,0.00013710698,0.00018049432,0.00010664763,0.00003743511,0.00024661838,0.000044520213,0.000015892765],"category_scores_gemma":[0.0015001474,0.000032306794,0.000027203885,0.000602298,0.0001114655,0.000011213703,0.000005090858,0.000112430644,3.497806e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021365933,0.000022985678,0.026244948,0.000044205815,0.00001931979,0.000010943957,0.03127412,0.000093475515,0.00008538575,0.93416756,0.004704576,0.0033110995],"study_design_scores_gemma":[0.0010721469,0.00010691337,0.01763069,0.0007486601,0.00013369515,5.489833e-7,0.20497252,0.00007246515,0.00038597945,0.02076016,0.7539434,0.00017280552],"about_ca_topic_score_codex":0.0023521746,"about_ca_topic_score_gemma":0.030381493,"teacher_disagreement_score":0.91340744,"about_ca_system_score_codex":0.00008417454,"about_ca_system_score_gemma":0.0016891102,"threshold_uncertainty_score":0.98731154},"labels":[],"label_agreement":null},{"id":"W4415150289","doi":"10.1002/berj.70056","title":"Self‐ and peer‐assessment in upper secondary schools. A quasi‐experimental study to investigate the educational effectiveness of formative assessment","year":2025,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Summative assessment; Metacognition; Knowledge survey; Test (biology); Educational research","score_opus":0.04421725327059,"score_gpt":0.4866450570754541,"score_spread":0.4424278038048641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415150289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9419923,0.00046387993,0.000019776062,0.028628495,0.0005258458,0.0015275799,0.0000118911485,0.0000051068755,0.026825115],"genre_scores_gemma":[0.99594885,0.00014085676,0.0015349593,0.00012900068,0.00026136916,0.00045088603,0.000009703182,0.000009074823,0.0015152975],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938564,0.0028154573,0.00046782568,0.00029530312,0.00208559,0.0004794596],"domain_scores_gemma":[0.99570423,0.0026234735,0.00010728703,0.00013868438,0.0011523193,0.00027399356],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.011907568,0.00012534547,0.0002370371,0.00049697526,0.0014837921,0.0008488076,0.00059493264,0.000049151986,0.000577016],"category_scores_gemma":[0.0012099646,0.00012234571,0.00006283301,0.0011084094,0.0003647277,0.0006033751,0.00027295243,0.0012071948,0.000007932881],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006102112,0.007700629,0.85707885,0.000061175466,0.00017517418,0.000004434001,0.026840713,0.000005982366,0.00015261433,0.09554146,0.0113574,0.0010205203],"study_design_scores_gemma":[0.00087547244,0.00034404668,0.8710309,0.0002928899,0.000009638115,0.000012678576,0.10975586,0.000014112491,0.00002493184,0.015991164,0.0015458076,0.00010245538],"about_ca_topic_score_codex":0.003186423,"about_ca_topic_score_gemma":0.0015616822,"teacher_disagreement_score":0.08291515,"about_ca_system_score_codex":0.0014599932,"about_ca_system_score_gemma":0.011371883,"threshold_uncertainty_score":0.9998161},"labels":[],"label_agreement":null},{"id":"W4415225444","doi":"10.15173/ijsap.v9i2.5886","title":"Assessment Met-befores","year":2025,"lang":"en","type":"article","venue":"International Journal for Students as Partners","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Formative assessment; Thematic analysis; Educational assessment; Self-assessment; Perception; Peer assessment; Assessment for learning; Alternative assessment","score_opus":0.04477588560886075,"score_gpt":0.6110586355681135,"score_spread":0.5662827499592528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415225444","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42351496,0.00015693209,0.004385466,0.012985858,0.020797553,0.0008040933,0.00001442784,0.000101499245,0.5372392],"genre_scores_gemma":[0.9439197,0.000256395,0.0011525478,0.0011276352,0.0008538894,0.00005440851,0.000009627483,0.000009659219,0.052616145],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750537,0.00008904235,0.00034180103,0.00018991533,0.0015571843,0.00031666775],"domain_scores_gemma":[0.99888533,0.00018505687,0.00016704823,0.00008606782,0.00055521034,0.00012125416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011967748,0.00012464986,0.00015899683,0.0002529167,0.00071332016,0.00091137993,0.0013655049,0.00006591506,0.00040827697],"category_scores_gemma":[0.00021204512,0.000112618,0.00020990541,0.00016251171,0.000111137255,0.00031608398,0.00015455682,0.00017974329,0.000039152146],"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":[0.000091197166,0.00032225664,0.502537,0.0000030270658,0.0010991483,0.000023654784,0.002682324,0.000026165999,0.00006704785,0.43922433,0.04422063,0.009703216],"study_design_scores_gemma":[0.001977978,0.00009633056,0.13826367,0.00006659746,0.00007535874,0.0000035308178,0.01127423,0.000017948998,0.00003565022,0.018420285,0.8295906,0.0001777966],"about_ca_topic_score_codex":0.00015813489,"about_ca_topic_score_gemma":0.000179267,"teacher_disagreement_score":0.78537,"about_ca_system_score_codex":0.0005041544,"about_ca_system_score_gemma":0.00042272254,"threshold_uncertainty_score":0.87884575},"labels":[],"label_agreement":null},{"id":"W4415642192","doi":"10.65214/2164-7992.1633","title":"A Situated Lens to Designing Assessments of Citizenship Competency","year":2024,"lang":"en","type":"article","venue":"Democracy & Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver Island University","funders":"","keywords":"Operationalization; Situated; Citizenship; Democracy; Active listening; Situated learning; Value (mathematics); Capability approach; Citizenship education","score_opus":0.049335920173832315,"score_gpt":0.4051396013983132,"score_spread":0.35580368122448086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415642192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62299985,0.0003245492,0.0028220878,0.007939412,0.002139593,0.00065670145,0.000004344594,0.00020307234,0.36291042],"genre_scores_gemma":[0.9865279,0.000071415685,0.0056061717,0.00017475385,0.0003577421,0.000027036627,0.000020443218,0.000013491963,0.0072010057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99876255,0.00015859357,0.0002292077,0.00022248393,0.00039572388,0.00023144108],"domain_scores_gemma":[0.99934334,0.00021536286,0.000059398088,0.00012554301,0.00016590559,0.00009044272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006034077,0.00009308804,0.00012629863,0.00019100077,0.00029516098,0.00014890452,0.00020316544,0.0000546309,0.00032073064],"category_scores_gemma":[0.000101127305,0.00009711684,0.000058026046,0.0007463412,0.000049359594,0.00027344562,0.00002213565,0.000096118776,0.00020333743],"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":[0.000045213244,0.0006814234,0.18678202,0.0002107368,0.00027184433,0.000007671563,0.12582219,0.00001786104,0.030425556,0.36988062,0.18762624,0.098228626],"study_design_scores_gemma":[0.0007668655,0.00050127634,0.6147915,0.0017188237,0.00048980664,0.000005039748,0.14344884,0.0008318538,0.004562332,0.11378919,0.11762213,0.0014722993],"about_ca_topic_score_codex":0.00054565724,"about_ca_topic_score_gemma":0.00009783623,"teacher_disagreement_score":0.4280095,"about_ca_system_score_codex":0.00015307518,"about_ca_system_score_gemma":0.0012404497,"threshold_uncertainty_score":0.39603096},"labels":[],"label_agreement":null},{"id":"W4415830486","doi":"10.1016/j.bushor.2025.10.007","title":"Lost in the stars: Making sense of information compression in ratings","year":2025,"lang":"en","type":"article","venue":"Business Horizons","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Leverage (statistics); Quality (philosophy); Phenomenon; Information system; Boundary (topology); Convergence (economics)","score_opus":0.01987467738093282,"score_gpt":0.3395603708934862,"score_spread":0.3196856935125534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415830486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9020037,0.0000374861,0.00044808254,0.0026456323,0.00025579814,0.00033082013,0.0000026489313,0.000012657888,0.09426319],"genre_scores_gemma":[0.9995261,0.00004390412,0.00017659391,0.00012624438,0.000029439816,0.000008703501,0.000005172472,0.000001439939,0.00008243039],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99921906,0.00011755031,0.0002199766,0.000059903494,0.00024847544,0.00013505614],"domain_scores_gemma":[0.9995563,0.00016727153,0.000086209846,0.00008916319,0.00009443804,0.0000066387943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006007069,0.000053140517,0.00009998465,0.00018458358,0.0001103487,0.0000670383,0.00016785214,0.00004834349,0.000025514255],"category_scores_gemma":[0.00019196441,0.000040955427,0.000016962596,0.0013834037,0.00007649197,0.00046265015,0.00004817907,0.00008250497,0.0000068648724],"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":[0.0001343814,0.00036664808,0.64223593,0.00019255672,0.000017003451,0.000011826423,0.13730207,0.00034278043,0.0014317483,0.19043852,0.0059478306,0.021578664],"study_design_scores_gemma":[0.0004746374,0.000009392272,0.94349223,0.00030800948,0.0000066481966,1.3039136e-7,0.036535934,0.00016320258,0.000029150777,0.0006126599,0.018292053,0.0000759732],"about_ca_topic_score_codex":0.0017054611,"about_ca_topic_score_gemma":0.0027326688,"teacher_disagreement_score":0.30125624,"about_ca_system_score_codex":0.00004590728,"about_ca_system_score_gemma":0.00011984157,"threshold_uncertainty_score":0.25781584},"labels":[],"label_agreement":null},{"id":"W4415962483","doi":"10.1128/jmbe.00205-25","title":"Question format is the best predictor of item discrimination: a multivariable analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Microbiology and Biology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Recall; Logistic regression; Item bank; Odds; Multivariable calculus; Correlation; Exploratory analysis; Relation (database); Odds ratio","score_opus":0.019586373810779545,"score_gpt":0.37255539891190975,"score_spread":0.3529690251011302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415962483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98531055,0.0019420503,0.0007669402,0.008670677,0.0009889379,0.00012112435,0.000007985774,0.0000029063883,0.002188827],"genre_scores_gemma":[0.99741006,0.00076635263,0.00037055358,0.00027370543,0.00013231218,0.000002989182,0.000015393267,8.9761284e-7,0.0010277502],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99927515,0.00026544844,0.00027760502,0.00006950907,0.000024044979,0.00008822368],"domain_scores_gemma":[0.99905866,0.000262058,0.0003326745,0.000056469,0.00027234657,0.000017795055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084513635,0.00005076264,0.00016296067,0.00019706748,0.00020371884,0.000012228809,0.0001452554,0.00013096897,0.000048712547],"category_scores_gemma":[0.0001602912,0.000031333395,0.00007323235,0.0003246591,0.00030452057,0.00009665981,0.000022214497,0.0000972434,9.0673e-7],"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":[0.00006913746,0.0002780919,0.9216166,0.000017534527,0.0006615641,6.209894e-8,0.0108855525,0.0000011651409,0.026244257,0.02825923,0.0059019164,0.006064884],"study_design_scores_gemma":[0.0013821253,0.0006254325,0.70760363,0.00025308583,0.003679722,0.000020549574,0.102691785,0.00006493853,0.0049296003,0.013509483,0.16496533,0.00027433713],"about_ca_topic_score_codex":0.00016625629,"about_ca_topic_score_gemma":0.00013678176,"teacher_disagreement_score":0.21401298,"about_ca_system_score_codex":0.00003976498,"about_ca_system_score_gemma":0.0002811867,"threshold_uncertainty_score":0.15668611},"labels":[],"label_agreement":null},{"id":"W4416175796","doi":"10.1016/j.ijme.2025.101307","title":"Innovative assessment and grading practices in higher education: a critical exploration for management educators","year":2025,"lang":"en","type":"article","venue":"The International Journal of Management Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Grading (engineering); Higher education; Mainstream; Relevance (law); Continuous assessment; Management development; Best practice","score_opus":0.09367867799178597,"score_gpt":0.5023638013586159,"score_spread":0.40868512336682994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416175796","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15137611,0.0010051911,0.0043415916,0.45964363,0.026148666,0.0020589228,0.0000021436801,0.000026400508,0.3553973],"genre_scores_gemma":[0.97865385,0.00079705176,0.007311712,0.0017849245,0.0008180121,0.00020928145,0.000007677157,0.0000063322877,0.010411177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986791,0.00012868721,0.0003992631,0.00014621028,0.0005168768,0.00012988521],"domain_scores_gemma":[0.9983834,0.0003342854,0.00048130404,0.00009222715,0.0006759275,0.000032840242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015971105,0.00008972182,0.000105014435,0.0005587299,0.000208626,0.00033765816,0.00048641395,0.000030477095,0.00007618471],"category_scores_gemma":[0.00013147335,0.000076091485,0.000038180064,0.00050029316,0.00008541355,0.00087424676,0.00008535231,0.00012169767,0.0000016486247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055579792,0.00056683447,0.014632614,0.00003978731,0.00018537224,8.540806e-7,0.0029921345,0.000004602803,0.000007415776,0.90217644,0.020272262,0.059066106],"study_design_scores_gemma":[0.00084002106,0.000056212662,0.27816215,0.0005540329,0.0001913567,0.0000018422858,0.1892173,0.000027286067,0.000014535987,0.16823807,0.36252528,0.00017191135],"about_ca_topic_score_codex":0.000060613787,"about_ca_topic_score_gemma":0.000042389634,"teacher_disagreement_score":0.8272777,"about_ca_system_score_codex":0.0005622366,"about_ca_system_score_gemma":0.0006148057,"threshold_uncertainty_score":0.32560453},"labels":[],"label_agreement":null},{"id":"W4416263112","doi":"10.55016/ojs/cpai.v8i4.81748","title":"Neutralizing the Threat of Technology","year":2025,"lang":"","type":"article","venue":"Canadian Perspectives on Academic Integrity","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Conestoga College","funders":"","keywords":"Value (mathematics); Foundation (evidence); Point (geometry); Filter (signal processing); Cognition","score_opus":0.028981222021889567,"score_gpt":0.36279158077491913,"score_spread":0.33381035875302956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416263112","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3312909,0.010104848,0.000026496451,0.17465447,0.0018304941,0.0010285476,0.0000719314,0.000065884466,0.48092645],"genre_scores_gemma":[0.9864267,0.005162466,0.000036717014,0.0013124981,0.00029826895,0.000030049565,0.0000014101164,0.000015184473,0.00671668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9969983,0.00036660026,0.0005216114,0.0006917872,0.00044101593,0.0009806523],"domain_scores_gemma":[0.9981013,0.00042853088,0.00023196476,0.0005255418,0.0004318544,0.00028080933],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0014216824,0.00035273196,0.000499729,0.0010781004,0.001252122,0.000072629125,0.0019612394,0.0013039458,0.0006648849],"category_scores_gemma":[0.0009990546,0.0002862136,0.0002706416,0.0029144557,0.0029842444,0.00017874868,0.00012785498,0.0050984696,0.000068704794],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002628967,0.00004175117,0.033999734,0.0000145913045,0.00016940151,0.0000037210004,0.04884691,0.0000016176783,0.000100971,0.9043193,0.008608523,0.0038672078],"study_design_scores_gemma":[0.00048138123,0.00012047292,0.045180026,0.00057901157,0.000181541,0.000001490019,0.82387036,0.00005986651,0.000526023,0.043203555,0.085375324,0.00042096738],"about_ca_topic_score_codex":0.21495257,"about_ca_topic_score_gemma":0.2041634,"teacher_disagreement_score":0.86111575,"about_ca_system_score_codex":0.0024391355,"about_ca_system_score_gemma":0.0035630462,"threshold_uncertainty_score":0.99999255},"labels":[],"label_agreement":null},{"id":"W4416328737","doi":"10.7592/tertium.2025.10.1.322","title":"Beyond the Bubble","year":2025,"lang":"pl","type":"article","venue":"Półrocznik Językoznawczy Tertium","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Summative assessment; Construct (python library); Excellence; Test (biology); Foreign language; Language assessment; Government (linguistics)","score_opus":0.01482895853523709,"score_gpt":0.3296920592079808,"score_spread":0.3148631006727437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416328737","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05214056,0.0037707686,0.0003379576,0.064972915,0.011539304,0.0013904372,0.0000307707,0.00030350793,0.8655138],"genre_scores_gemma":[0.7864155,0.00089136354,0.00011904841,0.006458654,0.0013476689,0.00010052818,0.000014993193,0.000036857986,0.20461537],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952185,0.0005483138,0.0007914386,0.00086976803,0.0011782844,0.0013936562],"domain_scores_gemma":[0.99753547,0.0006968841,0.00028494454,0.0009994599,0.00025313577,0.00023008263],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015881853,0.0005625989,0.00058740267,0.00023676912,0.0024036064,0.00092706224,0.0022265648,0.0004098318,0.0020085939],"category_scores_gemma":[0.00021038507,0.00042701614,0.0004578689,0.0019322273,0.0010039514,0.00046905648,0.00068836845,0.00072835846,0.0017887357],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016173226,0.0008032774,0.10499424,0.00015984714,0.0008037431,0.000027004982,0.03653573,0.000011835754,0.0010398218,0.19601601,0.6401635,0.019283298],"study_design_scores_gemma":[0.0013167422,0.00012266124,0.07373783,0.00019181865,0.0005493648,0.0000017555664,0.021153234,0.00024605507,0.000544487,0.013676701,0.8876441,0.0008152685],"about_ca_topic_score_codex":0.0013431482,"about_ca_topic_score_gemma":0.0011952011,"teacher_disagreement_score":0.734275,"about_ca_system_score_codex":0.0003251977,"about_ca_system_score_gemma":0.00064182363,"threshold_uncertainty_score":0.99981815},"labels":[],"label_agreement":null},{"id":"W4416363396","doi":"10.1080/0047231x.2025.2576707","title":"Can a Small Change in Exam Question Format Help Students? Sadly, Not","year":2025,"lang":"en","type":"article","venue":"Journal of College Science Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Field (mathematics); Set (abstract data type); Feature (linguistics); Frequently asked questions","score_opus":0.04610037157081655,"score_gpt":0.4123545222884498,"score_spread":0.3662541507176333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416363396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9720218,0.00010989328,0.00015425443,0.005972691,0.0013763552,0.00031708874,0.0000016637528,0.000018465533,0.020027779],"genre_scores_gemma":[0.99695677,0.00011977418,0.0009739269,0.00059274514,0.00031025015,0.0000077344075,1.4460832e-7,0.0000041136814,0.0010345735],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99713564,0.0003419683,0.0004895494,0.00017233483,0.0014025314,0.0004580006],"domain_scores_gemma":[0.99907696,0.00014158654,0.00032427188,0.000117010444,0.0001961226,0.0001440733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012280043,0.00011261837,0.00025006814,0.00087347836,0.0010431081,0.0003674012,0.0012657056,0.00006236548,0.000019945657],"category_scores_gemma":[0.0005455204,0.00009897736,0.0000830021,0.0013022411,0.00030263313,0.0013794674,0.00018179127,0.0004987028,0.0000029557107],"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":[0.00008653326,0.0005044329,0.68319005,0.000022865364,0.000029380717,0.00007384965,0.092590794,0.00002049601,0.0021744778,0.18930013,0.00082069717,0.03118629],"study_design_scores_gemma":[0.0014191937,0.00019225158,0.9175141,0.0006246895,0.000034253146,0.000008916876,0.070639014,0.0002553725,0.00013803753,0.001823109,0.007105868,0.00024520024],"about_ca_topic_score_codex":0.0015372677,"about_ca_topic_score_gemma":0.0061872057,"teacher_disagreement_score":0.23432404,"about_ca_system_score_codex":0.0008677654,"about_ca_system_score_gemma":0.00079772255,"threshold_uncertainty_score":0.80228496},"labels":[],"label_agreement":null},{"id":"W4416466302","doi":"10.5430/wje.v15n4p1","title":"Exploring Students' Perspective on University Exit Exam","year":2025,"lang":"","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Higher education; Anxiety; Relevance (law); Preference; Perspective (graphical); Likert scale; Test anxiety; Perception","score_opus":0.08070052760520088,"score_gpt":0.3979036730819686,"score_spread":0.31720314547676776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416466302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62869984,0.0009364108,0.000057440644,0.010947045,0.013175156,0.0002686748,8.942047e-7,0.0000096967215,0.34590483],"genre_scores_gemma":[0.9357908,0.0046995357,0.00012823359,0.00022453892,0.0012786348,0.0000012916573,3.944613e-7,0.0000067742285,0.057869837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99789345,0.00037102905,0.00038873957,0.00022487793,0.00085901003,0.00026287578],"domain_scores_gemma":[0.99799377,0.00029699615,0.0005695697,0.00015822273,0.00083036,0.00015108335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010755497,0.00016708129,0.00027895506,0.0017445505,0.0006660413,0.00021817403,0.0007800882,0.000047984202,0.0005339322],"category_scores_gemma":[0.00016017225,0.00018074867,0.00021422395,0.0028708747,0.00015528055,0.0010080779,0.000086793065,0.00046146702,0.00004364198],"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":[0.0008042212,0.0059633492,0.21318191,0.000047274047,0.0009595432,0.000019302312,0.16797623,0.000051823343,0.0000980432,0.4993457,0.071109705,0.040442888],"study_design_scores_gemma":[0.0007234766,0.00017899959,0.32777482,0.0007291932,0.00027956945,6.4377645e-7,0.52297264,0.0000012385572,0.0000414139,0.0022355567,0.14488836,0.00017406925],"about_ca_topic_score_codex":0.00042853612,"about_ca_topic_score_gemma":0.00038891326,"teacher_disagreement_score":0.49711016,"about_ca_system_score_codex":0.0020754617,"about_ca_system_score_gemma":0.0015705288,"threshold_uncertainty_score":0.7370717},"labels":[],"label_agreement":null},{"id":"W4416564265","doi":"10.1007/s12564-025-10099-2","title":"The impact of online feedback on student learning outcomes: a meta-analysis study","year":2025,"lang":"en","type":"article","venue":"Asia Pacific Education Review","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Peer feedback; Cognition; Set (abstract data type); Outcome (game theory); TUTOR; Inclusion (mineral); Online learning; Feedback regulation; Significant difference; Higher education","score_opus":0.08081612670346547,"score_gpt":0.4959486766171236,"score_spread":0.4151325499136581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416564265","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26819947,0.2526647,0.000039768496,0.065106586,0.0016330916,0.010300967,0.000023004302,0.0001850781,0.40184736],"genre_scores_gemma":[0.94396055,0.022335947,0.000031808675,0.0001713034,0.00003784691,0.0002072605,0.000018673763,0.000006764623,0.033229843],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99710315,0.0011457453,0.0006142686,0.00028190747,0.0006370231,0.0002179013],"domain_scores_gemma":[0.9980125,0.00070035155,0.00041168716,0.00050953106,0.0003002813,0.00006565306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024624588,0.00018936598,0.000953859,0.00017554413,0.0005451076,0.00011393074,0.00052652124,0.00003576601,0.00074487284],"category_scores_gemma":[0.00046621094,0.00010138314,0.0014575099,0.0022560968,0.00009099896,0.0000767765,0.000048403286,0.00018847712,0.00004775404],"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":[0.00000600612,0.0036345073,0.8822275,0.00007180025,0.07644351,2.5064827e-7,0.00922312,0.000024689454,6.715342e-7,0.0044009704,0.012135364,0.011831605],"study_design_scores_gemma":[0.00012659241,0.00012236122,0.76454926,0.00007925123,0.05971224,3.3956535e-8,0.12490721,0.0000012584959,1.9622912e-7,0.000072512245,0.05029661,0.00013248697],"about_ca_topic_score_codex":0.000763827,"about_ca_topic_score_gemma":0.0005442245,"teacher_disagreement_score":0.67576104,"about_ca_system_score_codex":0.00017142757,"about_ca_system_score_gemma":0.0006526911,"threshold_uncertainty_score":0.8155835},"labels":[],"label_agreement":null},{"id":"W4416724673","doi":"10.3126/erj.v2i01.86476","title":"From Standardized Tests to Meaningful Experiences: The Future of Student Assessment","year":2025,"lang":"","type":"article","venue":"Education Review Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Experiential learning; Standardized test; Dominance (genetics); Educational assessment; Rote learning; Sample (material)","score_opus":0.024654410534224732,"score_gpt":0.45762656978673516,"score_spread":0.4329721592525104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416724673","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18156959,0.5855422,0.00088371325,0.1463102,0.039651886,0.003271427,0.000017495071,0.000021945774,0.042731535],"genre_scores_gemma":[0.49527287,0.47644907,0.0039265663,0.010199108,0.0086772395,0.00043580303,0.00000968469,0.00002390449,0.0050057317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99460685,0.0013604187,0.0014117438,0.00038548908,0.0018302676,0.00040523187],"domain_scores_gemma":[0.99663895,0.00038947247,0.0010820298,0.0004980573,0.0011107692,0.00028069303],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040253205,0.00030360935,0.00076383195,0.00015146735,0.0012977071,0.0005746413,0.0016259174,0.000095662326,0.005904284],"category_scores_gemma":[0.00022917576,0.00020352172,0.0003970546,0.001703062,0.00021131692,0.00032800192,0.00020380312,0.00058562524,0.00003431775],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025078332,0.0010784107,0.03174872,0.00033179094,0.00046698452,0.0000014157586,0.23986156,0.0000022417032,0.000044887347,0.006265651,0.49011108,0.23006219],"study_design_scores_gemma":[0.00025070173,0.00007158783,0.048847668,0.0057485593,0.00034310893,0.0000011868835,0.40177166,6.937193e-7,0.0000070353144,0.0005658437,0.5422342,0.00015775606],"about_ca_topic_score_codex":0.00010594121,"about_ca_topic_score_gemma":0.00006996643,"teacher_disagreement_score":0.3137033,"about_ca_system_score_codex":0.00065011793,"about_ca_system_score_gemma":0.0072402037,"threshold_uncertainty_score":0.9983878},"labels":[],"label_agreement":null},{"id":"W4416760191","doi":"10.47116/apjcri.2025.11.20","title":"A Global Bibliometric Analysis of Assessment Literacy in Preservice Teacher Education (2000–2024)","year":2025,"lang":"","type":"article","venue":"Asia-pacific Journal of Convergent Research Interchange","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Teacher education; Literacy; Higher education; Student teacher","score_opus":0.07266060113008153,"score_gpt":0.48620090350209716,"score_spread":0.4135403023720156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416760191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7796365,0.01797712,0.0004819694,0.008602354,0.0066306475,0.0014393018,0.000067211775,0.000011528533,0.18515337],"genre_scores_gemma":[0.9644034,0.0132680945,0.00029832995,0.000053364685,0.0003705876,0.00005550139,0.00001747175,0.000017702418,0.02151557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9862078,0.0043034395,0.002645358,0.00070535316,0.0047164964,0.0014215674],"domain_scores_gemma":[0.9902063,0.0011373914,0.0012870992,0.0007435893,0.006037632,0.0005879688],"candidate_categories":["metaepi_narrow","bibliometrics","insufficient_payload"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.017690793,0.00044546538,0.001473402,0.13898927,0.00032107875,0.00071055855,0.0026557953,0.00041328667,0.009288974],"category_scores_gemma":[0.0013275222,0.00042193657,0.00095250324,0.3496183,0.0006517383,0.0015179176,0.0008452647,0.001660278,0.000034430126],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0005266097,0.004722189,0.84512895,0.00034397692,0.0037428413,0.00003902264,0.022355344,0.000014757606,0.00013631805,0.0039121523,0.030402577,0.08867527],"study_design_scores_gemma":[0.0012829859,0.0007714362,0.828411,0.0012209695,0.0012417606,0.000003229838,0.10898908,0.0014221243,0.000041408715,0.0017819911,0.0545038,0.00033024582],"about_ca_topic_score_codex":0.005924468,"about_ca_topic_score_gemma":0.002497775,"teacher_disagreement_score":0.210629,"about_ca_system_score_codex":0.0045685973,"about_ca_system_score_gemma":0.008436815,"threshold_uncertainty_score":0.9998233},"labels":[],"label_agreement":null},{"id":"W4416789755","doi":"10.3389/feduc.2025.1695771","title":"Training in-service subject teachers to implement formative assessment through action research","year":2025,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Action research; Professional development; Action (physics); Subject (documents); Faculty development; Training (meteorology)","score_opus":0.13557708049205017,"score_gpt":0.5319322045050002,"score_spread":0.39635512401295003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416789755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65051556,0.00015781182,0.007889895,0.025478657,0.008243334,0.0019287773,0.0000018883019,0.000043926553,0.30574012],"genre_scores_gemma":[0.9814859,0.00014342702,0.015390159,0.0005497555,0.00018609171,0.0004380521,0.000017948798,0.000006396911,0.00178226],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9981713,0.00047481334,0.0002477166,0.00023524153,0.00045432732,0.00041657558],"domain_scores_gemma":[0.9995199,0.00010361502,0.000052775235,0.00013155708,0.00014520469,0.000046981946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024982835,0.000083208935,0.00013659446,0.00051629794,0.0003305362,0.00010825247,0.0002747159,0.00007427355,0.00005581846],"category_scores_gemma":[0.00012124908,0.000093889874,0.000024466324,0.0020196869,0.000038897484,0.00052411924,0.000052563777,0.00028747888,0.0000085718475],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001610457,0.00023389017,0.1599846,0.0000148957215,0.000015994976,1.6290976e-7,0.6221379,0.000015031805,0.00003531705,0.0089775445,0.056485333,0.1520832],"study_design_scores_gemma":[0.00020331217,0.000025522317,0.13820894,0.00006767513,0.000004078749,1.2876126e-8,0.717291,0.0000218192,0.000041835527,0.0078398865,0.13621607,0.000079837424],"about_ca_topic_score_codex":0.007709767,"about_ca_topic_score_gemma":0.01753059,"teacher_disagreement_score":0.33097032,"about_ca_system_score_codex":0.0026501182,"about_ca_system_score_gemma":0.002078327,"threshold_uncertainty_score":0.99889797},"labels":[],"label_agreement":null},{"id":"W4416872428","doi":"10.47772/ijriss.2025.903sedu0705","title":"Global Trends in School-Based Assessment: Implications for Effective Implementation in Sri Lanka","year":2025,"lang":"","type":"article","venue":"International Journal of Research and Innovation in Social Science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Nexus (standard); Moderation; Workload; Quality (philosophy); Reliability (semiconductor); Foundation (evidence); Empirical evidence","score_opus":0.07689676829601365,"score_gpt":0.5939911336009404,"score_spread":0.5170943653049267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416872428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.921956,0.00011273554,0.0012843456,0.036324393,0.0011999044,0.0009214997,0.00006616565,0.000005343557,0.038129635],"genre_scores_gemma":[0.9986315,0.0001143267,0.00047667354,0.00022539379,0.00035255018,0.00010156638,0.000016439704,0.0000030135377,0.00007858649],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958516,0.00035813995,0.0011747293,0.00035910608,0.0016850616,0.00057139614],"domain_scores_gemma":[0.99480087,0.00057586405,0.00048681736,0.00007019453,0.003990085,0.00007619878],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.013071045,0.00012779215,0.0002556554,0.0065083946,0.0005894203,0.00065279024,0.0010130573,0.00011960206,0.00008728984],"category_scores_gemma":[0.0010788637,0.00013565115,0.00005846588,0.021738578,0.0011236813,0.0013615162,0.00016738189,0.00049007905,6.2220107e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016020612,0.0002614821,0.6525499,0.000008437075,0.000016718164,0.0000020811842,0.002218546,0.000013581452,0.0003843074,0.28068843,0.00047582758,0.06322047],"study_design_scores_gemma":[0.0032469395,0.00020894881,0.9296687,0.00014943945,0.0000037377615,4.6011888e-7,0.015073326,0.0002057236,0.000039773593,0.049606606,0.0016984174,0.00009790924],"about_ca_topic_score_codex":0.0007551787,"about_ca_topic_score_gemma":0.0021389695,"teacher_disagreement_score":0.27711883,"about_ca_system_score_codex":0.0042327647,"about_ca_system_score_gemma":0.0031739373,"threshold_uncertainty_score":0.9995898},"labels":[],"label_agreement":null},{"id":"W4416894890","doi":"10.1080/0969594x.2025.2591284","title":"An implementation of argument-based validation for assessing college major preferences with a hybrid of Likert-rating and forced-choice formats","year":2025,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data collection; Measure (data warehouse); Key (lock); Quality (philosophy)","score_opus":0.04844669177838798,"score_gpt":0.4835110550125784,"score_spread":0.4350643632341904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416894890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807323,0.00006987273,0.0032949657,0.004250352,0.00011073368,0.0011923717,0.00002554476,0.000014989774,0.010308842],"genre_scores_gemma":[0.9706818,0.00012551948,0.028502118,0.00024359168,0.00006391154,0.00021321933,0.00006602218,0.000006566947,0.00009725805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984451,0.00040218025,0.00045382106,0.0002187012,0.00028899734,0.00019123414],"domain_scores_gemma":[0.9965391,0.002300221,0.0006561158,0.00012795611,0.0003228883,0.00005369718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017770339,0.00011608828,0.0001861462,0.00030360027,0.0003287303,0.00016934877,0.00012277483,0.00004658314,0.000011089872],"category_scores_gemma":[0.00057838147,0.00011249646,0.000019607121,0.00042111013,0.00010287753,0.0019616962,0.000027588305,0.00008201207,5.816528e-8],"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":[0.0002057682,0.00097279815,0.47743312,0.0006083126,0.000109544424,1.704726e-7,0.014045234,0.00010367229,0.0021937191,0.4673372,0.00008502579,0.036905434],"study_design_scores_gemma":[0.0033265743,0.00059444696,0.568276,0.0005674294,0.00035218455,0.0000019917004,0.3990984,0.001538567,0.006703575,0.0060767853,0.013078263,0.00038580134],"about_ca_topic_score_codex":0.0052848696,"about_ca_topic_score_gemma":0.0017280047,"teacher_disagreement_score":0.4612604,"about_ca_system_score_codex":0.00015439543,"about_ca_system_score_gemma":0.0029677702,"threshold_uncertainty_score":0.7989177},"labels":[],"label_agreement":null},{"id":"W4416920459","doi":"10.1108/book-978-1-64113-529-020251067","title":"Assessment For Learning In Saskatchewan Mathematics Classes","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Class (philosophy); Work (physics); Process (computing); Data collection","score_opus":0.04024173403330422,"score_gpt":0.3559005485326526,"score_spread":0.3156588144993484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416920459","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018345164,0.000056373767,0.0013269796,0.0004286336,0.00044979647,0.0011701441,0.0000052627015,0.000113624985,0.9962657],"genre_scores_gemma":[0.008029566,0.00019695827,0.0120522175,0.00009386139,0.00033617922,0.000031991483,0.000035482113,0.000055596298,0.9791682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822235,0.00002808435,0.00039455932,0.00034775698,0.0006245309,0.0003827215],"domain_scores_gemma":[0.99877053,0.00060456333,0.00025746692,0.00018789445,0.00010878194,0.000070774906],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008762122,0.000265758,0.0004938185,0.00016457717,0.00020530791,0.00016123231,0.00035398718,0.00041077932,0.0023027398],"category_scores_gemma":[0.000041089144,0.0002549451,0.00020421615,0.0000417558,0.00010140899,0.00012373777,0.000086970176,0.00041600122,0.00019930198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039894667,0.00004967977,0.003102869,0.00009916976,0.00006577037,0.000002364001,0.0060375934,0.0000069047846,0.00000997643,0.9832467,0.0037505198,0.0036244744],"study_design_scores_gemma":[0.00064010406,0.0001280942,0.0009172055,0.00026744636,0.00008098723,2.1187485e-7,0.046088748,0.0001310408,0.0000019785823,0.045942433,0.9051717,0.00063007284],"about_ca_topic_score_codex":0.0002439278,"about_ca_topic_score_gemma":0.011225805,"teacher_disagreement_score":0.93730426,"about_ca_system_score_codex":0.00034602982,"about_ca_system_score_gemma":0.0009989516,"threshold_uncertainty_score":0.9999903},"labels":[],"label_agreement":null},{"id":"W4416934519","doi":"10.1016/j.tate.2025.105343","title":"“How should I assess their writing? It’s a headache for me.”: Understanding teacher assessment literacy in the collaborative writing context","year":2025,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Social Science Fund of China","keywords":"Literacy; Context (archaeology); Writing assessment; Collaborative learning; Collaborative writing; Mainland China; Teacher education","score_opus":0.10887334018280642,"score_gpt":0.4503753852886655,"score_spread":0.3415020451058591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416934519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62952745,0.0016408213,0.019137157,0.17638525,0.00086961983,0.00272845,0.000011613575,0.00016896453,0.16953069],"genre_scores_gemma":[0.9879573,0.0000467827,0.0017740075,0.0021209884,0.00052128115,0.00037764394,0.000035872283,0.000017744987,0.0071483757],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9967767,0.0016534814,0.00035011375,0.0004123061,0.00038356343,0.00042383728],"domain_scores_gemma":[0.99790055,0.0015016422,0.00018340247,0.00020978083,0.00014112402,0.00006352909],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0072111646,0.00023225367,0.00027426358,0.00020460931,0.0018348448,0.0016142536,0.00034618424,0.0001706038,0.000018167639],"category_scores_gemma":[0.0005621026,0.00018329981,0.000079514124,0.0004355242,0.00015408854,0.0006897158,0.000050232884,0.0009168153,5.18228e-7],"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":[0.000027707321,0.0008779151,0.16644457,0.000069268615,0.00007722577,4.7170278e-7,0.37067735,9.2470907e-7,0.00011945037,0.34436214,0.016849197,0.10049377],"study_design_scores_gemma":[0.00061862863,0.000044496846,0.027962198,0.0002743236,0.0000601769,6.24431e-7,0.89698386,0.000394785,0.0000052914475,0.008494516,0.06492588,0.00023521944],"about_ca_topic_score_codex":0.0014016789,"about_ca_topic_score_gemma":0.0012831008,"teacher_disagreement_score":0.5263065,"about_ca_system_score_codex":0.0007364441,"about_ca_system_score_gemma":0.0008361411,"threshold_uncertainty_score":0.99946463},"labels":[],"label_agreement":null},{"id":"W4417318533","doi":"10.65431/jrell.v1i2.22","title":"The influence of peer assessment on students’ writing scores in descriptive text","year":2025,"lang":"","type":"article","venue":"Journal of Research in English Language Teaching and Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"CLARITY; Peer assessment; Peer feedback; Descriptive statistics; Peer tutor; Context (archaeology); Writing assessment; Thematic analysis; Metacognition; Perception","score_opus":0.041063488038485814,"score_gpt":0.4627083866701615,"score_spread":0.4216448986316757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417318533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95130473,0.0021976253,0.000007843173,0.00045100105,0.001187577,0.00032344004,0.000004869924,0.0000062018094,0.044516716],"genre_scores_gemma":[0.99526066,0.0018834247,0.0005913745,0.000035182216,0.0012382861,0.0000050655926,5.711062e-7,0.0000124444605,0.0009730004],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99080163,0.003564721,0.0012726816,0.0002783603,0.003335262,0.00074731885],"domain_scores_gemma":[0.9878308,0.009121113,0.00050777534,0.00023845566,0.0021579978,0.00014385344],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04596387,0.00020101873,0.0005007897,0.0009826852,0.00094983523,0.00074351364,0.0012199401,0.00016825204,0.000007650923],"category_scores_gemma":[0.079825416,0.0001529645,0.00010280738,0.0010012655,0.00083243876,0.000112367066,0.0004370677,0.004892096,4.5596963e-7],"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":[0.00025640053,0.0007790633,0.61009264,0.00016951039,0.00012520494,0.0002695587,0.3387151,0.00060998165,0.00005505536,0.036993798,0.0005140892,0.01141956],"study_design_scores_gemma":[0.0015929635,0.00055839564,0.22946459,0.005156802,0.00003696411,7.31452e-7,0.75570166,0.00021743155,0.000014478856,0.0013795053,0.00571297,0.00016353058],"about_ca_topic_score_codex":0.0020638444,"about_ca_topic_score_gemma":0.0009306663,"teacher_disagreement_score":0.41698653,"about_ca_system_score_codex":0.0006367206,"about_ca_system_score_gemma":0.0008352808,"threshold_uncertainty_score":0.9974037},"labels":[],"label_agreement":null},{"id":"W4417351506","doi":"10.1093/conphys/coaf085","title":"Tips and tricks for writing constructive peer reviews","year":2025,"lang":"en","type":"article","venue":"Conservation Physiology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Fisheries and Oceans Canada; University of New Brunswick","funders":"","keywords":"Constructive; Peer review; Peer evaluation","score_opus":0.05521597252947013,"score_gpt":0.40198410600867734,"score_spread":0.3467681334792072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417351506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86467946,0.0023882773,0.005384238,0.037222918,0.001394108,0.0023370003,0.000015353831,0.0001173471,0.08646129],"genre_scores_gemma":[0.9739322,0.00076602964,0.0027139292,0.0054318015,0.00031020187,0.00022557231,0.000037502672,0.0000058366845,0.016576918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993805,0.00012575147,0.00016145536,0.00014697293,0.000057582853,0.0001277321],"domain_scores_gemma":[0.9991643,0.0004761271,0.0000802045,0.000057507255,0.00020270645,0.000019168121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049898494,0.000053981305,0.00015555193,0.000042668464,0.00033021928,0.000026160644,0.000074180534,0.00006169126,0.000037265152],"category_scores_gemma":[0.00060659344,0.00005156186,0.00003398804,0.00016083474,0.00023021825,0.00008885978,0.000026121206,0.000045523448,0.0000055888727],"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":[0.000057159683,0.000028749515,0.073718,0.00004817544,0.000043023152,1.1939284e-7,0.0036601636,1.1859285e-7,0.005320983,0.75061566,0.13768439,0.028823458],"study_design_scores_gemma":[0.000518765,0.000019784236,0.1045546,0.00002025161,0.000022575055,1.1886188e-7,0.0041239946,0.00004956303,0.000042173342,0.024898788,0.86566913,0.00008027055],"about_ca_topic_score_codex":0.00008890311,"about_ca_topic_score_gemma":0.00007231549,"teacher_disagreement_score":0.7279847,"about_ca_system_score_codex":0.00002367281,"about_ca_system_score_gemma":0.00008785366,"threshold_uncertainty_score":0.25398132},"labels":[],"label_agreement":null},{"id":"W4417409629","doi":"10.13140/rg.2.2.31942.42560","title":"Pupils' self-evaluation biases influence teachers' judgments about their competence","year":2019,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Competence (human resources); Perception; Affect (linguistics); Cognitive bias","score_opus":0.043450442722163106,"score_gpt":0.3578247868108449,"score_spread":0.3143743440886818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417409629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7846679,0.00007415088,0.000011065266,0.00035812953,0.0003205128,0.00057769456,0.0000013230704,0.00015294514,0.21383628],"genre_scores_gemma":[0.99324054,0.00010779301,0.00049929146,0.00039643963,0.000101376965,0.000030279905,0.0000065668005,0.0000075353914,0.0056101745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981142,0.00022816427,0.00018299594,0.00026830926,0.0008803909,0.00032589553],"domain_scores_gemma":[0.9991895,0.00023385325,0.00009413612,0.00021182913,0.00018461193,0.000086077365],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012698239,0.00012308186,0.0001427579,0.000059320482,0.00030122773,0.00018097964,0.00040851388,0.00007470493,0.0025433265],"category_scores_gemma":[0.0001376857,0.000101516285,0.00005864729,0.00029250327,0.000097037024,0.000591843,0.00007200224,0.000101761005,0.0011018579],"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":[0.000005337805,0.00014623848,0.9502714,0.0000049959804,0.000045162673,4.357612e-7,0.03662391,0.00006212419,0.00079514785,0.006340608,0.0012339822,0.0044706156],"study_design_scores_gemma":[0.00087781745,0.000076865086,0.9275485,0.00006589633,0.00004544249,2.726171e-7,0.035394132,0.0010016244,0.00033267026,0.00073454087,0.033556566,0.0003656525],"about_ca_topic_score_codex":0.0010182717,"about_ca_topic_score_gemma":0.000498724,"teacher_disagreement_score":0.20857266,"about_ca_system_score_codex":0.00016181715,"about_ca_system_score_gemma":0.00020203851,"threshold_uncertainty_score":0.99967587},"labels":[],"label_agreement":null},{"id":"W4417427785","doi":"10.1111/tct.70259","title":"Feeling Feedback: The Role of Emotions in Feedback","year":2025,"lang":"en","type":"article","venue":"The Clinical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Feeling; Pride; Sadness; Situated; Negative feedback; Peer feedback; Control (management); Anger","score_opus":0.06854066440182474,"score_gpt":0.4319387592460753,"score_spread":0.36339809484425056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417427785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6960965,0.00034534902,0.000027267022,0.025032066,0.00051323074,0.0003465982,0.0000010426663,0.00003997869,0.277598],"genre_scores_gemma":[0.9774273,0.00023882264,0.00008270456,0.00039938084,0.00033585366,0.0000135910195,8.955003e-7,0.000006525664,0.021494906],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99786335,0.0008883801,0.00048469566,0.00019086436,0.00029769627,0.00027502025],"domain_scores_gemma":[0.9979301,0.0014825143,0.00012743736,0.00035663502,0.00006308462,0.000040199946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004773432,0.00009292449,0.00022947918,0.00004181163,0.0003708678,0.000053534175,0.0008252533,0.00013940744,0.00036317258],"category_scores_gemma":[0.0009516434,0.000054074648,0.00019237975,0.0005855987,0.0007288292,0.00007141591,0.00017655123,0.00050761935,0.00009299948],"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":[0.000049352948,0.00052248634,0.8382421,0.0000046687687,0.000105409694,5.2919324e-7,0.012374064,0.000022231345,0.0000521939,0.09097395,0.009539622,0.048113387],"study_design_scores_gemma":[0.00057549006,0.000025180587,0.7757,0.000057493013,0.000059005022,6.230179e-8,0.04005617,0.00016145787,0.000009030713,0.027231451,0.15601848,0.00010621094],"about_ca_topic_score_codex":0.000753142,"about_ca_topic_score_gemma":0.0013742606,"teacher_disagreement_score":0.28133085,"about_ca_system_score_codex":0.000045482022,"about_ca_system_score_gemma":0.00017188137,"threshold_uncertainty_score":0.3976485},"labels":[],"label_agreement":null},{"id":"W568408786","doi":"10.1057/9780230621565_12","title":"The Uses of Error: Toward a Realist Methodology of Student Evaluation","year":2009,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan US eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Wonder; Documentation; Mathematics education; Class (philosophy); Perception; Set (abstract data type); Quarter (Canadian coin); Psychology; Field (mathematics); Epistemology; Pedagogy; Computer science; Social psychology; Mathematics; Engineering; Philosophy","score_opus":0.21058115007426195,"score_gpt":0.4256058278644708,"score_spread":0.21502467779020887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W568408786","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014745271,0.0014796254,0.000038472255,0.0002294973,0.0005232814,0.0012019945,0.00003822562,0.00003564952,0.9949787],"genre_scores_gemma":[0.96838135,0.0010897188,0.0006934797,0.00010202806,0.00041239586,0.00003606344,0.00003252317,0.000039472772,0.02921298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996044,0.0007296297,0.0007778037,0.00037734656,0.0017046101,0.00036665332],"domain_scores_gemma":[0.9968973,0.00094101,0.000965783,0.0005076167,0.0005963543,0.00009193949],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040551564,0.00031941247,0.0007077707,0.00016119034,0.00030726715,0.000046218447,0.00083398074,0.00036457318,0.00024069332],"category_scores_gemma":[0.00019170094,0.0002457245,0.00035494525,0.000034464938,0.00088737666,0.0000028634875,0.00014795295,0.00024385251,0.000010317632],"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":[0.0000644775,0.000003963197,0.0013856911,0.000025940262,0.00029822328,0.00000324683,0.01306685,0.0000016216413,0.000106559084,0.9265771,0.00012815469,0.058338195],"study_design_scores_gemma":[0.0007560374,0.00036418735,0.019584911,0.0001767234,0.00079841696,0.0000017647247,0.0050443844,0.000007892148,0.00017664002,0.93918484,0.033398855,0.0005053405],"about_ca_topic_score_codex":0.0011125236,"about_ca_topic_score_gemma":0.0041161086,"teacher_disagreement_score":0.9669068,"about_ca_system_score_codex":0.00016343534,"about_ca_system_score_gemma":0.00038208358,"threshold_uncertainty_score":0.9999995},"labels":[],"label_agreement":null},{"id":"W6886083659","doi":"10.14288/1.0406080","title":"English for academic purposes in Canada : practitioners’ assessment practices and construction of assessment literacy","year":2021,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Literacy; English for academic purposes; Assessment for learning; Higher education; Population; Mainland; Grounded theory; Needs assessment","score_opus":0.01624634877687258,"score_gpt":0.2852179691138342,"score_spread":0.2689716203369616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6886083659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922889,0.00016543774,0.00013712449,0.00058956596,0.00033870983,0.0003457144,0.00012957893,0.000012417695,0.0059925662],"genre_scores_gemma":[0.9911307,0.0013519321,0.0071132216,0.000029084125,0.000053146658,0.0000023133712,0.000025983367,0.000005066453,0.00028854114],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99876326,0.00018133389,0.00017878918,0.00027250338,0.00040764693,0.00019644985],"domain_scores_gemma":[0.9983523,0.00038907878,0.00051458774,0.00009689563,0.00056641904,0.00008071626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047578817,0.00003700193,0.00023200749,0.000038848186,0.00026587653,0.0001040857,0.00015637506,0.00008426928,0.00012821266],"category_scores_gemma":[0.0002378606,0.00012084417,0.000046103574,0.0003065156,0.0002150284,0.0009851372,0.00007852548,0.00018055769,1.2145556e-7],"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":[0.000010308631,0.00011557292,0.8044933,0.00011462128,0.000064519176,0.000055364842,0.003349835,0.000002645861,0.0001782292,0.0003447482,0.001000252,0.19027062],"study_design_scores_gemma":[0.0007828606,0.000027888176,0.88889354,0.00011744595,0.00004738082,0.0000060042453,0.10544107,0.000054266646,0.0000014920869,0.00036516943,0.0041561997,0.000106694],"about_ca_topic_score_codex":0.95523185,"about_ca_topic_score_gemma":0.9963099,"teacher_disagreement_score":0.19016393,"about_ca_system_score_codex":0.0004496059,"about_ca_system_score_gemma":0.0030273008,"threshold_uncertainty_score":0.53703016},"labels":[],"label_agreement":null},{"id":"W6887713702","doi":"10.17608/k6.auckland.5547727.v1","title":"Appendix B 2013 Safeya Janahi MA.pdf","year":2017,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Citation; Quarter (Canadian coin); Glossary; Appendix","score_opus":0.06679611374813141,"score_gpt":0.3683753477491411,"score_spread":0.3015792340010097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6887713702","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016219558,0.000116182535,3.5224065e-7,0.0025468485,0.00039067655,0.00030693013,0.012394952,0.00008706272,0.98253506],"genre_scores_gemma":[0.7496859,0.000078609526,0.00015372025,0.00045435992,0.002488111,0.0001706198,0.028753452,0.00003342047,0.21818185],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990032,0.00003483815,0.00009520714,0.00018481804,0.00036720667,0.00031477935],"domain_scores_gemma":[0.99928963,0.000055162338,0.00012736578,0.00034824613,0.00006466646,0.00011491909],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010263559,0.00009102227,0.00010799267,0.000026803287,0.0014881806,0.0005275668,0.00088131585,0.00009104114,0.78642416],"category_scores_gemma":[0.00046726712,0.000089056775,0.00007388746,0.000043863234,0.000033279182,0.0004256454,0.00020071102,0.00010297503,0.16437757],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020665138,0.000014435064,0.003464194,0.000007607122,0.000009562915,0.000008135468,0.0009582223,1.4531953e-7,0.0000030061601,0.000498964,0.9929219,0.0021117928],"study_design_scores_gemma":[0.00015228843,0.000009064751,0.055866934,0.00013115333,0.000004425536,1.8658369e-7,0.00083294796,0.0000063418593,0.000012472713,0.00015627129,0.94269764,0.00013028808],"about_ca_topic_score_codex":0.00067368476,"about_ca_topic_score_gemma":0.0018884371,"teacher_disagreement_score":0.7643532,"about_ca_system_score_codex":0.000045951296,"about_ca_system_score_gemma":0.00008119453,"threshold_uncertainty_score":0.99981177},"labels":[],"label_agreement":null},{"id":"W6902225316","doi":"10.6084/m9.figshare.22615813","title":"Additional file 1 of Introducing ACTFAiREST2 to implement online assessments amid COVID–19: a case study from a low resource setting","year":2023,"lang":"en","type":"article","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Resource (disambiguation); Key (lock); Government (linguistics); Data collection","score_opus":0.09351254665865326,"score_gpt":0.46311784848391685,"score_spread":0.3696053018252636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902225316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75951207,0.0000014487639,0.0000059636627,0.0012151361,0.00009303515,0.0013287707,0.23220441,0.000012815538,0.0056263404],"genre_scores_gemma":[0.8062389,0.0000031003628,0.041182637,0.000749801,0.0020021508,0.0012871221,0.12667522,0.000067063316,0.02179403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976978,0.00030954665,0.00038585195,0.0005064555,0.00072184106,0.0003785494],"domain_scores_gemma":[0.9970976,0.0020612013,0.0002019793,0.00028047452,0.000083339655,0.00027540245],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000959377,0.00013856111,0.00024969404,0.00013247938,0.0006774657,0.00028165767,0.0006296594,0.0000464513,0.7138885],"category_scores_gemma":[0.0013504361,0.00014350272,0.000054385997,0.00074486615,0.000048122478,0.00023154012,0.00080712937,0.00012571929,0.0004549444],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029154313,0.00043081978,0.0045833467,0.0000027216267,0.00008486132,0.00047017704,0.03056977,0.000024440715,0.00003302147,0.0000022974864,0.9418437,0.021925682],"study_design_scores_gemma":[0.0005405745,0.00014768708,0.009628419,0.00006738718,0.000027182092,0.0000031639383,0.3136744,0.000102676306,0.0000074012405,0.00001545787,0.6756199,0.00016572933],"about_ca_topic_score_codex":0.009653447,"about_ca_topic_score_gemma":0.037921213,"teacher_disagreement_score":0.71343356,"about_ca_system_score_codex":0.00021780354,"about_ca_system_score_gemma":0.0007090844,"threshold_uncertainty_score":0.9969413},"labels":[],"label_agreement":null},{"id":"W6902235466","doi":"10.6084/m9.figshare.26720376.v1","title":"Additional file 3 of Protocol for a scoping review study on learning plan use in undergraduate medical education","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Protocol (science); Plan (archaeology); Data collection; Protocol analysis; MEDLINE; Data extraction","score_opus":0.1710229444398138,"score_gpt":0.48094805455268513,"score_spread":0.3099251101128713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902235466","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003543204,0.000053932974,2.3569076e-7,0.0006483341,0.000041697378,0.12776726,0.8614008,0.000067085755,0.010017142],"genre_scores_gemma":[0.0000959745,0.0000026856899,0.000054692777,0.00013595051,0.00016646092,0.7002484,0.297631,0.000007667841,0.0016571219],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990748,0.00010565024,0.00016610864,0.00014032314,0.00040846522,0.00010461065],"domain_scores_gemma":[0.9978719,0.0019279817,0.00005920224,0.00004401427,0.000056717858,0.000040198185],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013049782,0.00005336205,0.000099658435,0.000054096785,0.00008241298,0.000058713278,0.00010979946,0.000035477722,0.9521891],"category_scores_gemma":[0.009296213,0.000048307018,0.000039502753,0.000219133,0.0000064280675,0.000131336,0.000025307269,0.00010774583,0.000316717],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033917147,0.000120716635,0.000056838027,0.0014789072,0.0000046525643,0.0000013674413,0.00036163008,2.2445502e-7,1.3786752e-8,0.000041158008,0.9955387,0.0023924115],"study_design_scores_gemma":[0.00010086977,0.0000762371,0.0011174235,0.26628846,0.0000020301857,9.9554626e-8,0.0004252877,0.000024200908,1.0755374e-7,0.000026052037,0.73188734,0.000051905532],"about_ca_topic_score_codex":0.000017712182,"about_ca_topic_score_gemma":0.0005527369,"teacher_disagreement_score":0.9518724,"about_ca_system_score_codex":0.000048909453,"about_ca_system_score_gemma":0.0012470753,"threshold_uncertainty_score":0.9990489},"labels":[],"label_agreement":null},{"id":"W6922134379","doi":"10.11575/ajer.v50i3.55088","title":"Teachers' Attitudes Toward Government-Mandated Provincial Testing in Manitoba","year":2009,"lang":"en","type":"article","venue":"University of Calgary","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Negativity effect; Rural area; Test (biology); Measure (data warehouse); Data collection","score_opus":0.028802977772965133,"score_gpt":0.26591936553619494,"score_spread":0.2371163877632298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6922134379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8187723,0.000019346906,0.000095702206,0.0003288572,0.00005037044,0.00015816402,0.0000015692677,0.000039358594,0.18053435],"genre_scores_gemma":[0.9969183,0.000017356784,0.001554196,0.00004476485,0.000046625686,5.2988945e-8,0.0000022048964,0.000002079125,0.0014144283],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991611,0.00006465366,0.00007624253,0.00012940638,0.0003907177,0.0001778536],"domain_scores_gemma":[0.9997413,0.000053507247,0.00005984239,0.000060843988,0.000034201836,0.00005030771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024369905,0.000060969232,0.00011305816,0.000036986872,0.0001659368,0.000015449472,0.00024907407,0.00006498331,0.00009855176],"category_scores_gemma":[0.00006539263,0.000074451396,0.000036271253,0.00019903667,0.000114955685,0.00019759247,0.000049037833,0.0000996959,0.000010766793],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006671917,0.00023992894,0.9372938,0.000006961343,0.000015373234,0.00005732125,0.018287092,0.0000023800917,0.0007647265,0.0034393133,0.0008148211,0.03901153],"study_design_scores_gemma":[0.0006678831,0.00008224408,0.9735946,0.00003310128,0.000016295051,1.663784e-7,0.019171664,0.00004507806,0.00003174185,0.0001339596,0.006104852,0.00011842676],"about_ca_topic_score_codex":0.0074050175,"about_ca_topic_score_gemma":0.010473692,"teacher_disagreement_score":0.17911991,"about_ca_system_score_codex":0.00026095787,"about_ca_system_score_gemma":0.00010276586,"threshold_uncertainty_score":0.99920475},"labels":[],"label_agreement":null},{"id":"W6924725559","doi":"10.15468/dl.t73qgv","title":"Occurrence Download","year":2022,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Alien; Range (aeronautics); State (computer science); Identification (biology)","score_opus":0.024638893759826846,"score_gpt":0.28368674675292505,"score_spread":0.2590478529930982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924725559","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002155045,0.000017168515,5.1789885e-7,0.0003758247,0.0013550057,0.00038728298,0.99493396,0.000100373996,0.0026143573],"genre_scores_gemma":[0.000009985965,0.00021118295,5.4948487e-7,0.00045659748,0.0000034722882,0.000007254223,0.99930984,7.954733e-9,0.000001140055],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778694,0.00019235827,0.000289427,0.00019463344,0.0011798294,0.00035680665],"domain_scores_gemma":[0.99904144,0.0000340097,0.00028362076,0.0003086299,0.00017008728,0.0001621936],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00068123493,0.00019637003,0.00021759073,0.00008250503,0.0015404564,0.00026194993,0.0009017089,0.00023659525,0.15598817],"category_scores_gemma":[0.00016355533,0.00022587224,0.00015717994,0.00048756553,0.00029635636,0.0010546871,0.0005142647,0.0003224664,0.081554756],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023332803,0.000038786584,0.0036033045,0.00002755319,0.000024955447,0.0000014700875,0.0007603827,0.0000015221347,2.6742564e-9,0.0000011740548,0.9949085,0.0006089827],"study_design_scores_gemma":[0.00021928734,0.000022086486,0.00017300964,5.7849877e-7,0.0000418655,2.8542328e-7,0.004733378,7.87397e-9,4.2164814e-8,0.000001141415,0.99456894,0.00023935548],"about_ca_topic_score_codex":0.005136836,"about_ca_topic_score_gemma":0.00022347376,"teacher_disagreement_score":0.074433416,"about_ca_system_score_codex":0.00083283585,"about_ca_system_score_gemma":0.0004006507,"threshold_uncertainty_score":0.9997594},"labels":[],"label_agreement":null},{"id":"W6931027851","doi":"10.5281/zenodo.14233711","title":"Strategies of the Principal in Establishing Partnerships with Stakeholders at SMK Negeri 1 Simpang Kanan in 2023","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies","funders":"","keywords":"Internship; Principal (computer security); Work (physics); Qualitative research; Data collection","score_opus":0.13942321416138787,"score_gpt":0.32131755364104747,"score_spread":0.1818943394796596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931027851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68710953,0.000104725645,0.00003957925,0.0015788247,0.00010488552,0.00040909537,0.00002274903,0.0001742752,0.31045637],"genre_scores_gemma":[0.99778074,0.00005074178,0.000021705493,0.000016306782,0.000056035893,6.1794566e-8,0.00004216938,0.00020179233,0.0018304745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834543,0.0004127502,0.00018088071,0.00023524513,0.00050503993,0.0003206789],"domain_scores_gemma":[0.9995544,0.00005889613,0.000052100575,0.00017659359,0.0000959589,0.00006203131],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011573792,0.00008282207,0.00010078124,0.00017387218,0.00077269564,0.00097281655,0.00070516544,0.000043620013,0.002358672],"category_scores_gemma":[0.00021421177,0.000066000895,0.000029060655,0.0013394867,0.00028223617,0.00053808367,0.00047783452,0.00023525771,0.00020869766],"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":[0.00040475695,0.00060318597,0.021016276,0.000627834,0.0001971561,0.0002249589,0.33950785,0.0025599988,0.006067857,0.47763404,0.10314904,0.048007045],"study_design_scores_gemma":[0.00047106188,0.00009491073,0.03751203,0.00022579587,0.000011622241,0.0000037440418,0.09439929,0.00034299528,0.00009063826,0.00031784247,0.86635077,0.0001792805],"about_ca_topic_score_codex":0.00044631644,"about_ca_topic_score_gemma":0.0007636305,"teacher_disagreement_score":0.7632018,"about_ca_system_score_codex":0.00027136004,"about_ca_system_score_gemma":0.000026982802,"threshold_uncertainty_score":0.99855334},"labels":[],"label_agreement":null},{"id":"W6939359645","doi":"10.6084/m9.figshare.22615813.v1","title":"Additional file 1 of Introducing ACTFAiREST2 to implement online assessments amid COVID–19: a case study from a low resource setting","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Resource (disambiguation); Key (lock); Government (linguistics); Data collection","score_opus":0.09088905368708154,"score_gpt":0.42840310566075385,"score_spread":0.3375140519736723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939359645","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02391502,0.000003174535,3.6573002e-7,0.00050403783,0.00004362959,0.0007388319,0.9734519,0.00016136351,0.0011816577],"genre_scores_gemma":[0.056905303,3.009305e-7,0.0006839664,0.000404948,0.0008141888,0.001103161,0.93870866,0.000022237109,0.0013572194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99773806,0.00023116164,0.00033738438,0.00044153765,0.00083540054,0.0004164321],"domain_scores_gemma":[0.99604744,0.003062815,0.00020019268,0.00026127204,0.00013405048,0.00029421214],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023397256,0.0001532942,0.00021568811,0.00015968407,0.0005795799,0.00012215984,0.00037935335,0.00005895301,0.9767384],"category_scores_gemma":[0.006533983,0.00016331216,0.00008069125,0.00084134925,0.000011380891,0.00015323129,0.00045611634,0.00015305087,0.0011999991],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000089574905,0.00020508637,0.00048800165,0.000019305518,0.00005272684,0.0004431942,0.009927672,0.000024478206,0.0000044411904,0.0000011174712,0.9868288,0.0019962068],"study_design_scores_gemma":[0.00034902754,0.00011239457,0.013539324,0.00049584603,0.000013148764,0.0000032182338,0.124751166,0.0001287607,0.0000022541103,0.000011574491,0.8604028,0.00019043796],"about_ca_topic_score_codex":0.001681746,"about_ca_topic_score_gemma":0.0087396335,"teacher_disagreement_score":0.9755384,"about_ca_system_score_codex":0.00023736079,"about_ca_system_score_gemma":0.0005028104,"threshold_uncertainty_score":0.9995777},"labels":[],"label_agreement":null},{"id":"W6939399316","doi":"10.6084/m9.figshare.26758069.v1","title":"Additional file 1 of Rethinking assessment strategies to improve authentic representations of learning: using blogs as a creative assessment alternative to develop professional skills","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Online assessment; Creativity; Qualitative research; The Internet","score_opus":0.05138699011387045,"score_gpt":0.4314784504174476,"score_spread":0.38009146030357716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939399316","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036277052,0.000010912401,0.00010081771,0.00031215532,0.0002590153,0.0009988043,0.9248342,0.00008154521,0.069774844],"genre_scores_gemma":[0.35474446,0.000002607754,0.043963764,0.00014549895,0.0006517622,0.0033744301,0.5616635,0.00006511474,0.035388842],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99760365,0.00026339202,0.0003894071,0.00040016734,0.0010546519,0.00028869984],"domain_scores_gemma":[0.99602485,0.0026051642,0.0002461656,0.00012646397,0.0008646775,0.00013271114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022465293,0.00016665897,0.00024513254,0.00023850412,0.0003683266,0.00019856992,0.00032344687,0.000092178336,0.9085435],"category_scores_gemma":[0.0030499,0.0001598018,0.000095645664,0.001030192,0.000044192184,0.00042034296,0.0002916193,0.00029262784,0.0002731799],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008691771,0.00015420244,0.00009188964,0.00010294841,0.00018055637,0.000013643604,0.0438808,0.00031619647,0.00032304716,0.0040685786,0.9501371,0.0007223495],"study_design_scores_gemma":[0.00060947554,0.0008316718,0.08827226,0.02922562,0.00014724398,0.000004146764,0.22033529,0.004432637,0.0008974803,0.011027319,0.6430245,0.0011923751],"about_ca_topic_score_codex":0.0002209693,"about_ca_topic_score_gemma":0.00012481467,"teacher_disagreement_score":0.90827036,"about_ca_system_score_codex":0.0003245394,"about_ca_system_score_gemma":0.0034060935,"threshold_uncertainty_score":0.6516528},"labels":[],"label_agreement":null},{"id":"W6966793858","doi":"10.48550/arxiv.astro-ph/0301378","title":"The initial Helium content of Galactic Globular Cluster stars from the R-parameter: comparison with the CMB constraint","year":2003,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Globular cluster; Cosmic microwave background; Metallicity; Stars; Big Bang nucleosynthesis; Nucleosynthesis; Helium; Equation of state; Constraint (computer-aided design)","score_opus":0.08819173292958332,"score_gpt":0.35891130730223664,"score_spread":0.2707195743726533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6966793858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84412086,0.0014593708,0.0034783646,0.04179373,0.0030221145,0.0039006157,0.00008837393,0.000093778726,0.10204279],"genre_scores_gemma":[0.99656194,0.00024482465,0.00045457264,0.001249038,0.0003094325,0.000083009625,0.000019083982,0.00001884677,0.0010592465],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99597144,0.0012827582,0.00055202795,0.00041251536,0.0012948267,0.0004864089],"domain_scores_gemma":[0.99522996,0.0031042495,0.00060700934,0.00066279003,0.00030793,0.000088046676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018465618,0.00033143166,0.00049697247,0.00002107181,0.0009902586,0.0006328885,0.0013791667,0.00023345649,0.0004856847],"category_scores_gemma":[0.0002140678,0.00013674964,0.00024557643,0.00015452037,0.0023483287,0.00007423624,0.00046915535,0.0008658239,0.000025642481],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021594032,0.0014960038,0.58611125,0.00010035258,0.006959189,0.000026690008,0.17562719,0.00069716154,0.0002524911,0.076170295,0.13792716,0.012472813],"study_design_scores_gemma":[0.0037872463,0.0005904824,0.19556329,0.00042495856,0.0017171936,0.0000035911528,0.6726084,0.0011910462,0.0004678035,0.0046226676,0.11742753,0.0015958457],"about_ca_topic_score_codex":0.0129656475,"about_ca_topic_score_gemma":0.019905508,"teacher_disagreement_score":0.49698117,"about_ca_system_score_codex":0.00014509595,"about_ca_system_score_gemma":0.0005601819,"threshold_uncertainty_score":0.9979787},"labels":[],"label_agreement":null},{"id":"W6967454824","doi":"10.5281/zenodo.11196292","title":"HOLISTIC APPROACHES TO ASSESSMENT: BRIDGING GAPS IN TEACHING AND LEARNING","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Bridging (networking); Variety (cybernetics); Process (computing); Quality (philosophy); Promotion (chess); Holistic education; Cognition","score_opus":0.1268015008519633,"score_gpt":0.34620474149193614,"score_spread":0.21940324063997285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6967454824","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23821577,0.00023871684,0.0064001777,0.004320259,0.0001905909,0.00053594704,0.000012724165,0.0010353128,0.7490505],"genre_scores_gemma":[0.9960638,0.00005802969,0.0006475335,0.00005385452,0.00020855585,6.391204e-8,0.00007958184,0.0003331402,0.0025554362],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806416,0.000793181,0.00014171866,0.00032705808,0.00035163877,0.00032223767],"domain_scores_gemma":[0.99961567,0.00008304259,0.000024366822,0.00009911363,0.000045066896,0.00013273286],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027441615,0.00008593077,0.000097002085,0.00029007008,0.0030167107,0.002086308,0.00037782843,0.000038467977,0.0012935766],"category_scores_gemma":[0.0007050029,0.00009449926,0.000022100925,0.00051029155,0.0001001854,0.0003241991,0.0005415582,0.0005723176,0.0007951187],"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":[0.00001882792,0.000107115324,0.0005643729,0.0001335352,0.000043460037,0.000043888176,0.09251036,0.00022494454,0.0008967941,0.23043217,0.02234692,0.6526776],"study_design_scores_gemma":[0.00014675589,0.00006433388,0.007066825,0.00008987077,0.000008687249,0.0000066349153,0.011923171,0.0022948242,0.0000035027815,0.00028560896,0.9779611,0.0001486493],"about_ca_topic_score_codex":0.00017768986,"about_ca_topic_score_gemma":0.000005322212,"teacher_disagreement_score":0.9556142,"about_ca_system_score_codex":0.00020289388,"about_ca_system_score_gemma":0.000007065314,"threshold_uncertainty_score":0.9999829},"labels":[],"label_agreement":null},{"id":"W6976950042","doi":"10.6084/m9.figshare.26758069","title":"Additional file 1 of Rethinking assessment strategies to improve authentic representations of learning: using blogs as a creative assessment alternative to develop professional skills","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Online assessment; Creativity; Qualitative research; The Internet","score_opus":0.05138699011387045,"score_gpt":0.4314784504174476,"score_spread":0.38009146030357716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976950042","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036277052,0.000010912401,0.00010081771,0.00031215532,0.0002590153,0.0009988043,0.9248342,0.00008154521,0.069774844],"genre_scores_gemma":[0.35474446,0.000002607754,0.043963764,0.00014549895,0.0006517622,0.0033744301,0.5616635,0.00006511474,0.035388842],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99760365,0.00026339202,0.0003894071,0.00040016734,0.0010546519,0.00028869984],"domain_scores_gemma":[0.99602485,0.0026051642,0.0002461656,0.00012646397,0.0008646775,0.00013271114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022465293,0.00016665897,0.00024513254,0.00023850412,0.0003683266,0.00019856992,0.00032344687,0.000092178336,0.9085435],"category_scores_gemma":[0.0030499,0.0001598018,0.000095645664,0.001030192,0.000044192184,0.00042034296,0.0002916193,0.00029262784,0.0002731799],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008691771,0.00015420244,0.00009188964,0.00010294841,0.00018055637,0.000013643604,0.0438808,0.00031619647,0.00032304716,0.0040685786,0.9501371,0.0007223495],"study_design_scores_gemma":[0.00060947554,0.0008316718,0.08827226,0.02922562,0.00014724398,0.000004146764,0.22033529,0.004432637,0.0008974803,0.011027319,0.6430245,0.0011923751],"about_ca_topic_score_codex":0.0002209693,"about_ca_topic_score_gemma":0.00012481467,"teacher_disagreement_score":0.90827036,"about_ca_system_score_codex":0.0003245394,"about_ca_system_score_gemma":0.0034060935,"threshold_uncertainty_score":0.6516528},"labels":[],"label_agreement":null},{"id":"W6977076320","doi":"10.6084/m9.figshare.26720376","title":"Additional file 3 of Protocol for a scoping review study on learning plan use in undergraduate medical education","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Protocol (science); Plan (archaeology); Data collection; Protocol analysis; MEDLINE; Data extraction","score_opus":0.1710229444398138,"score_gpt":0.48094805455268513,"score_spread":0.3099251101128713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977076320","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003543204,0.000053932974,2.3569076e-7,0.0006483341,0.000041697378,0.12776726,0.8614008,0.000067085755,0.010017142],"genre_scores_gemma":[0.0000959745,0.0000026856899,0.000054692777,0.00013595051,0.00016646092,0.7002484,0.297631,0.000007667841,0.0016571219],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990748,0.00010565024,0.00016610864,0.00014032314,0.00040846522,0.00010461065],"domain_scores_gemma":[0.9978719,0.0019279817,0.00005920224,0.00004401427,0.000056717858,0.000040198185],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013049782,0.00005336205,0.000099658435,0.000054096785,0.00008241298,0.000058713278,0.00010979946,0.000035477722,0.9521891],"category_scores_gemma":[0.009296213,0.000048307018,0.000039502753,0.000219133,0.0000064280675,0.000131336,0.000025307269,0.00010774583,0.000316717],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033917147,0.000120716635,0.000056838027,0.0014789072,0.0000046525643,0.0000013674413,0.00036163008,2.2445502e-7,1.3786752e-8,0.000041158008,0.9955387,0.0023924115],"study_design_scores_gemma":[0.00010086977,0.0000762371,0.0011174235,0.26628846,0.0000020301857,9.9554626e-8,0.0004252877,0.000024200908,1.0755374e-7,0.000026052037,0.73188734,0.000051905532],"about_ca_topic_score_codex":0.000017712182,"about_ca_topic_score_gemma":0.0005527369,"teacher_disagreement_score":0.9518724,"about_ca_system_score_codex":0.000048909453,"about_ca_system_score_gemma":0.0012470753,"threshold_uncertainty_score":0.9990489},"labels":[],"label_agreement":null},{"id":"W6977109243","doi":"10.6084/m9.figshare.26586285.v1","title":"Additional file 1 of Breastfeeding support provided by lactation consultants in high-income countries for improved breastfeeding rates, self-efficacy, and infant growth: a systematic review and meta-analysis protocol","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Toronto Western Hospital; University of Toronto","funders":"","keywords":"Breastfeeding; Protocol (science); MEDLINE; Breast feeding; Lactation","score_opus":0.029451509741930854,"score_gpt":0.33811026254807486,"score_spread":0.308658752806144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977109243","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003918095,0.00069022505,6.343529e-7,0.0008066939,0.000005714314,0.036304872,0.961919,0.0000611757,0.00020776236],"genre_scores_gemma":[0.015729308,0.000042774696,0.0005290582,0.00021897061,0.000067326175,0.5376037,0.44473258,0.00003292571,0.0010433997],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984894,0.000110539324,0.0005430164,0.0003144524,0.0003198749,0.0002227141],"domain_scores_gemma":[0.99607885,0.0030192395,0.0003276876,0.000076422766,0.00042226719,0.00007552478],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003971698,0.00017468457,0.0009101825,0.00016553109,0.00014577586,0.0002533028,0.00013389463,0.000079835576,0.5359458],"category_scores_gemma":[0.003452345,0.00013834765,0.00014220683,0.00084420294,0.00002680542,0.00045593266,0.000055715504,0.000081329585,0.000022270768],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012322185,0.00004130281,0.000024648503,0.091055326,0.005496762,0.0000017262821,0.00068945263,4.2677378e-8,0.0000030656279,0.00011334493,0.9025499,0.0000121090425],"study_design_scores_gemma":[0.0073279794,0.001071055,0.026613316,0.23812702,0.3552651,0.000044956443,0.004349466,0.004352674,0.00010669285,0.0004744901,0.3583474,0.003919836],"about_ca_topic_score_codex":0.00008996346,"about_ca_topic_score_gemma":0.00017921228,"teacher_disagreement_score":0.5442025,"about_ca_system_score_codex":0.00006886835,"about_ca_system_score_gemma":0.0002625168,"threshold_uncertainty_score":0.56416535},"labels":[],"label_agreement":null},{"id":"W6980799941","doi":"","title":"Credit repair for survivors of modern slavery and human trafficking","year":2022,"lang":"en","type":"other","venue":"UNU Collections (United Nations University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human trafficking; Financial sector; Credit crunch; Debt; Government (linguistics)","score_opus":0.025212338900149414,"score_gpt":0.2777655466348463,"score_spread":0.2525532077346969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980799941","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00069777033,0.000047725556,0.00071151793,0.0001182459,0.00030363695,0.00068078324,0.00020683614,0.00034619495,0.99688727],"genre_scores_gemma":[0.0032386624,0.0002613309,0.0007751923,0.000007446351,0.00012131868,0.00000950357,0.00017631057,0.000062927145,0.9953473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990411,0.00016257426,0.00011412329,0.00024377636,0.00026994728,0.00016848608],"domain_scores_gemma":[0.9991763,0.0002791002,0.0001843511,0.00014310985,0.0001591746,0.000057923633],"candidate_categories":["bibliometrics","sts","insufficient_payload"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.00019759951,0.00012249623,0.00018695979,0.15456028,0.0029318377,0.000038452912,0.00022547111,0.0001780039,0.0020777513],"category_scores_gemma":[0.00007133497,0.00017239385,0.00014203998,0.10124493,0.00020165446,0.00010208452,0.00007401569,0.0001494196,8.773423e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009301294,0.00013024035,0.0006399202,0.000023372762,0.00022214268,0.0000019972956,0.0033819124,0.00005146275,0.000005181619,0.7786818,0.21679479,0.000057844383],"study_design_scores_gemma":[0.00046521195,0.00005810912,0.000020874786,0.00002038365,0.00016461952,2.3288906e-7,0.010410651,0.0001696419,3.6655857e-7,0.00020546935,0.9883208,0.00016359153],"about_ca_topic_score_codex":0.0014201613,"about_ca_topic_score_gemma":0.027273446,"teacher_disagreement_score":0.77847636,"about_ca_system_score_codex":0.0002579509,"about_ca_system_score_gemma":0.00021564902,"threshold_uncertainty_score":0.9988345},"labels":[],"label_agreement":null},{"id":"W6981475138","doi":"","title":"El marketing digital y los emprendimientos en el sector de artesanías en la región Tacna, Perú","year":2024,"lang":"en","type":"article","venue":"Dialnet (Universidad de la Rioja)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Craft; Purchasing; The Internet; E-commerce; Clothing","score_opus":0.00982829444486833,"score_gpt":0.3061886526824386,"score_spread":0.2963603582375703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981475138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6146392,0.00022295032,0.00025328482,0.00095493044,0.0003752404,0.00020593841,0.000045566896,0.00028318496,0.3830197],"genre_scores_gemma":[0.98144156,0.00021750221,0.0003025441,0.000084819156,0.0008704091,0.000009603449,0.000028790379,0.000039244922,0.017005514],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973303,0.0008522212,0.00015592221,0.00043430933,0.0005690476,0.0006581918],"domain_scores_gemma":[0.9971955,0.0022306899,0.000069706584,0.00020293264,0.00004387371,0.00025733138],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016665517,0.00022355537,0.00022361333,0.00027469924,0.00042455093,0.00093131844,0.0005758983,0.00031340888,0.0009556487],"category_scores_gemma":[0.00036264566,0.0002514989,0.00021363824,0.0006319423,0.00029291474,0.0008604705,0.00018468511,0.00042073027,0.00018372829],"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":[0.00029518906,0.00045833146,0.37063736,0.00023122199,0.0007306863,0.0020697801,0.27364075,0.00005027664,0.0026150204,0.19397928,0.10493815,0.05035395],"study_design_scores_gemma":[0.0009814405,0.00007769691,0.33717903,0.0002577388,0.00017922104,0.000024082736,0.053580314,0.0009750284,0.00003917509,0.0034500062,0.60249037,0.00076588494],"about_ca_topic_score_codex":0.00061060075,"about_ca_topic_score_gemma":0.0003460777,"teacher_disagreement_score":0.49755222,"about_ca_system_score_codex":0.0005667138,"about_ca_system_score_gemma":0.0004729667,"threshold_uncertainty_score":0.99999374},"labels":[],"label_agreement":null},{"id":"W6981765487","doi":"","title":"FAIRNESS IN CLASSROOM ASSESSMENT: CONCEPTUAL AND EMPIRICAL INVESTIGATIONS","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Work (physics); Reliability (semiconductor); Quality (philosophy); Subconscious; Limiting","score_opus":0.020941052767542188,"score_gpt":0.29154497184692624,"score_spread":0.270603919079384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981765487","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69520634,0.00007779761,0.000026485624,0.048028164,0.00067759614,0.0005616908,0.000043574604,0.00022589884,0.25515246],"genre_scores_gemma":[0.46860933,0.0013577031,0.002128575,0.00026751476,0.00023860823,0.000004731421,0.00161044,0.000048258204,0.52573484],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997738,0.00052595173,0.00019551604,0.00057645846,0.0005514551,0.00041260902],"domain_scores_gemma":[0.9989769,0.0002761558,0.00018841914,0.00020329743,0.00007877552,0.00027645164],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010399971,0.00028075013,0.00041691816,0.00037786303,0.0005725574,0.0002734511,0.00044668932,0.0005364818,0.0008808192],"category_scores_gemma":[0.000056530138,0.00035553836,0.000116947725,0.0010845349,0.0004384647,0.0015150082,0.00016010145,0.00064486434,0.000016270365],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004714369,0.0001773124,0.7289766,0.00006722861,0.00009896563,0.0002208636,0.045416657,0.000003846308,0.000003874074,0.10942342,0.11529072,0.00027337833],"study_design_scores_gemma":[0.0007243318,0.000041809686,0.36401084,0.00019285754,0.00009312317,5.4761873e-8,0.33652616,0.0000034322004,0.000028611987,0.0011996307,0.29662615,0.0005529774],"about_ca_topic_score_codex":0.008298894,"about_ca_topic_score_gemma":0.008179134,"teacher_disagreement_score":0.36496574,"about_ca_system_score_codex":0.00022849896,"about_ca_system_score_gemma":0.00189503,"threshold_uncertainty_score":0.9998897},"labels":[],"label_agreement":null},{"id":"W6991109319","doi":"","title":"Exploring K–12 Teachers’ Assessment Literacy and Self-efficacy in China","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Literacy; China; Educational assessment; Quantitative assessment; Professional development; Adult literacy","score_opus":0.3368514475856944,"score_gpt":0.5943787217653435,"score_spread":0.25752727417964905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991109319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9461093,0.010738304,0.00004873909,0.00080908835,0.001165459,0.00057712087,0.0000056369345,0.000113498376,0.040432878],"genre_scores_gemma":[0.96187973,0.036299247,0.00046392187,0.000064044114,0.00043559461,0.00007160449,0.0000039061883,0.000038295857,0.00074366614],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968105,0.0004897011,0.00067684916,0.00051573676,0.0009870796,0.0005201431],"domain_scores_gemma":[0.99860543,0.000551841,0.0002510433,0.00024812264,0.00007094471,0.00027260958],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031105846,0.00027963432,0.00054700545,0.0008822362,0.0004402829,0.004996918,0.0016933949,0.00009283431,0.003672066],"category_scores_gemma":[0.00014187791,0.00025996534,0.0001444194,0.0013210778,0.0001422952,0.007185109,0.0007711173,0.0006216439,0.000015159345],"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":[0.000023307603,0.00081429834,0.8670411,0.00007865277,0.00021092537,0.000104468345,0.04552465,0.000015901629,0.0015929716,0.002359654,0.00481792,0.07741616],"study_design_scores_gemma":[0.0003904727,0.000008886423,0.946808,0.0005549043,0.000057401998,0.0000018458975,0.0016140847,0.00008242787,0.000106581894,0.0017727426,0.048281286,0.0003213876],"about_ca_topic_score_codex":0.0031151224,"about_ca_topic_score_gemma":0.00028721936,"teacher_disagreement_score":0.079766884,"about_ca_system_score_codex":0.00032748657,"about_ca_system_score_gemma":0.0003003333,"threshold_uncertainty_score":0.9999853},"labels":[],"label_agreement":null},{"id":"W6991573789","doi":"","title":"Grade Scaling: Issues and Approaches","year":2003,"lang":"en","type":"article","venue":"Carleton University's Institutional Repository (MacOdrum Library, Carleton University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Context (archaeology); Set (abstract data type); Class (philosophy); Test (biology); Axiom; Scaling","score_opus":0.03188456343583341,"score_gpt":0.2327190848528795,"score_spread":0.2008345214170461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991573789","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31716657,0.000534478,0.00026467067,0.0010950046,0.00093343004,0.00035995615,0.000021642212,0.00034186736,0.67928237],"genre_scores_gemma":[0.86550504,0.00087560236,0.001120374,0.00013001903,0.0003363711,4.1897945e-7,0.000033213804,0.000024360994,0.1319746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970821,0.0006351276,0.00021049427,0.0007554731,0.00072400935,0.0005927642],"domain_scores_gemma":[0.99872756,0.0001603556,0.0001722425,0.00031376848,0.000100138444,0.0005259379],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00024433946,0.00034807657,0.000356811,0.0006504324,0.0031519718,0.00026912888,0.0007364249,0.000342163,0.00017531856],"category_scores_gemma":[0.000047235197,0.00043912735,0.0002356707,0.0011585563,0.0017041916,0.0026436464,0.0002877672,0.00037172934,0.000021195307],"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":[0.00009974253,0.00015687734,0.050867137,0.0000310947,0.00016148435,0.00092754426,0.0026642075,0.00012943854,0.000393575,0.9405581,0.0036291513,0.0003816497],"study_design_scores_gemma":[0.0011581461,0.000051763305,0.006352865,0.000051294795,0.00015516157,0.000027468623,0.02529923,0.00003838869,0.0009563254,0.00025790685,0.96508735,0.0005640656],"about_ca_topic_score_codex":0.000617219,"about_ca_topic_score_gemma":0.00006125281,"teacher_disagreement_score":0.9614582,"about_ca_system_score_codex":0.00052165316,"about_ca_system_score_gemma":0.00108858,"threshold_uncertainty_score":0.99980605},"labels":[],"label_agreement":null},{"id":"W6991650725","doi":"","title":"Impacts of pre/post examination metacognition prompts on study strategies and predicting grades","year":2023,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metacognition; Cognition; Class (philosophy); Inclusion (mineral); Academic achievement; Qualitative property","score_opus":0.13614975146700337,"score_gpt":0.3905274174875319,"score_spread":0.2543776660205285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991650725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9980038,0.000013313253,0.000010692601,0.000088411914,0.00012686836,0.0007590281,0.0000129997015,0.00021041452,0.0007744809],"genre_scores_gemma":[0.9989317,0.000058889214,0.000005751562,0.00001451577,0.000074401854,0.0000027496303,0.0000211019,0.000015913987,0.0008749616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99785775,0.0005951596,0.00019751549,0.00035623542,0.00066418387,0.00032913327],"domain_scores_gemma":[0.99905807,0.00023858585,0.00020778221,0.00016287978,0.00020309616,0.00012957913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011425988,0.00017595383,0.00022314097,0.00043097296,0.0005013032,0.00042504925,0.0003232728,0.00011130769,0.000010987009],"category_scores_gemma":[0.00011662978,0.00018920597,0.000055844055,0.0008294369,0.00016300139,0.002722559,0.00015936777,0.00022362963,0.00002504538],"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":[0.000056978006,0.00018879998,0.97734743,0.000037257993,0.00007415946,0.000034570217,0.02039476,0.000004402032,0.00079801626,0.0002564379,1.2546312e-7,0.0008070621],"study_design_scores_gemma":[0.00075466477,0.00044544355,0.8967558,0.00011015941,0.000101482045,5.5337733e-7,0.10127191,3.9433652e-7,0.00030096277,0.00008091909,0.000019355666,0.00015833006],"about_ca_topic_score_codex":0.00008539341,"about_ca_topic_score_gemma":0.008138041,"teacher_disagreement_score":0.08087715,"about_ca_system_score_codex":0.00009730887,"about_ca_system_score_gemma":0.000095376214,"threshold_uncertainty_score":0.77155954},"labels":[],"label_agreement":null},{"id":"W6992297165","doi":"","title":"La motivation scolaire des élèves du secondaire est-elle plus élevée lorsque ces derniers participent à un programme particulier de plein air?","year":2023,"lang":"fr","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); General interest; Decorum","score_opus":0.036960269624157195,"score_gpt":0.3020176555506169,"score_spread":0.26505738592645967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6992297165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7770102,0.00054505456,0.0007102852,0.003342219,0.0010883734,0.0016615626,0.000011988532,0.001202789,0.2144275],"genre_scores_gemma":[0.8868557,0.0007309991,0.00092525186,0.0002249773,0.00077672966,0.00042088624,0.000020002693,0.0003750576,0.10967038],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99531233,0.0008324153,0.0006393459,0.0008203954,0.00088041346,0.0015151037],"domain_scores_gemma":[0.99787366,0.00073721353,0.00039655587,0.00031609423,0.00014656395,0.0005299191],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014786688,0.000644075,0.00066396064,0.0001543768,0.0009384099,0.00040876342,0.0006295651,0.0007482645,0.013015388],"category_scores_gemma":[0.00050866435,0.00057803735,0.00035462444,0.0009849286,0.0016994425,0.00047965607,0.00024204158,0.00045629154,0.000928854],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055017328,0.000781627,0.68318623,0.0003410028,0.000876293,0.00010111723,0.15412007,0.0005293184,0.000025659669,0.046381813,0.010497094,0.10310474],"study_design_scores_gemma":[0.001792351,0.00027518446,0.60315067,0.0007912095,0.00054003025,0.000005104492,0.14014712,0.002018564,0.0003744041,0.0024835062,0.2469629,0.001458938],"about_ca_topic_score_codex":0.0048549324,"about_ca_topic_score_gemma":0.044716407,"teacher_disagreement_score":0.23646581,"about_ca_system_score_codex":0.001113994,"about_ca_system_score_gemma":0.00080559764,"threshold_uncertainty_score":0.999849},"labels":[],"label_agreement":null},{"id":"W6995956337","doi":"","title":"Public knowledge and perceptions of large-scale assessments","year":2016,"lang":"en","type":"article","venue":"IslandScholar (University of Prince Edward Island)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Center for Makroøkologi, Evolution og Klima","keywords":"Nucleofection; Gestational period; Diafiltration; TSG101; Articular cartilage damage; Hyporeflexia; Dysgeusia; Tubulopathy","score_opus":0.022389491914067885,"score_gpt":0.3044506025167043,"score_spread":0.28206111060263644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6995956337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9095172,0.00009335455,0.0064200275,0.0009914247,0.00016986352,0.00017401615,0.00006680532,0.00003915651,0.08252814],"genre_scores_gemma":[0.98856705,0.00088080147,0.0011987084,0.000008541685,0.00006871046,3.8421385e-7,0.000005401884,0.0000066858124,0.009263706],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987961,0.00018925166,0.00012949918,0.00024776568,0.00034791935,0.00028944874],"domain_scores_gemma":[0.999178,0.0001196175,0.0001411496,0.00020490082,0.00022780879,0.00012850422],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007679031,0.000102907274,0.000233089,0.00015989592,0.00047934212,0.000030878742,0.00040369423,0.000118163414,0.0012203365],"category_scores_gemma":[0.000054930653,0.000093981034,0.000094661074,0.00026431752,0.00034349333,0.0008258855,0.00022923615,0.000109891625,0.00005448315],"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":[0.000029932604,0.00023271011,0.9630925,0.000021493046,0.00006340666,0.0000023170228,0.018968653,4.7053383e-8,0.0013274926,0.00770933,0.0023573097,0.0061948043],"study_design_scores_gemma":[0.0022968748,0.00012245403,0.8148922,0.000092956856,0.000065270055,8.5986045e-7,0.032995712,0.000015981444,0.0000276422,0.0006910002,0.14856297,0.00023608224],"about_ca_topic_score_codex":0.00014656903,"about_ca_topic_score_gemma":0.007265211,"teacher_disagreement_score":0.1482003,"about_ca_system_score_codex":0.000064600164,"about_ca_system_score_gemma":0.00016860505,"threshold_uncertainty_score":0.9996927},"labels":[],"label_agreement":null},{"id":"W6996631828","doi":"","title":"In the service of the stakeholder: a critical, mixed-method program of research in high-stakes language assessment","year":2011,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Certification; Stakeholder; Language assessment; Language proficiency; Perception; Task (project management); Service (business); Field (mathematics)","score_opus":0.10398658210226995,"score_gpt":0.4408162889804222,"score_spread":0.3368297068781522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996631828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.859044,0.00018220163,5.340868e-8,0.00030689477,0.00085377967,0.00204438,0.000225893,0.00004070364,0.13730206],"genre_scores_gemma":[0.99523574,0.00015460032,0.0019170075,0.00011911779,0.000060715152,0.0005270411,0.000082366336,0.00006385796,0.0018395556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98897976,0.005417051,0.0010635569,0.0007197907,0.0028610614,0.0009588076],"domain_scores_gemma":[0.9952474,0.002356965,0.0004844247,0.00091378874,0.0008768537,0.0001205716],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011232448,0.0004050455,0.00072044757,0.0005587314,0.0009149007,0.00012428974,0.0025386342,0.00065036555,0.00028558035],"category_scores_gemma":[0.0012679924,0.00029649562,0.00024281659,0.0033247415,0.00038766058,0.0005607139,0.0002217896,0.0023711892,0.00001750906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024591485,0.0037432073,0.0042466517,0.0015309092,0.00015053019,0.00007819207,0.008506314,0.000004610602,0.00755663,0.91350025,0.00003339251,0.060403388],"study_design_scores_gemma":[0.0031279207,0.0008293704,0.26951057,0.0038695158,0.00038999622,0.000004533245,0.565253,0.000017377024,0.02015358,0.10828816,0.026880188,0.0016757775],"about_ca_topic_score_codex":0.03347684,"about_ca_topic_score_gemma":0.12720181,"teacher_disagreement_score":0.8052121,"about_ca_system_score_codex":0.00043855005,"about_ca_system_score_gemma":0.0003613162,"threshold_uncertainty_score":0.99994874},"labels":[],"label_agreement":null},{"id":"W6996941080","doi":"","title":"A study of the reliability and validity of the standardized exams used in grade 10 science in a Winnipeg school division","year":2009,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Test (biology); Affect (linguistics); Statistical analysis; Quality (philosophy); Standardized test; Validity","score_opus":0.03187281653173227,"score_gpt":0.3007936059981488,"score_spread":0.2689207894664165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996941080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961154,0.000018281564,0.0000012192362,0.00031227022,0.00019379122,0.0010718651,0.000007018987,0.0000070346923,0.0022731586],"genre_scores_gemma":[0.99947673,0.00004155082,0.000029141922,0.0000022759116,0.000008266131,4.74642e-7,0.0000016119399,0.0000038432013,0.000436094],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973727,0.00059601426,0.00018436591,0.0003245536,0.0013229268,0.00019944823],"domain_scores_gemma":[0.99879295,0.00015161997,0.00044220962,0.0003748554,0.00019190885,0.000046462712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021820362,0.00012915532,0.00038369198,0.00020926258,0.00044401537,0.00002585522,0.0010355184,0.00013131484,0.000008419779],"category_scores_gemma":[0.00037678806,0.000107830405,0.000098785415,0.0014291877,0.0006624866,0.00027155096,0.00021568214,0.0002788189,4.908751e-7],"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":[0.000103144215,0.00044368967,0.97523373,0.000034229026,0.000006973583,0.0000012998985,0.023458028,0.000017211752,0.00037549628,0.00006317834,0.000053974396,0.0002090198],"study_design_scores_gemma":[0.0009284423,0.000093626484,0.72946584,0.00013764032,0.00003274459,1.8500376e-8,0.2689978,0.000010122398,0.00007324173,0.00014864317,0.000039743343,0.00007214502],"about_ca_topic_score_codex":0.0252908,"about_ca_topic_score_gemma":0.8224928,"teacher_disagreement_score":0.79720193,"about_ca_system_score_codex":0.00030720147,"about_ca_system_score_gemma":0.0005103564,"threshold_uncertainty_score":0.98119986},"labels":[],"label_agreement":null},{"id":"W7000495802","doi":"","title":"Frequent, low-stakes assessments: Balance and benefits","year":2025,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workload; Stakeholder; Isolation (microbiology); Perception; Online assessment; Balance (ability); Contradiction; Stakeholder engagement","score_opus":0.10167408059832438,"score_gpt":0.3821524828414491,"score_spread":0.2804784022431247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000495802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97911376,0.00034074622,0.00022672067,0.0007153443,0.00054175756,0.00035622888,0.000019254334,0.00018908233,0.018497134],"genre_scores_gemma":[0.96729326,0.0006256888,0.000065281,0.00051668566,0.00010403446,0.0000020047396,0.000011945293,0.000016554794,0.031364515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978427,0.00031404028,0.00021546072,0.000562665,0.0005022485,0.0005628829],"domain_scores_gemma":[0.9989535,0.00017257169,0.00014012546,0.00033415997,0.00017238871,0.00022723748],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005401061,0.0002577084,0.00030051163,0.0003983687,0.0008386382,0.00059030915,0.00080466503,0.00021968038,0.0000637868],"category_scores_gemma":[0.000054857854,0.00030263036,0.00009383678,0.0007808099,0.0003069924,0.0018352355,0.00032176852,0.0003754086,0.00007179005],"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":[0.000034719236,0.00008394567,0.9891314,0.000029752233,0.0000762061,0.00003743811,0.0008845588,0.0000024983653,0.00011254051,0.008534045,0.000006330478,0.001066554],"study_design_scores_gemma":[0.0009961308,0.000043891923,0.97817653,0.00025005382,0.00008125657,8.436799e-7,0.0033963278,2.2016738e-7,0.00015022831,0.00035145626,0.016236419,0.00031665695],"about_ca_topic_score_codex":0.000056919816,"about_ca_topic_score_gemma":0.0057389885,"teacher_disagreement_score":0.016230088,"about_ca_system_score_codex":0.00030849501,"about_ca_system_score_gemma":0.00023118731,"threshold_uncertainty_score":0.9999426},"labels":[],"label_agreement":null},{"id":"W7001130225","doi":"","title":"Intensive training and practice (ITaP): Impact and possibilities for primary trainee teachers and schools","year":2024,"lang":"en","type":"article","venue":"Edge Hill University Research Information Repository (Edge Hill University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Curriculum; Control (management); Focus (optics); Training (meteorology); Focus group","score_opus":0.06463478474217471,"score_gpt":0.3576662179976658,"score_spread":0.2930314332554911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001130225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7505565,0.00077115576,0.00079340686,0.0041028783,0.00049476157,0.0016331059,0.000098206285,0.0003029779,0.241247],"genre_scores_gemma":[0.9775367,0.0010383487,0.00066318066,0.00011480555,0.00021988119,0.0000013748875,0.00004605177,0.0000146527145,0.020365048],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9976611,0.00080464984,0.00019783777,0.00033751878,0.0005112242,0.00048763226],"domain_scores_gemma":[0.99630016,0.0019815967,0.00010473922,0.00015625902,0.0010355501,0.00042168755],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0027951957,0.00018130381,0.00023236276,0.0010146482,0.002056369,0.00069968146,0.00027262527,0.00021086818,0.0000131402185],"category_scores_gemma":[0.0013305916,0.00019836987,0.000098943354,0.0007699312,0.0010083488,0.0066009467,0.00027855916,0.0005712859,0.000006600685],"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":[0.0014232878,0.00010351252,0.01120213,0.0006204598,0.00081106735,0.00042823824,0.82047665,0.00001161393,0.0006878655,0.087608,0.02885263,0.04777454],"study_design_scores_gemma":[0.00087715354,0.00025441436,0.0075959624,0.00010391747,0.00008656366,0.000036755646,0.61669016,0.00032469459,0.000008379242,0.00016756722,0.37360817,0.00024628863],"about_ca_topic_score_codex":0.0007131376,"about_ca_topic_score_gemma":0.00006855001,"teacher_disagreement_score":0.34475553,"about_ca_system_score_codex":0.0010018571,"about_ca_system_score_gemma":0.0009033068,"threshold_uncertainty_score":0.99924284},"labels":[],"label_agreement":null},{"id":"W7006674247","doi":"","title":"Using \"assessment for learning\" practices with pre-university level students of English as a Second Language: a mixed methods study of teacher and student performance and beliefs","year":2011,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Class (philosophy); Control (management); Data collection; Exploratory research; Language acquisition; Action research; English language; Note-taking; Teaching method","score_opus":0.05408613286330487,"score_gpt":0.40666346692551686,"score_spread":0.352577334062212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006674247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751821,0.00012973054,8.907497e-7,9.166317e-7,0.00035503617,0.0020996118,0.000076865916,0.000044688146,0.022110129],"genre_scores_gemma":[0.9821974,0.00021899187,0.006883987,0.000004949582,0.00004102835,0.000044663255,0.00003834579,0.0000594952,0.01051115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99588484,0.0013075286,0.0005288032,0.00074926583,0.0011203237,0.00040923318],"domain_scores_gemma":[0.9961715,0.0004983207,0.0019316924,0.00028571492,0.0009343062,0.0001784716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003392711,0.00043318362,0.0007941664,0.00030849766,0.0012567808,0.00010497318,0.0006358404,0.00033656563,0.0000922589],"category_scores_gemma":[0.0007489643,0.00043129892,0.000096866555,0.00036630433,0.00015825474,0.0009980546,0.00027560038,0.0007689396,4.868597e-7],"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":[0.004346098,0.00955382,0.6708564,0.00305531,0.0060333195,0.000040090395,0.16016273,0.000023787512,0.009252233,0.009876767,0.0000040186906,0.12679541],"study_design_scores_gemma":[0.0037132143,0.002331598,0.5073218,0.0003615943,0.0012379204,0.0000012248622,0.479143,0.000009048557,0.0011782696,0.00006460986,0.0039830958,0.00065467274],"about_ca_topic_score_codex":0.003754647,"about_ca_topic_score_gemma":0.015993236,"teacher_disagreement_score":0.31898025,"about_ca_system_score_codex":0.00025612803,"about_ca_system_score_gemma":0.00015319748,"threshold_uncertainty_score":0.99981385},"labels":[],"label_agreement":null},{"id":"W7010134099","doi":"","title":"Gormley - Scott Aitchison - Thursday, May 12, 2022","year":2022,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Yesterday; Joins; Field (mathematics); Work (physics)","score_opus":0.00968297778947116,"score_gpt":0.2375199158444829,"score_spread":0.22783693805501173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7010134099","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034211742,0.0005344089,9.835636e-8,0.0005983019,0.0011723338,0.00072267227,0.00014036706,0.00029621855,0.9965014],"genre_scores_gemma":[0.00038871824,0.0012123579,0.00028740498,0.00037773603,0.00053092855,0.000044130113,0.0002700542,0.00013221471,0.99675643],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99704015,0.0002496685,0.0005902026,0.00027759987,0.0013336327,0.0005087463],"domain_scores_gemma":[0.99849516,0.00014879793,0.00071850256,0.00038788567,0.00008314377,0.00016652513],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006996932,0.0003559062,0.00047154192,0.000135853,0.00041087365,0.00012918942,0.00084111333,0.00040217146,0.9336138],"category_scores_gemma":[0.00012823743,0.00038143806,0.0002497983,0.000021743983,0.00028110464,4.722652e-7,0.0002530037,0.00046685868,0.014486329],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039296006,0.00006987983,0.00008994523,0.00010805105,0.00008133536,0.000012613006,0.0018041028,0.000015159008,8.523938e-8,0.00047795242,0.9958464,0.0014552119],"study_design_scores_gemma":[0.00045784912,0.0001031087,0.000039886716,0.000069492424,0.00006805429,0.000004874523,0.003245377,0.0000017792242,4.6669666e-7,0.000017588593,0.99557203,0.00041948896],"about_ca_topic_score_codex":0.029844394,"about_ca_topic_score_gemma":0.018350752,"teacher_disagreement_score":0.91912746,"about_ca_system_score_codex":0.00020316032,"about_ca_system_score_gemma":0.00012608767,"threshold_uncertainty_score":0.99986374},"labels":[],"label_agreement":null},{"id":"W7015669281","doi":"","title":"Thematic Working Group 5: Formative assessment supported by technology.","year":2023,"lang":"en","type":"article","venue":"IPIR – Repository of the Institute for Educational Research (Institute for Educational Research, Belgrade, Serbia)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universitetet i Oslo; University of Mumbai; Victoria University of Wellington; Tel Aviv University; Victoria University; Curtin University of Technology; Tata Trusts; Griffith University; University of North Texas; University of Wollongong; Al Akhawayn University in Ifrane; Itä-Suomen Yliopisto; Université de Sherbrooke; Vrije Universiteit Brussel; King's College London; Dublin City University; Universiteit van Amsterdam; Monash University; Université Laval; West Virginia University; University of Canterbury; Tata Institute of Social Sciences; Manchester Metropolitan University; University of Otago; Arizona State University; Nova Southeastern University; Kasetsart University","keywords":"Formative assessment; Summative assessment; Accountability; Thematic analysis; Focus group; Knowledge survey; Peer assessment; Work (physics); Educational assessment; Assessment for learning","score_opus":0.15973400638312366,"score_gpt":0.4819537601001392,"score_spread":0.3222197537170155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015669281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7363808,0.000821188,0.00035557654,0.20358542,0.011526601,0.01123031,0.00061444205,0.00016801,0.03531766],"genre_scores_gemma":[0.93930304,0.00026085204,0.00499275,0.000078515244,0.0022514812,0.0070222733,0.00145467,0.00006984486,0.04456656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906527,0.0006915917,0.0010634916,0.0009286921,0.0048662904,0.0017972328],"domain_scores_gemma":[0.9880676,0.00653733,0.00046155017,0.0009521666,0.0035234932,0.00045781187],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.009113919,0.0003668312,0.00049199944,0.0016692411,0.008698954,0.0005093889,0.003186412,0.00039009692,0.000109468325],"category_scores_gemma":[0.0072806394,0.00033001162,0.00044276332,0.005550095,0.005555905,0.0013107684,0.00058424176,0.0012090937,0.000072513925],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015586641,0.00160243,0.013106407,0.00046494804,0.00042094736,0.0000011248726,0.007331147,0.00013646416,0.008301412,0.6359785,0.33110082,0.0013999181],"study_design_scores_gemma":[0.0014519406,0.00041519324,0.02770042,0.0010058347,0.00008284427,0.000012250381,0.023391463,0.0003576801,0.0027098062,0.14128219,0.80092895,0.0006614414],"about_ca_topic_score_codex":0.0022592691,"about_ca_topic_score_gemma":0.0023877528,"teacher_disagreement_score":0.49469635,"about_ca_system_score_codex":0.0023391205,"about_ca_system_score_gemma":0.01245498,"threshold_uncertainty_score":0.9999152},"labels":[],"label_agreement":null},{"id":"W7017400211","doi":"","title":"Assessment for learning in a chinese university context: a mixed methods case study on english as a foreign language speaking ability","year":2012,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Perception; Foreign language; English as a foreign language; English language; Multimethodology; Qualitative research; Selection (genetic algorithm); China; Second language","score_opus":0.028748098564853525,"score_gpt":0.38507770390510826,"score_spread":0.3563296053402547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017400211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83482945,0.000059970713,0.0000019506078,0.0000049607524,0.00131134,0.0029591923,0.00011195989,0.00023757778,0.16048357],"genre_scores_gemma":[0.99388874,0.000016308291,0.0016628238,0.00003445162,0.00018029347,0.00016495114,0.00021256159,0.00010585534,0.0037340468],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9921728,0.0038961018,0.0007213159,0.001170867,0.0010243435,0.001014605],"domain_scores_gemma":[0.9954951,0.0023531513,0.0007160999,0.0005225829,0.0005455799,0.0003675313],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.008409334,0.0007152571,0.0010316215,0.0005735082,0.0025667364,0.0001801011,0.0007483515,0.00066479185,0.00024694856],"category_scores_gemma":[0.0038459417,0.00075887796,0.0004844541,0.0010253441,0.00009206352,0.00097283995,0.00017521509,0.0018857382,0.000021980404],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019423286,0.0067304494,0.13086642,0.00059170276,0.0013059278,0.003314236,0.05658976,0.000038918617,0.0035836399,0.15968737,0.0000042212555,0.63534504],"study_design_scores_gemma":[0.003856548,0.0006994588,0.10643011,0.00021838918,0.0004218879,0.000010270512,0.8725071,0.000018768289,0.00017792538,0.0017415877,0.012693729,0.0012242271],"about_ca_topic_score_codex":0.019626593,"about_ca_topic_score_gemma":0.13222279,"teacher_disagreement_score":0.8159173,"about_ca_system_score_codex":0.0023461573,"about_ca_system_score_gemma":0.00022166589,"threshold_uncertainty_score":0.9994862},"labels":[],"label_agreement":null},{"id":"W7018513866","doi":"","title":"Does self-assessment with specific criteria enhance graduate level ESL students' writing?","year":2007,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Control (management); English as a second language; Graduate students; Qualitative research; Second language; Language proficiency; Note-taking","score_opus":0.039696675660746555,"score_gpt":0.3751141077246522,"score_spread":0.3354174320639056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018513866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.796476,0.00013004965,0.0000018123405,0.00006115337,0.003941431,0.0016036985,0.0004030512,0.0006002862,0.1967825],"genre_scores_gemma":[0.9607446,0.0017415207,0.005782857,0.00025455866,0.0006002411,0.00028777076,0.0006896867,0.00028871425,0.029610049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98887014,0.00082042115,0.0014371111,0.0020073631,0.004993371,0.0018715706],"domain_scores_gemma":[0.9954518,0.0005115633,0.0012047028,0.0009644658,0.0011920178,0.0006754584],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0042505367,0.0012880736,0.00124079,0.0006195357,0.004226718,0.0010730646,0.0023628175,0.0009724305,0.0011702735],"category_scores_gemma":[0.00012831358,0.0010362442,0.0004481382,0.0013217618,0.00023428952,0.0014617939,0.00025935363,0.0022492753,0.0003915878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032279515,0.010987321,0.043086167,0.0024603498,0.006198724,0.0022121114,0.0069318702,0.00000794597,0.041432932,0.50390106,0.0008380643,0.3787155],"study_design_scores_gemma":[0.0064141224,0.0012080892,0.39399812,0.0034131429,0.0016264506,0.000015450549,0.08174358,0.0000049693767,0.028283926,0.01695392,0.4571663,0.00917194],"about_ca_topic_score_codex":0.0012828506,"about_ca_topic_score_gemma":0.012305417,"teacher_disagreement_score":0.48694715,"about_ca_system_score_codex":0.0023777096,"about_ca_system_score_gemma":0.0003145363,"threshold_uncertainty_score":0.9999871},"labels":[],"label_agreement":null},{"id":"W7018553199","doi":"","title":"Dineren onder vrienden (en rivalen). Literaire prijzen, netwerken en consecratiestrategieën","year":2008,"lang":"nl","type":"article","venue":"Open Repository and Bibliography (University of Liège)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Francophone University Association","funders":"","keywords":"Government (linguistics); Set (abstract data type); Identification (biology); Context (archaeology); Perspective (graphical)","score_opus":0.028881407520693146,"score_gpt":0.2748239915696272,"score_spread":0.24594258404893407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018553199","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8102336,0.0015416763,0.00003759649,0.0012201404,0.0005672259,0.0007456832,0.000050258055,0.000052120038,0.1855517],"genre_scores_gemma":[0.9538516,0.016326906,0.00063615764,0.000056358032,0.00027029103,5.660738e-7,0.000019214322,0.000016190783,0.028822728],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996871,0.0008493372,0.00034765835,0.0006938764,0.0007386972,0.0004994077],"domain_scores_gemma":[0.9981743,0.00035176848,0.00044507906,0.0004112141,0.00026608456,0.0003515556],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0007239593,0.0003550036,0.0006266143,0.003323812,0.0022917532,0.00050992524,0.001518507,0.00041402777,0.00063482294],"category_scores_gemma":[9.85018e-7,0.0003975022,0.00035437456,0.0088365525,0.0016858802,0.0021641618,0.00084792095,0.00037298558,0.000028588865],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023100406,0.0003061451,0.89109844,0.00007475509,0.00050888816,0.00025803907,0.038700227,0.0000016475601,0.00046580718,0.0014789056,0.066808455,0.000067686655],"study_design_scores_gemma":[0.0016101013,0.00047037491,0.9191742,0.00018126388,0.00029245217,0.000038498838,0.06619772,0.000023168705,0.00003249423,0.00028521204,0.011106165,0.0005883554],"about_ca_topic_score_codex":0.013670653,"about_ca_topic_score_gemma":0.00021835696,"teacher_disagreement_score":0.15672897,"about_ca_system_score_codex":0.000032773925,"about_ca_system_score_gemma":0.00033418156,"threshold_uncertainty_score":0.9998477},"labels":[],"label_agreement":null},{"id":"W7019173226","doi":"","title":"Exploring Feedback Literacy in the Undergraduate Medical Education Context","year":2024,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Context (archaeology); Literacy; Psychological intervention; Peer feedback; Health literacy; Higher education; Active learning (machine learning)","score_opus":0.04418322156107731,"score_gpt":0.3121943755882959,"score_spread":0.2680111540272186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019173226","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05042033,0.0005032947,0.0000054898146,0.0040124836,0.0026468446,0.00042699347,0.0000026354794,0.00007508945,0.94190687],"genre_scores_gemma":[0.23332734,0.001171477,0.000027184498,0.00031028973,0.00047918884,0.000010671315,0.00011971449,0.000026111613,0.76452804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99769807,0.00036756712,0.00022484153,0.00041306618,0.0009388498,0.00035763107],"domain_scores_gemma":[0.9993069,0.00016332018,0.00011590942,0.00018400744,0.0001024457,0.00012738661],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004177649,0.00024318851,0.00023674642,0.000274895,0.0003243157,0.00038664113,0.00094540947,0.00025055336,0.029914519],"category_scores_gemma":[0.000064321335,0.00022081542,0.0001534636,0.0011769292,0.000097011936,0.00070960086,0.00006636934,0.0006366984,0.00040336428],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076082244,0.00016643881,0.0019571409,0.00012584035,0.00006904831,0.00011373684,0.12866984,5.815994e-7,0.0000015739112,0.077941276,0.006791911,0.7840865],"study_design_scores_gemma":[0.00029627635,0.000016075555,0.0022724767,0.0004988503,0.00006871668,5.722399e-7,0.2846205,0.000007535213,0.0000014695282,0.0006928571,0.711318,0.00020667701],"about_ca_topic_score_codex":0.0032469966,"about_ca_topic_score_gemma":0.04975738,"teacher_disagreement_score":0.7838799,"about_ca_system_score_codex":0.0003526749,"about_ca_system_score_gemma":0.0011757289,"threshold_uncertainty_score":0.9709723},"labels":[],"label_agreement":null},{"id":"W7019427849","doi":"","title":"Guiding students Towards Success in Calculus via a Focused Assessment Approach","year":2023,"lang":"en","type":"article","venue":"York University Digital Library (York University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Calculus (dental); Curriculum","score_opus":0.038946072673093725,"score_gpt":0.2679864002203329,"score_spread":0.22904032754723916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019427849","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43743762,0.00001563065,0.00059444644,0.0005345704,0.00026650063,0.0005234955,0.000097522585,0.0007931283,0.5597371],"genre_scores_gemma":[0.9214771,0.00011226182,0.0004917336,0.000046063786,0.00010575371,4.081058e-7,0.00021661438,0.000028400667,0.07752166],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708575,0.00027316497,0.00020268325,0.00065422774,0.0009786552,0.00080554275],"domain_scores_gemma":[0.998997,0.00014712304,0.00014462706,0.0003039943,0.00004151738,0.00036576617],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002256376,0.00029442215,0.00037444296,0.0012007022,0.00086951244,0.0006977252,0.0021128706,0.00023404979,0.00017601877],"category_scores_gemma":[0.00001653017,0.00037435896,0.00023330812,0.0061217574,0.00034024945,0.0042232787,0.0012415698,0.0002589486,0.00015006827],"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":[0.00021494523,0.00070128153,0.9242485,0.00003569095,0.00020156176,0.0010205285,0.0067317076,0.00012563205,0.000012615809,0.04902424,0.012862534,0.0048207534],"study_design_scores_gemma":[0.0042288643,0.00015851093,0.23987168,0.00011596707,0.00010810505,0.0000017078098,0.1337419,0.0005873779,0.000015760717,0.0003820721,0.6195493,0.001238793],"about_ca_topic_score_codex":0.00076376647,"about_ca_topic_score_gemma":0.00017795923,"teacher_disagreement_score":0.68437684,"about_ca_system_score_codex":0.00059831253,"about_ca_system_score_gemma":0.00053453515,"threshold_uncertainty_score":0.99987084},"labels":[],"label_agreement":null},{"id":"W7023926164","doi":"","title":"The Poverty Police: Police-Proxy University Services and Homelessness","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Poverty; Pipeline (software); Vulnerability (computing); Public health; Community service","score_opus":0.13373077805529454,"score_gpt":0.5308291729785508,"score_spread":0.39709839492325627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023926164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9209042,0.015289339,0.000015747115,0.0015335389,0.0011451823,0.0004612868,0.00003871157,0.000090603084,0.06052138],"genre_scores_gemma":[0.9562813,0.039454475,0.000019440095,0.00021668666,0.00043833247,0.0000045053084,0.000003249673,0.00002372687,0.0035582955],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99761415,0.00037186558,0.00033224642,0.00036717879,0.0008449117,0.00046965],"domain_scores_gemma":[0.9983997,0.0006088037,0.0002617528,0.00026764077,0.00019859709,0.00026352773],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015740028,0.00022105519,0.00039478994,0.00037095207,0.0015483325,0.004347941,0.0030141417,0.0001177432,0.0018484725],"category_scores_gemma":[0.000024438652,0.00016802183,0.00013719787,0.0014346296,0.0003725932,0.0030325141,0.0010901002,0.00031962252,0.000023378916],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015005578,0.00012575537,0.90624136,0.00018101177,0.00043378866,0.000027134007,0.028345326,0.0000052301566,0.0020860203,0.010841566,0.02952456,0.022038177],"study_design_scores_gemma":[0.00029282807,0.000006182113,0.67742646,0.0002877523,0.000113825015,0.0000019953795,0.028678326,0.00006738983,0.00018821695,0.0033755323,0.2892124,0.00034912117],"about_ca_topic_score_codex":0.056576226,"about_ca_topic_score_gemma":0.014103064,"teacher_disagreement_score":0.25968784,"about_ca_system_score_codex":0.00015875182,"about_ca_system_score_gemma":0.00026202202,"threshold_uncertainty_score":0.9997515},"labels":[],"label_agreement":null},{"id":"W7026718776","doi":"","title":"An Argument-Based Approach to the Validity of Interpretation and Use of Chinese High School Students' Grades across Educational Contexts","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Interpretation (philosophy); China; Argument (complex analysis); External validity; Predictive validity; Internal validity; Test validity; Globalization; Empirical research","score_opus":0.013832816171119582,"score_gpt":0.2983439730504333,"score_spread":0.2845111568793137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7026718776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99254066,0.000016590448,0.00014067681,0.0048980545,0.00032380526,0.0006366587,0.00012975936,0.000031983865,0.001281823],"genre_scores_gemma":[0.9653168,0.00009772809,0.0013217988,0.00007514824,0.00009086343,0.00000456384,0.0010397929,0.000017740353,0.03203557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979901,0.00050906674,0.00019938091,0.00038436014,0.00070646685,0.0002106439],"domain_scores_gemma":[0.99867624,0.00031270695,0.00034679033,0.00028430964,0.00020296763,0.00017697758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017295363,0.00021532059,0.0003419576,0.0001677577,0.00039676685,0.00028142575,0.0007046328,0.00018217824,0.00017586631],"category_scores_gemma":[0.00012397877,0.000198407,0.00012475663,0.0006051916,0.00017012295,0.0013760125,0.000113578884,0.00020809754,0.000002594572],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000343278,0.000815879,0.9413876,0.00014416403,0.00017630073,0.0000021542166,0.04395838,0.00009698197,0.000025130596,0.0048545385,0.007992737,0.00020284731],"study_design_scores_gemma":[0.00043247762,0.000088142246,0.94197077,0.000112525566,0.00008407852,1.5252608e-8,0.054713808,0.0000073685487,0.0001705144,0.00013668204,0.0020579253,0.00022567845],"about_ca_topic_score_codex":0.009195525,"about_ca_topic_score_gemma":0.0016274175,"teacher_disagreement_score":0.030753747,"about_ca_system_score_codex":0.00008372191,"about_ca_system_score_gemma":0.0005655718,"threshold_uncertainty_score":0.9974023},"labels":[],"label_agreement":null},{"id":"W7034584056","doi":"","title":"Tunique aux couleurs multiples: Deux siècles de présence juive au Canada","year":2021,"lang":"fr","type":"article","venue":"Project Muse (Johns Hopkins University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Meaning (existential); Narrative; Identity (music)","score_opus":0.030327235380401725,"score_gpt":0.2794713260612569,"score_spread":0.2491440906808552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034584056","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3307818,0.00004461035,0.00039847277,0.0051349835,0.0026715172,0.0006213941,0.0001446085,0.00013402809,0.6600686],"genre_scores_gemma":[0.80855095,0.18314415,0.0020569446,0.00074918236,0.0008272205,0.000005025588,0.000048662136,0.000052104606,0.0045657232],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961801,0.0008093131,0.0002730679,0.0007442488,0.0007718403,0.0012214307],"domain_scores_gemma":[0.997942,0.00052147947,0.0002231502,0.00041583244,0.0005191046,0.00037845198],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034972935,0.00041338275,0.00043660865,0.0012537977,0.0011279209,0.00014179175,0.0009126133,0.00031807367,0.0003389342],"category_scores_gemma":[0.00028541495,0.0005277751,0.00022583063,0.009277047,0.00068199716,0.0007224974,0.00043902872,0.00050079095,0.000038359143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0003640084,0.0023201923,0.37000424,0.00073963264,0.0016482583,0.015158464,0.3638163,0.00034447285,0.0001998915,0.15962744,0.028218508,0.05755861],"study_design_scores_gemma":[0.0008532352,0.000065307104,0.0048273955,0.00020358474,0.00022188998,0.000013470112,0.05998412,0.00030991685,0.0004125054,0.0000038981193,0.932522,0.00058269995],"about_ca_topic_score_codex":0.99471813,"about_ca_topic_score_gemma":0.99821323,"teacher_disagreement_score":0.9043035,"about_ca_system_score_codex":0.0040243827,"about_ca_system_score_gemma":0.03113795,"threshold_uncertainty_score":0.999799},"labels":[],"label_agreement":null},{"id":"W7036622043","doi":"","title":"Chatting with Bill and Ian","year":2021,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Check-in; Soul; The Internet; Ticket; Launched","score_opus":0.009140975278899111,"score_gpt":0.22650067570483357,"score_spread":0.21735970042593444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036622043","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000063911895,0.00044419724,1.2992922e-7,0.00056600786,0.00015709906,0.0002778213,0.0000136953295,0.000087648776,0.9983895],"genre_scores_gemma":[0.00083412114,0.00058738224,0.000991272,0.00015725537,0.00024233929,0.0000073120227,0.000047399033,0.000053962565,0.99707896],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988145,0.00007188703,0.0002526775,0.0001547302,0.00046101148,0.00024518854],"domain_scores_gemma":[0.99926543,0.00006524732,0.0003202816,0.00014895693,0.000100775134,0.000099306526],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024118947,0.00018593446,0.00027246808,0.00004929269,0.00014477281,0.00010458667,0.00017676335,0.00023386994,0.36287007],"category_scores_gemma":[0.000058317288,0.00014916022,0.000054543245,0.0000102535605,0.00022490125,1.5353964e-7,0.00006286577,0.00014724422,0.0007878397],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011792704,0.000015541933,0.00008827364,0.0001289633,0.000047668032,0.000010618501,0.0016159854,0.000002246552,5.9401113e-8,0.000107348715,0.99655765,0.0014138228],"study_design_scores_gemma":[0.0002889127,0.000049108006,0.000055826637,0.00029909017,0.000033894416,0.000007101328,0.003424568,0.0000011114988,5.9513013e-7,0.000003704713,0.99562234,0.00021372846],"about_ca_topic_score_codex":0.017452115,"about_ca_topic_score_gemma":0.016240796,"teacher_disagreement_score":0.3620822,"about_ca_system_score_codex":0.000029817553,"about_ca_system_score_gemma":0.000054896485,"threshold_uncertainty_score":0.99999017},"labels":[],"label_agreement":null},{"id":"W7037814327","doi":"","title":"Estudo geofísico da transição continente-oceano e das anomalias-J na parte distal do sistema rifte ibéria-newfoundland : paleorreconstrução e implicações para a evolução tectônica","year":2021,"lang":"pt","type":"article","venue":"Repositório Digital Institucional da UFPR (Universidade Federal do Paraná)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Deformation (meteorology); Work (physics); Filter (signal processing)","score_opus":0.037345793831580286,"score_gpt":0.3083338666166812,"score_spread":0.27098807278510095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037814327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87491834,0.0038638206,0.0009207677,0.0033399318,0.0027701496,0.0017421733,0.001367917,0.00039821377,0.11067871],"genre_scores_gemma":[0.97360384,0.00048588976,0.00014946933,0.0002646043,0.00083901844,0.000056964214,0.0010785981,0.00013696481,0.02338462],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9892413,0.00062736054,0.0018983136,0.0029743027,0.0028055715,0.0024531311],"domain_scores_gemma":[0.9945485,0.00076992996,0.0010957498,0.001333376,0.0008969415,0.0013555241],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.00064543454,0.0017150094,0.0022087696,0.00044990284,0.004052519,0.0082204,0.0016987021,0.00095048227,0.00089184655],"category_scores_gemma":[0.0002287053,0.0018904653,0.001913628,0.002050835,0.0017028053,0.0045262673,0.0008615087,0.0012850306,0.00064356666],"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":[0.0040809293,0.008146853,0.8065408,0.0011801391,0.008426894,0.0144838495,0.03835551,0.00018941738,0.0031755636,0.08721099,0.011128779,0.017080285],"study_design_scores_gemma":[0.02714658,0.002727885,0.46889636,0.0047211414,0.0034869234,0.00410754,0.14614676,0.0014195492,0.0003843444,0.002394693,0.32702664,0.011541611],"about_ca_topic_score_codex":0.0008221993,"about_ca_topic_score_gemma":0.004878592,"teacher_disagreement_score":0.33764446,"about_ca_system_score_codex":0.0009802346,"about_ca_system_score_gemma":0.0018967285,"threshold_uncertainty_score":0.99955964},"labels":[],"label_agreement":null},{"id":"W7043557011","doi":"","title":"Towards a Situated View of Assessment Literacy for Higher Education","year":2022,"lang":"en","type":"dissertation","venue":"University Library (University of Saskatchewan)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Situated; Higher education; Sample (material); Thematic analysis; Literacy; Relation (database); Situated learning; Term (time)","score_opus":0.013788561541878961,"score_gpt":0.2838788324900515,"score_spread":0.27009027094817256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043557011","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61275464,0.00064896076,0.00012427213,0.0025543123,0.0026838598,0.0020981452,0.00078861514,0.0002536003,0.37809357],"genre_scores_gemma":[0.48874545,0.0006442398,0.00639681,0.00004743886,0.00010785755,6.212029e-7,0.0034911346,0.000027108934,0.5005393],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.998353,0.00023250807,0.00018537995,0.00039312875,0.0005753295,0.00026063027],"domain_scores_gemma":[0.9986119,0.00012649353,0.00059329893,0.0002561152,0.00027655633,0.00013558457],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018341054,0.00022079461,0.0004998839,0.0004700353,0.0007398214,0.000038946848,0.0010242965,0.00027884694,0.012152399],"category_scores_gemma":[0.0000049361047,0.00032810122,0.00039248253,0.00082817324,0.00017131135,0.001704897,0.00018555051,0.00026104294,0.0000057427346],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022435037,0.0026395586,0.018583564,0.0022102357,0.0013821137,0.0000454322,0.79726905,0.000012946874,0.0004568345,0.060845453,0.0443976,0.06991369],"study_design_scores_gemma":[0.00068118423,0.000118231954,0.022741433,0.00013460885,0.0003083758,7.143146e-8,0.5607357,0.000004922609,0.000022847595,0.0008244369,0.41414526,0.0002829162],"about_ca_topic_score_codex":0.006724093,"about_ca_topic_score_gemma":0.0019623926,"teacher_disagreement_score":0.36974767,"about_ca_system_score_codex":0.00027689294,"about_ca_system_score_gemma":0.003986715,"threshold_uncertainty_score":0.9999171},"labels":[],"label_agreement":null},{"id":"W7071929433","doi":"","title":"Unpacking 'the Next Black Box': Investigating the Cognitive and Affective Underpinnings of Student Self-Assessment","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Unpacking; Session (web analytics); Cognition; Centrality; Class (philosophy); TRACE (psycholinguistics); Process (computing); Empirical research; Protocol analysis","score_opus":0.017294814971463176,"score_gpt":0.28373958965874113,"score_spread":0.26644477468727795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071929433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91110706,0.00012130252,0.000025625615,0.020808894,0.00035363276,0.0011418255,0.000015792362,0.0001391956,0.06628667],"genre_scores_gemma":[0.9635673,0.0015879773,0.00046238353,0.00020482387,0.00016748976,0.0000047496114,0.00014720918,0.00004098839,0.03381705],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9970541,0.00093345565,0.00021472888,0.00052028225,0.00087260315,0.00040483003],"domain_scores_gemma":[0.9975652,0.0012360779,0.00059684174,0.00023580536,0.00021829207,0.0001477905],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00031670294,0.00034285526,0.00043557235,0.00016863264,0.0014245572,0.00046679316,0.0006954615,0.00027269314,0.00016321283],"category_scores_gemma":[0.000050414223,0.00028590448,0.00019143507,0.00095791614,0.0006307764,0.0011075288,0.00037512233,0.0006998962,0.0000052354717],"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":[0.00009437176,0.00033428802,0.40266323,0.0003114562,0.0017179205,0.00007948769,0.50894433,0.000011402339,0.000035990943,0.061366696,0.023470437,0.0009703915],"study_design_scores_gemma":[0.00046616598,0.00007477407,0.29235217,0.00051474234,0.00044604088,6.0272704e-8,0.70206416,0.0000047274402,0.00018600003,0.0003670976,0.00320477,0.00031930264],"about_ca_topic_score_codex":0.006196415,"about_ca_topic_score_gemma":0.0013386549,"teacher_disagreement_score":0.19311981,"about_ca_system_score_codex":0.00024616148,"about_ca_system_score_gemma":0.0012137326,"threshold_uncertainty_score":0.9999593},"labels":[],"label_agreement":null},{"id":"W7073581443","doi":"","title":"Acute and sublethal toxicity of novaluron, a novel chitin synthesis inhibitor, to Leptinotarsa decemlineata (Coleoptera: Chrysomelidae)","year":2011,"lang":"en","type":"article","venue":"The Atrium (University of Guelph)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agriculture and Agri-Food Canada","keywords":"Leptinotarsa; Novaluron; Colorado potato beetle; Larva; PEST analysis; Insect growth regulator","score_opus":0.03697645924542412,"score_gpt":0.2620231421321643,"score_spread":0.2250466828867402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7073581443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98450005,0.000043471908,0.0005585659,0.001461999,0.00011022113,0.00029910382,0.00003900669,0.00002928118,0.01295828],"genre_scores_gemma":[0.9961731,0.00007910409,0.0029487072,0.00005091307,0.0000840603,4.5480792e-7,0.000001662427,0.000007035479,0.00065495714],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988502,0.000097253236,0.00015298578,0.00022952493,0.00039943506,0.0002705521],"domain_scores_gemma":[0.999127,0.00017415288,0.0001712492,0.00025741113,0.00014841667,0.00012178366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006552309,0.00012504793,0.00027799836,0.000094937335,0.00038297038,0.000015771868,0.0006775455,0.00009193769,0.00037489118],"category_scores_gemma":[0.000072293675,0.00012195024,0.00011499095,0.000422266,0.0005055423,0.00023172467,0.000352568,0.00010716216,0.000021628468],"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":[0.0018023549,0.0011986914,0.19261517,0.00011316335,0.0009031914,0.000039112027,0.2819298,0.0000075258567,0.4957699,0.01298978,0.0033870183,0.009244306],"study_design_scores_gemma":[0.0011491091,0.0002731873,0.9488622,0.00006972251,0.00042381874,0.0000027190172,0.037457574,0.00004395772,0.00831149,0.00014484442,0.002921925,0.00033943678],"about_ca_topic_score_codex":0.004869635,"about_ca_topic_score_gemma":0.0028669282,"teacher_disagreement_score":0.75624704,"about_ca_system_score_codex":0.00004438071,"about_ca_system_score_gemma":0.00009141438,"threshold_uncertainty_score":0.73614645},"labels":[],"label_agreement":null},{"id":"W7095385706","doi":"","title":"Canadian Society for the Study of Education","year":2013,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Higher education; Work (physics)","score_opus":0.031446218296256094,"score_gpt":0.36755614502329503,"score_spread":0.33610992672703893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095385706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8590054,0.000027948605,0.000032287215,0.0073447474,0.00040448483,0.0015593362,4.8552636e-7,0.000009597298,0.13161573],"genre_scores_gemma":[0.98064965,0.0000066855187,0.0001744969,0.00025492717,0.00010585617,0.000112902206,4.3987e-7,0.0000014633729,0.018693564],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9997137,0.000010890535,0.000047698162,0.00004147531,0.00009713148,0.00008907678],"domain_scores_gemma":[0.99973446,0.000079273945,0.000017240163,0.00005417784,0.00007827299,0.000036566264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001789825,0.000019770107,0.000028471608,0.000008523909,0.0002974612,0.00003626319,0.0001286082,0.000014578725,0.0007096088],"category_scores_gemma":[0.000012642923,0.000012518888,0.00003442035,0.00007885715,0.000024243805,0.00006304258,0.000005744769,0.000014188524,0.00001324332],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.3882126e-7,0.00029359295,0.31310585,0.0000025858308,0.000075556476,4.3845865e-9,0.16913846,8.650582e-7,0.000018570347,0.027764743,0.45676073,0.03283831],"study_design_scores_gemma":[0.000107348766,0.00003229691,0.20868154,7.231603e-7,0.000015244948,3.5961507e-9,0.7346069,0.000029795998,0.000002299866,0.0005946674,0.05589641,0.00003276564],"about_ca_topic_score_codex":0.86153495,"about_ca_topic_score_gemma":0.84973055,"teacher_disagreement_score":0.56546843,"about_ca_system_score_codex":0.000053737,"about_ca_system_score_gemma":0.00037511985,"threshold_uncertainty_score":0.7769719},"labels":[],"label_agreement":null},{"id":"W7095589736","doi":"","title":"Knowledge and Skills Related to the Development and Use of Teacher-Made Tests","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Test (biology); Recall; Standardized test; Knowledge level; Quarter (Canadian coin)","score_opus":0.033680102457859705,"score_gpt":0.3461971084290518,"score_spread":0.31251700597119214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095589736","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94195765,0.00007427381,0.000023541155,0.002282329,0.00006294661,0.00018470017,4.2846594e-7,0.000020694428,0.055393443],"genre_scores_gemma":[0.9226,0.000072320465,0.0010080768,0.00003320418,0.000018537286,0.000005797533,1.3680308e-7,0.0000031487182,0.076258816],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994634,0.00005739806,0.00011655202,0.000109061904,0.00012594122,0.0001276401],"domain_scores_gemma":[0.99946177,0.0003454108,0.000026610982,0.00006456183,0.00003640914,0.00006521926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039056467,0.00005159766,0.00007090066,0.00003572356,0.0001889162,0.00003396282,0.00008717291,0.0000383382,0.00013243264],"category_scores_gemma":[0.00018690596,0.000025126672,0.000009459236,0.0001503041,0.00011419799,0.00010958654,0.000085431006,0.000024340321,0.00003873359],"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":[0.000004602619,0.0000879279,0.80729705,0.0000031224897,0.000031945954,2.9785718e-7,0.072590336,3.3879882e-8,0.0007791687,0.02547894,0.005344377,0.088382214],"study_design_scores_gemma":[0.00017927309,0.000016718293,0.7522333,0.00002745367,0.00000557541,1.273097e-7,0.0020149495,4.6053455e-7,0.000265386,0.00012389055,0.24506477,0.000068052206],"about_ca_topic_score_codex":0.00008342549,"about_ca_topic_score_gemma":0.002907057,"teacher_disagreement_score":0.23972039,"about_ca_system_score_codex":0.000023222412,"about_ca_system_score_gemma":0.000052622185,"threshold_uncertainty_score":0.16222061},"labels":[],"label_agreement":null},{"id":"W7096392813","doi":"","title":"Toronto","year":2005,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Confidentiality; Expectancy theory; Inflation (cosmology); Function (biology); Anonymity","score_opus":0.025201443647737347,"score_gpt":0.37703904011560563,"score_spread":0.3518375964678683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096392813","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020641198,0.000079417725,0.00005126574,0.0029564523,0.000103312945,0.00003784167,5.583919e-8,0.00006335284,0.9760671],"genre_scores_gemma":[0.8773964,0.00006578325,0.0013897,0.00039678722,0.00054262864,0.0000018108547,1.9258114e-7,0.0000013731641,0.120205335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996747,0.000012488729,0.000033646706,0.000044308672,0.00013554045,0.00009931851],"domain_scores_gemma":[0.999898,0.0000136491335,0.0000063821913,0.000036046873,0.000011862636,0.000034066074],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012180803,0.000019274941,0.000024146813,0.0000029816365,0.00011992539,0.000028739632,0.00008238633,0.000016517259,0.014114229],"category_scores_gemma":[0.00000697681,0.00001662315,0.000015696862,0.000023082373,0.000023461851,0.0001975884,0.000010191661,0.0000105221425,0.00048546775],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023802324,0.000060455794,0.031615008,3.8760487e-7,0.000008850246,3.355911e-7,0.021661062,4.9595087e-7,0.000080078156,0.7360169,0.1306779,0.07987613],"study_design_scores_gemma":[0.00005629147,0.000003519427,0.009421237,3.5927187e-7,0.0000012720251,1.3902672e-8,0.00745043,0.000004938468,0.00001542987,0.000114282855,0.98289824,0.00003401625],"about_ca_topic_score_codex":0.003275514,"about_ca_topic_score_gemma":0.05862909,"teacher_disagreement_score":0.8567552,"about_ca_system_score_codex":0.00007171548,"about_ca_system_score_gemma":0.00001808268,"threshold_uncertainty_score":0.986787},"labels":[],"label_agreement":null},{"id":"W7096394374","doi":"","title":"Learning","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Curriculum; Space (punctuation); Key (lock); Philosophy of education; Affect (linguistics); Formative assessment","score_opus":0.027973769974527177,"score_gpt":0.356247329041961,"score_spread":0.32827355906743383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096394374","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12326247,0.000004209713,0.00036934833,0.003697199,0.000104690465,0.000023780756,2.4618291e-8,0.0000814009,0.87245685],"genre_scores_gemma":[0.7882639,0.000032301847,0.00011072502,0.00004211946,0.000105588304,9.769726e-7,2.9307568e-8,0.0000011195532,0.21144322],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99968976,0.000028532975,0.0000263723,0.000043785094,0.00011618916,0.000095334886],"domain_scores_gemma":[0.99987084,0.000059618418,0.000008052284,0.00002207813,0.0000132273135,0.000026202986],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001666008,0.00001608357,0.00002104925,0.000009912661,0.00014740916,0.00001693748,0.00006081435,0.000014118325,0.0042941314],"category_scores_gemma":[0.00005267619,0.000009035648,0.000013308291,0.000043737313,0.00004232939,0.00007919877,0.000011606721,0.0000129317095,0.0007484698],"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":[0.0000020535992,0.000011699333,0.58675927,2.6902606e-7,0.0000058790056,8.0430544e-7,0.0053079035,4.85971e-8,0.0013141377,0.3030173,0.009710692,0.093869954],"study_design_scores_gemma":[0.0001471224,0.000015742065,0.04342563,0.0000035508392,0.0000015621822,2.5068173e-8,0.0057702214,4.6634213e-7,0.000082300896,0.0012051284,0.9492933,0.00005493736],"about_ca_topic_score_codex":0.000113210685,"about_ca_topic_score_gemma":0.00014159779,"teacher_disagreement_score":0.93958265,"about_ca_system_score_codex":0.000015613816,"about_ca_system_score_gemma":0.000015460646,"threshold_uncertainty_score":0.99661607},"labels":[],"label_agreement":null},{"id":"W7096583644","doi":"","title":"Washback in language assessment","year":2013,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Language assessment; Quarter (Canadian coin); Language proficiency; English language; Criterion-referenced test","score_opus":0.01766615138195563,"score_gpt":0.37841698802956336,"score_spread":0.3607508366476077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096583644","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48309982,0.0000131811275,0.000023509665,0.0016561345,0.00009329527,0.0001650627,1.0596539e-7,0.000036656274,0.51491225],"genre_scores_gemma":[0.955054,0.000025005265,0.0014685137,0.00029387968,0.000093648225,0.00003227515,0.00000148461,0.0000038376306,0.043027356],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99924123,0.000063850915,0.00010065216,0.00010740679,0.00025613772,0.0002307384],"domain_scores_gemma":[0.99976486,0.0000533363,0.00001910406,0.00008273641,0.000023154244,0.000056795187],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027709245,0.00005002234,0.00007372296,0.000046128112,0.00008141379,0.000100548205,0.00016524782,0.000039509185,0.012784973],"category_scores_gemma":[0.000016197919,0.000042575826,0.000025141992,0.00018979615,0.000048418053,0.00024034097,0.00003427668,0.00006908585,0.00097572803],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011681385,0.00017098656,0.8247873,0.000003723534,0.000011016748,0.0000065409904,0.022104315,0.0000014171046,0.0014112279,0.106832854,0.0306038,0.0140656065],"study_design_scores_gemma":[0.0003972167,0.000017918783,0.89359486,0.0000072382873,0.000002664667,7.513235e-8,0.087152205,0.00011050974,0.000036250927,0.0011396604,0.017379012,0.00016238372],"about_ca_topic_score_codex":0.0114091635,"about_ca_topic_score_gemma":0.0049442337,"teacher_disagreement_score":0.47195417,"about_ca_system_score_codex":0.00008093517,"about_ca_system_score_gemma":0.000055087723,"threshold_uncertainty_score":0.9998021},"labels":[],"label_agreement":null},{"id":"W7097327432","doi":"","title":"Perceptions of Assessment","year":2015,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Windsor; Permission; Perception; Legislation","score_opus":0.07329582133251847,"score_gpt":0.43890915689663546,"score_spread":0.365613335564117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097327432","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24392064,0.0000052174796,0.0006856431,0.00083910755,0.00014679044,0.00005872797,4.1531175e-7,0.000027287837,0.75431615],"genre_scores_gemma":[0.9703137,0.000012586742,0.003934573,0.000044531847,0.00007876198,0.0000033316712,0.0000010658648,0.0000017147036,0.02560971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994396,0.00004569651,0.000072107934,0.000051280982,0.00030299457,0.00008835146],"domain_scores_gemma":[0.99973595,0.000022989507,0.000021950174,0.00005805646,0.000088692505,0.00007238253],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038514956,0.000025418425,0.000053108088,0.000024162728,0.00006950547,0.000016576758,0.000103207014,0.000022046399,0.001422789],"category_scores_gemma":[0.00002160287,0.00002193293,0.0000257422,0.00011360729,0.00008592962,0.000088564055,0.000021549085,0.000025582174,0.0000686193],"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":[0.0000020291095,0.00012797937,0.59146816,0.0000012667641,0.000012570161,3.785797e-7,0.014925185,0.0000028950694,0.00037427497,0.36299315,0.028108329,0.0019838016],"study_design_scores_gemma":[0.00065290835,0.000114766895,0.52262384,0.0000065681847,0.000024546704,1.5505032e-7,0.32053384,0.000085318876,0.00003643548,0.00500175,0.15074497,0.00017489726],"about_ca_topic_score_codex":0.00084895064,"about_ca_topic_score_gemma":0.00049417466,"teacher_disagreement_score":0.7287065,"about_ca_system_score_codex":0.000047502534,"about_ca_system_score_gemma":0.00016222958,"threshold_uncertainty_score":0.99949},"labels":[],"label_agreement":null},{"id":"W7097468103","doi":"","title":"Differential Bundle Functioning on Mathematics and Science Achievement Tests: A Small Step Toward Understanding Differential Performance","year":2000,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Test (biology); Student achievement; Achievement test; Standardized test; Selection (genetic algorithm); Academic achievement; Subject (documents)","score_opus":0.07533882156350026,"score_gpt":0.3092023842523159,"score_spread":0.23386356268881564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097468103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90313405,0.0000064157143,0.0048896912,0.0003596772,0.00032528213,0.00026743248,9.157415e-7,0.00010063162,0.09091589],"genre_scores_gemma":[0.9933137,0.00013974444,0.0010756496,0.000059458263,0.00021578527,0.000012567178,0.0000018648097,0.00001080458,0.0051703677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99813676,0.000029004783,0.00021706171,0.00033932558,0.00078499626,0.00049285643],"domain_scores_gemma":[0.99951273,0.00008508734,0.00006326891,0.00014603882,0.00003667699,0.00015617837],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034091002,0.0001670178,0.00017100711,0.00012349461,0.0015987724,0.00055264233,0.0002949316,0.000057638157,0.0030836472],"category_scores_gemma":[0.00002291476,0.00013886616,0.000044516415,0.00034280057,0.0005279419,0.00030832566,0.00008535884,0.00013924079,0.000058133217],"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":[0.00036100537,0.0033258563,0.27896038,0.00021023348,0.00021783164,0.000005296942,0.079726964,0.000055221142,0.004540421,0.57848346,0.0007294971,0.05338379],"study_design_scores_gemma":[0.010272073,0.004704764,0.64526004,0.0010593885,0.00054444093,0.0000099103545,0.258056,0.05660199,0.002184639,0.0084288,0.008888582,0.003989348],"about_ca_topic_score_codex":0.00016849166,"about_ca_topic_score_gemma":0.0002481934,"teacher_disagreement_score":0.5700547,"about_ca_system_score_codex":0.0003399987,"about_ca_system_score_gemma":0.0000930269,"threshold_uncertainty_score":0.999701},"labels":[],"label_agreement":null},{"id":"W7099236764","doi":"","title":"Principles for Fair Student Assessment Practices for Education in Canada The Principles for Fair Student Assessment Practices for Education in Canada contains a set of","year":2011,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Process (computing); Standards-based assessment; Commission; Construct (python library); Educational assessment; Curriculum; Professional association; Best practice","score_opus":0.13526576797902734,"score_gpt":0.4662201732620031,"score_spread":0.33095440528297576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099236764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9381475,0.0002278969,0.0023831306,0.01140853,0.002933391,0.022952786,0.00026591073,0.000029938916,0.021650942],"genre_scores_gemma":[0.9633484,0.00013721184,0.019890303,0.00051864673,0.0003773763,0.011220241,0.00016723048,0.00003933215,0.0043012947],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956982,0.00034360378,0.0012863787,0.00069412077,0.0011814301,0.00079627224],"domain_scores_gemma":[0.99161845,0.0036631145,0.0031307524,0.00043194322,0.0009773843,0.00017836299],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004009926,0.00036135982,0.00057464524,0.00017054903,0.00059162994,0.00021863337,0.001127722,0.0001050005,0.000061454026],"category_scores_gemma":[0.0011633771,0.0002937579,0.00014544628,0.00030952273,0.00008128125,0.00083508244,0.00015308004,0.00019439482,2.2744699e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00025954004,0.0018706924,0.8373876,0.00034364124,0.00027263525,4.9014943e-7,0.014346364,0.000100720754,0.00004693108,0.13269356,0.005109236,0.007568573],"study_design_scores_gemma":[0.0013216916,0.00027906647,0.46445838,0.000076267475,0.00014590379,2.9115384e-7,0.38375744,0.00053512177,0.000074735406,0.00036316208,0.14868692,0.00030104147],"about_ca_topic_score_codex":0.9963252,"about_ca_topic_score_gemma":0.999948,"teacher_disagreement_score":0.37292925,"about_ca_system_score_codex":0.0073317112,"about_ca_system_score_gemma":0.11037561,"threshold_uncertainty_score":0.9999515},"labels":[],"label_agreement":null},{"id":"W7099448534","doi":"","title":"Development Canada.","year":2003,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human resources; Government (linguistics); Human development (humanity); Human Development Report; Work (physics); Development aid","score_opus":0.027569301283668142,"score_gpt":0.3112024190526638,"score_spread":0.2836331177689957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099448534","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088860385,0.000011606649,0.000041216987,0.0003885503,0.00023112155,0.000041424846,4.4454435e-8,0.000017941578,0.9104077],"genre_scores_gemma":[0.920109,0.000004515085,0.0037815433,0.00034657956,0.000025484644,0.000003005589,3.236365e-7,0.0000016655949,0.075727925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99951196,0.000021751395,0.000048205806,0.000051479205,0.00023292172,0.000133669],"domain_scores_gemma":[0.99987775,0.000016237149,0.000008786407,0.000029574678,0.000017770628,0.00004987159],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017180678,0.000025419173,0.000028992814,0.000007135685,0.00022940325,0.000019434765,0.00006272567,0.000011968078,0.0022958827],"category_scores_gemma":[0.000026187632,0.000022561127,0.0000055289797,0.00007604855,0.000014429821,0.000029000243,0.000004921662,0.000016980746,0.000041958403],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.371336e-7,0.000023998284,0.100320876,9.3268716e-7,0.000014340296,0.000003392516,0.007887806,3.0225505e-7,0.000033057837,0.78841186,0.099994615,0.003308208],"study_design_scores_gemma":[0.00004067215,5.387891e-7,0.010587785,4.7648035e-7,6.415847e-7,2.8203395e-8,0.0077133253,1.0342367e-7,0.00014709447,0.000056455214,0.98141074,0.000042146043],"about_ca_topic_score_codex":0.3961795,"about_ca_topic_score_gemma":0.9831106,"teacher_disagreement_score":0.88141614,"about_ca_system_score_codex":0.00012082445,"about_ca_system_score_gemma":0.0013705591,"threshold_uncertainty_score":0.99861616},"labels":[],"label_agreement":null},{"id":"W7099739439","doi":"","title":"from members of the project team. Special thanks are due to the following people for their advice and intellectual","year":2010,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Advice (programming); Corporate governance; Section (typography); Identification (biology); Key (lock); Point (geometry)","score_opus":0.021261052201838267,"score_gpt":0.31628644087335356,"score_spread":0.2950253886715153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099739439","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90675765,0.000009362056,0.00005485288,0.0033277713,0.0015078803,0.0008586437,0.0000141855635,0.000024851006,0.08744479],"genre_scores_gemma":[0.9943257,0.000004364111,0.00033889795,0.00019911233,0.0018245196,0.000038362097,0.0000013050027,0.0000075919875,0.0032601466],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99917716,0.00006815137,0.00012253074,0.00016838957,0.00026856276,0.00019518341],"domain_scores_gemma":[0.99880075,0.00088996225,0.000059912752,0.00016525334,0.000047913098,0.000036192716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050701626,0.00008906837,0.00014741186,0.00002425065,0.0005017531,0.000092192495,0.0004556658,0.00006468152,0.00036706147],"category_scores_gemma":[0.00050182734,0.00004432968,0.000120311386,0.00026300666,0.00009193692,0.00008604242,0.00014191346,0.00012734512,0.000005318202],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008806853,0.00008867822,0.08939795,0.000007051119,0.00014812815,4.0176113e-7,0.70348597,0.0000010816756,0.0010497547,0.0049195355,0.19649214,0.004321242],"study_design_scores_gemma":[0.00062092015,0.00007319737,0.083394155,0.000026509391,0.00008080007,4.7677085e-7,0.61204064,0.00014349984,0.0010842071,0.001510638,0.3007646,0.0002603789],"about_ca_topic_score_codex":0.006097531,"about_ca_topic_score_gemma":0.1702857,"teacher_disagreement_score":0.16418818,"about_ca_system_score_codex":0.00001424099,"about_ca_system_score_gemma":0.00009957191,"threshold_uncertainty_score":0.9217683},"labels":[],"label_agreement":null},{"id":"W7100101866","doi":"","title":"THE UNIVERSITY OF WESTERN ONTARIO FACULTY OF GRADUATE STUDIES CERTIFICATE OF EXAMINATION Advisor Examining Board","year":2000,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Certificate; Graduate students; Graduate research; Higher education; Editorial board","score_opus":0.2949934286798181,"score_gpt":0.37382672880350487,"score_spread":0.07883330012368678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100101866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9585583,0.000039963685,0.00001426137,0.0002566522,0.000049139035,0.00011773205,0.000002014209,0.000011088354,0.040950835],"genre_scores_gemma":[0.9529546,0.00038722376,0.00012091539,0.0000030162341,0.000009022572,3.8226005e-7,0.0000016222502,0.0000020174627,0.04652122],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99915236,0.00011181497,0.00017019582,0.00009899749,0.0003521629,0.00011444749],"domain_scores_gemma":[0.99941313,0.00015966922,0.00014513676,0.0000959201,0.0001663479,0.000019821862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005745761,0.000055069675,0.00015471851,0.000023774595,0.00023583269,0.000007885848,0.00022711685,0.00002822384,0.000245],"category_scores_gemma":[0.000022169821,0.000041389256,0.000042428866,0.00014185718,0.00040966275,0.00012367245,0.000035892896,0.0000425982,0.000007674994],"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":[0.0000736289,0.0001351532,0.58259857,0.000024279205,0.00021698854,9.340281e-7,0.34489337,0.00001798231,0.000567996,0.0015638758,0.0011466183,0.068760626],"study_design_scores_gemma":[0.00022117411,0.000058832713,0.88727796,0.00001812199,0.00003372704,1.9059359e-8,0.10444288,0.0000054127245,0.00036889018,0.00006791904,0.007454249,0.00005080387],"about_ca_topic_score_codex":0.032848936,"about_ca_topic_score_gemma":0.16940445,"teacher_disagreement_score":0.30467942,"about_ca_system_score_codex":0.00006620115,"about_ca_system_score_gemma":0.000059458576,"threshold_uncertainty_score":0.9735914},"labels":[],"label_agreement":null},{"id":"W7100226999","doi":"","title":"Paper Presented at the Symposium entitled “Improving Large-Scale Assessment in Education ” at the Annual Meeting of the Canadian Society for the Study of Education","year":2013,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Research council; Standardized test; Educational assessment; Government (linguistics); National education","score_opus":0.011477720456780673,"score_gpt":0.323893062274081,"score_spread":0.3124153418173003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100226999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93909186,0.00011692815,0.0000059612817,0.023390124,0.00078246807,0.003695367,0.000008620284,0.000006890821,0.032901753],"genre_scores_gemma":[0.97506577,0.000023544162,0.000054457763,0.0004212852,0.00014866026,0.0005180826,0.000005577314,0.00000803801,0.023754591],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9985545,0.00025847115,0.0002674216,0.00016708528,0.00048560897,0.00026686833],"domain_scores_gemma":[0.9986916,0.00043894615,0.00021305251,0.00032409158,0.00029127504,0.000041029434],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0015183325,0.00008995721,0.00010370993,0.000022360367,0.0015406465,0.00010007479,0.0005505684,0.000054166263,0.0006213435],"category_scores_gemma":[0.00006697476,0.0000402926,0.00012504391,0.00030681663,0.00016538384,0.00018875545,0.00019002026,0.00011411222,0.000004055982],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072918556,0.0008599695,0.69657725,0.000021815218,0.00011024349,7.466134e-9,0.21603304,0.0000483813,0.0016729432,0.0021516832,0.079956606,0.0025607846],"study_design_scores_gemma":[0.00025178064,0.000025295456,0.38650241,0.00001312658,0.000060189275,5.030954e-8,0.5960877,0.0003146171,0.00009112057,0.00006844934,0.016523838,0.00006146247],"about_ca_topic_score_codex":0.5558246,"about_ca_topic_score_gemma":0.9472316,"teacher_disagreement_score":0.39140698,"about_ca_system_score_codex":0.0005328787,"about_ca_system_score_gemma":0.001342315,"threshold_uncertainty_score":0.9997592},"labels":[],"label_agreement":null},{"id":"W7102398008","doi":"10.65005/154230723836949059","title":"Students′ Perceptions of Skills Transfer in a First-Year Seminar","year":2023,"lang":"en","type":"article","venue":"Journal of The First-Year Experience & Students in Transition","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perception; Academic skills; Study skills; Skills management; Transfer of training; Life skills","score_opus":0.014708777745636491,"score_gpt":0.353956143502827,"score_spread":0.3392473657571905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7102398008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99694145,0.000034474782,0.00007369907,0.0013303229,0.00067412434,0.00044629644,0.000008578618,0.000017798304,0.00047327747],"genre_scores_gemma":[0.99832654,0.0010896106,0.00008476662,0.00007500415,0.00016021197,0.00003053385,0.0000014518299,0.000016774966,0.00021513508],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99634683,0.0002264465,0.0007608295,0.00021495143,0.0020477914,0.00040317257],"domain_scores_gemma":[0.9992612,0.00013550879,0.00016690008,0.00020545242,0.00014402326,0.00008690089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015793326,0.00016988293,0.00036537868,0.00037851342,0.0003369344,0.00010954886,0.0014046121,0.00013702837,0.0002860455],"category_scores_gemma":[0.00008659854,0.00013938158,0.0002651411,0.0014775753,0.00032683936,0.00056806026,0.000083396844,0.0003627405,0.000026390855],"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":[0.00007849459,0.0006348751,0.6999825,0.000015219161,0.000023429759,0.00001738331,0.29817376,0.00029605525,0.00028522505,0.0001475258,0.0002992726,0.00004625026],"study_design_scores_gemma":[0.0016871176,0.00013054228,0.80895996,0.00042840923,0.00002932664,0.000002612172,0.18758143,0.000009430713,0.00014901909,0.00014669649,0.00072892115,0.00014655308],"about_ca_topic_score_codex":0.00025067828,"about_ca_topic_score_gemma":0.0018630687,"teacher_disagreement_score":0.11059232,"about_ca_system_score_codex":0.0002966286,"about_ca_system_score_gemma":0.00007681229,"threshold_uncertainty_score":0.56838155},"labels":[],"label_agreement":null},{"id":"W7103494908","doi":"","title":"A Collaborative &amp; Systematic Approach To Implementing An Effective Standards-Based Grading And Reporting System: A Change Leadership Plan","year":2017,"lang":"","type":"article","venue":"Digital Commons - NLU (National Louis University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Action plan; General partnership; Best practice; Program evaluation; Quarter (Canadian coin); Plan (archaeology); Standardized test","score_opus":0.16643018346009017,"score_gpt":0.3582139314163848,"score_spread":0.19178374795629463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103494908","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36539948,0.00019745227,0.0030213736,0.001342946,0.0006089566,0.008659377,0.0024878667,0.00027140748,0.6180112],"genre_scores_gemma":[0.99828714,0.0000030163785,0.0003590359,0.000044230434,0.00025763753,0.000048120593,0.00016980682,0.00003074749,0.0008002886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9949914,0.0006345535,0.0008403446,0.0008596587,0.001876114,0.00079790456],"domain_scores_gemma":[0.99416524,0.0007179399,0.0027157487,0.00047690878,0.0014445832,0.00047959504],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0036309366,0.0004554584,0.00088218256,0.0007353451,0.005476933,0.00391153,0.00097348745,0.00018259809,0.000010752469],"category_scores_gemma":[0.002136339,0.00051130564,0.00019140341,0.0009771641,0.00050666725,0.0031064819,0.0005189932,0.00028036666,0.000010682014],"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":[0.00078905816,0.0013028432,0.39774206,0.015736163,0.0017268583,0.0002395436,0.14445475,0.00006677905,0.000046375237,0.43549377,0.00076535525,0.0016364548],"study_design_scores_gemma":[0.0062447838,0.0011623154,0.10776838,0.015170528,0.0013126848,0.000030879524,0.8365522,0.00593471,0.00003082816,0.00042467503,0.022074467,0.0032935422],"about_ca_topic_score_codex":0.0004616751,"about_ca_topic_score_gemma":0.0017245489,"teacher_disagreement_score":0.6920975,"about_ca_system_score_codex":0.0018612647,"about_ca_system_score_gemma":0.0006106411,"threshold_uncertainty_score":0.99973387},"labels":[],"label_agreement":null},{"id":"W7103756966","doi":"10.5206/cjsotlrcacea.2025.1.19788","title":"Student Reflections on Mindfully Reframing Feedback for Growth in Academic, Personal, and Professional Settings","year":2025,"lang":"fr","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"Schulich School of Medicine and Dentistry; Social Sciences and Humanities Research Council of Canada","keywords":"Cognitive reframing; Mindfulness; Thematic analysis; Literacy; Focus group; Professional development; Meaning (existential); Metacognition; Adult literacy","score_opus":0.06407297731461939,"score_gpt":0.4286397605762346,"score_spread":0.3645667832616152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103756966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87603647,0.007461709,0.000110801564,0.11143487,0.0020201455,0.0006176447,0.000010297191,0.0000067338106,0.0023013281],"genre_scores_gemma":[0.959972,0.00023028157,0.00038648423,0.0009712962,0.0005318881,0.000030308953,0.0000017485124,0.000016666127,0.037859302],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99709207,0.0014513131,0.00036630238,0.00022367974,0.00030854382,0.00055809447],"domain_scores_gemma":[0.9960508,0.0032477186,0.00027405855,0.000068090194,0.00014136177,0.00021799648],"candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0151029825,0.00017669068,0.00023238514,0.00025844562,0.011583013,0.000465968,0.00044724988,0.00022752973,0.000019922518],"category_scores_gemma":[0.003220187,0.00012458618,0.00012088171,0.0002539242,0.000467021,0.00029951867,0.0000466664,0.0053205476,8.753476e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033262468,0.0000863217,0.2665723,0.00031797457,0.00056109024,0.0000058707865,0.3810158,0.00027787927,0.00023488278,0.21060176,0.0059198374,0.13407364],"study_design_scores_gemma":[0.002386262,0.0005674113,0.26244402,0.00463651,0.0005114233,0.00003941041,0.38179046,0.0007532133,0.000025107049,0.023559796,0.32282004,0.0004663514],"about_ca_topic_score_codex":0.006287161,"about_ca_topic_score_gemma":0.017947586,"teacher_disagreement_score":0.3169002,"about_ca_system_score_codex":0.00037915897,"about_ca_system_score_gemma":0.0007619618,"threshold_uncertainty_score":0.9999723},"labels":[],"label_agreement":null},{"id":"W7106788186","doi":"10.1108/978-1-68123-046-720251012","title":"Student Assessment in A Blended Learning Environment","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Blended learning; Experiential learning; Student engagement; Electronic learning; Test (biology); Process (computing); Online assessment","score_opus":0.05432146798584401,"score_gpt":0.36860370754773575,"score_spread":0.3142822395618917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106788186","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019450596,0.00032727217,0.000044601868,0.00088115263,0.00033384154,0.00064751145,0.0000018587134,0.00008906213,0.9974802],"genre_scores_gemma":[0.030206641,0.001559642,0.00048587687,0.000058995865,0.00034951427,0.000034768993,0.000025752215,0.000041934836,0.9672369],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996786,0.000114067945,0.00041450458,0.00048445357,0.0017649896,0.00043596397],"domain_scores_gemma":[0.9992357,0.000092137525,0.00020905107,0.00022257947,0.000045303364,0.00019524852],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014406885,0.00031738362,0.00044178253,0.0001942126,0.00021068654,0.00012864132,0.00045733363,0.00033982447,0.012413984],"category_scores_gemma":[0.000012314457,0.0003128631,0.0001315548,0.00003566543,0.00017338019,0.0001182723,0.00027847104,0.00078401633,0.0008353655],"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":[0.000011406276,0.0001748299,0.01750969,0.000010033407,0.0001423136,0.00007114176,0.009394895,0.00008900267,0.000004873819,0.95695275,0.008718259,0.0069208285],"study_design_scores_gemma":[0.00058202515,0.00009962454,0.0051051043,0.000054733184,0.0000465377,2.2169192e-7,0.007101751,0.000009789763,2.3560582e-7,0.0072770617,0.9792796,0.00044332063],"about_ca_topic_score_codex":0.0003596213,"about_ca_topic_score_gemma":0.0014609455,"teacher_disagreement_score":0.9705613,"about_ca_system_score_codex":0.0014440594,"about_ca_system_score_gemma":0.00061265106,"threshold_uncertainty_score":0.9999426},"labels":[],"label_agreement":null},{"id":"W7106822041","doi":"10.1108/978-1-68123-046-720251004","title":"Empowering Learners to Engage in Authentic Online Assessment","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Online assessment; Qualitative research; Process (computing); The Internet; Context (archaeology); Work (physics)","score_opus":0.09050856878806421,"score_gpt":0.42984025083243166,"score_spread":0.3393316820443675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106822041","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030844,0.00008659968,0.00006455487,0.0013093014,0.00078107335,0.0005691312,0.000008952961,0.00011439907,0.9939816],"genre_scores_gemma":[0.048609942,0.00011765884,0.0017535841,0.00021168099,0.00033282157,0.0000109492585,0.000034409186,0.000043920627,0.948885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977511,0.000068684516,0.00034950709,0.00041567997,0.0010001746,0.0004148551],"domain_scores_gemma":[0.99919266,0.00010307318,0.00010562236,0.00024191456,0.000089716275,0.00026703932],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012781492,0.0002685941,0.00038812964,0.0003009509,0.00016067275,0.00012721341,0.0004783677,0.000276466,0.004374781],"category_scores_gemma":[0.00006164191,0.00026623002,0.000111694775,0.000095068695,0.00009534089,0.00011865022,0.00022113674,0.000579911,0.0004497767],"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":[0.000023989736,0.00019808832,0.0038233746,0.000029142888,0.00013309003,0.00010296304,0.046223477,0.000052278243,0.000033270127,0.91011614,0.028125916,0.011138298],"study_design_scores_gemma":[0.00038349882,0.00008412009,0.001276571,0.00014980904,0.00003430064,2.1867622e-7,0.021065272,0.000032818396,2.953327e-7,0.004891144,0.9715393,0.0005426614],"about_ca_topic_score_codex":0.0010289797,"about_ca_topic_score_gemma":0.013093338,"teacher_disagreement_score":0.9434134,"about_ca_system_score_codex":0.0007151608,"about_ca_system_score_gemma":0.00046997066,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W7111684596","doi":"","title":"Redefining Neuro-Inclusive, Stakeholder-Informed Language Assessment in UK Higher Education","year":2025,"lang":"en","type":"book-chapter","venue":"Pure (Coventry University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Formative assessment; Higher education; Equity (law); Accreditation; Quality (philosophy); Best practice; Educational assessment; Resource (disambiguation); Discourse analysis; Scope (computer science)","score_opus":0.03523103187095834,"score_gpt":0.31009817115500404,"score_spread":0.2748671392840457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7111684596","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00071578147,0.00020788303,0.00001610044,0.0021150007,0.0014127381,0.0005174269,0.000029001114,0.00008839871,0.99489766],"genre_scores_gemma":[0.03967135,0.0006175692,0.00017241054,0.00042308224,0.0003370573,0.0000020118118,0.0001421652,0.000021702639,0.9586126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826676,0.00007046755,0.00024852,0.0004465144,0.00057591294,0.00039185566],"domain_scores_gemma":[0.9990022,0.00021202216,0.00028126346,0.00029380107,0.00008261449,0.0001280797],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018226526,0.0002964764,0.00035462045,0.00071294035,0.00040865724,0.00011954919,0.0006214801,0.00040511062,0.0024174843],"category_scores_gemma":[0.00003318698,0.00036997726,0.00016740158,0.00031489815,0.00012500581,0.00021899548,0.00031528482,0.00060827326,0.000046574147],"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":[0.00002847635,0.00006210328,0.0059287697,0.000047448957,0.000078050725,0.00014139812,0.0021793933,0.000004848525,0.00000604954,0.96787494,0.02024511,0.0034034078],"study_design_scores_gemma":[0.0005518635,0.000023759487,0.0068543437,0.00034674074,0.000120551,2.8438572e-7,0.0062383064,0.0000034189502,7.3886326e-7,0.0020684816,0.9834047,0.00038682827],"about_ca_topic_score_codex":0.00083892274,"about_ca_topic_score_gemma":0.0032138794,"teacher_disagreement_score":0.9658065,"about_ca_system_score_codex":0.0015713318,"about_ca_system_score_gemma":0.0027206168,"threshold_uncertainty_score":0.9998752},"labels":[],"label_agreement":null},{"id":"W7115402523","doi":"","title":"Teacher-Led Learning Circles for Formative Assessment:Full Report of International Research Findings","year":2024,"lang":"en","type":"book","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"Ministère de l’Éducation, Gouvernement de l’Ontario; Jacobs Foundation; Queen's University; University of South Florida; American Educational Research Association","keywords":"Formative assessment; Qualitative research; Experiential learning; Research methodology","score_opus":0.1450135143569837,"score_gpt":0.4418710255656071,"score_spread":0.29685751120862336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115402523","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012961981,0.0005240063,0.0009942118,0.006026902,0.0033080056,0.002621996,0.00013421923,0.00018121047,0.97324747],"genre_scores_gemma":[0.04862821,0.0026975293,0.0011383102,0.0000051767397,0.0031791825,0.00003925925,0.0005257409,0.00007791992,0.94370866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98953795,0.00056697347,0.00074568164,0.0010917281,0.006678404,0.0013792727],"domain_scores_gemma":[0.9898875,0.0038478118,0.00054149894,0.0005539501,0.0047667986,0.00040244768],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.021633586,0.00039665867,0.0009572007,0.0031543758,0.0018528999,0.00026803836,0.0026416453,0.00084846735,0.010661024],"category_scores_gemma":[0.0023539183,0.0004795319,0.0006930055,0.0012592969,0.002951769,0.0011739867,0.0017246787,0.0035617133,0.000028394257],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000274436,0.00021481799,0.000855437,0.00014047883,0.0007926521,0.00019747317,0.087590106,0.000005506592,0.00037268136,0.007638468,0.8999046,0.0020133464],"study_design_scores_gemma":[0.00084180647,0.0004614828,0.00012985422,0.0009510026,0.00011348324,0.0000038832877,0.19663686,0.0003143439,0.000025238929,0.024564303,0.77556556,0.00039218078],"about_ca_topic_score_codex":0.0007847767,"about_ca_topic_score_gemma":0.00025244043,"teacher_disagreement_score":0.12433903,"about_ca_system_score_codex":0.002300301,"about_ca_system_score_gemma":0.004109102,"threshold_uncertainty_score":0.99976563},"labels":[],"label_agreement":null},{"id":"W7116078021","doi":"10.20343/teachlearninqu.13.61","title":"Structured Flexibility in Assessment: Students’ Perceptions of the Impact of Different Elements of Choice on Their Decision Making, Engagement, and Learning Experiences","year":2025,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Flexibility (engineering); Autonomy; Perception; Quality (philosophy); Process (computing); Scholarship; Higher education","score_opus":0.051035545615166655,"score_gpt":0.4602103792120843,"score_spread":0.40917483359691764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116078021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99750376,0.00006136646,0.00045398372,0.00012669325,0.00038072764,0.0003032694,9.322584e-7,0.000014033571,0.0011552557],"genre_scores_gemma":[0.9993923,0.00009059451,0.00020088584,0.000016507902,0.00009568109,0.0000072386642,7.1902434e-7,0.000009373891,0.00018670059],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9937253,0.0040798057,0.00071095064,0.00022506097,0.0009498542,0.00030901897],"domain_scores_gemma":[0.99714077,0.0016427876,0.000847449,0.00023098353,0.0000939263,0.00004408609],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006682818,0.00019279608,0.0003713368,0.00022355371,0.0017862783,0.00015405353,0.00096237735,0.00007825408,0.00019011405],"category_scores_gemma":[0.0016730593,0.000097107346,0.00022576404,0.00033027696,0.0005164294,0.00018556947,0.00039067765,0.0019890617,1.9374228e-7],"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":[0.000053299205,0.00018543535,0.8037802,0.00000851552,0.00009775221,2.0537581e-7,0.17929971,0.0020875474,0.00096605235,0.00034005777,0.000029097491,0.013152151],"study_design_scores_gemma":[0.0004983262,0.00019290925,0.7901393,0.00043246362,0.000028835531,5.310353e-7,0.20763612,0.00033085106,0.000022194883,0.0005672,0.00008082527,0.0000704061],"about_ca_topic_score_codex":0.00036271702,"about_ca_topic_score_gemma":0.00012665,"teacher_disagreement_score":0.028336411,"about_ca_system_score_codex":0.00029826173,"about_ca_system_score_gemma":0.00015790931,"threshold_uncertainty_score":0.99951327},"labels":[],"label_agreement":null},{"id":"W7116316694","doi":"10.1016/j.ijedudev.2025.103476","title":"Exploring effective teacher certificate requirements to benefit student achievement: Evidence from a global perspective","year":2025,"lang":"en","type":"article","venue":"International Journal of Educational Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Certification; Licensure; Certificate; Perspective (graphical); Test (biology); Professional certification (computer technology)","score_opus":0.20509403059623602,"score_gpt":0.46798326171927596,"score_spread":0.26288923112303997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116316694","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.931724,0.00043951324,0.0008110795,0.048136517,0.005770346,0.00042217682,0.0000070430847,0.000010798789,0.012678499],"genre_scores_gemma":[0.9914341,0.00015645381,0.0044740555,0.00049024995,0.0008808334,0.00013099912,0.0000062734543,0.0000063160637,0.0024207185],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997162,0.00010898001,0.00058381783,0.0002774095,0.0016353854,0.00023244381],"domain_scores_gemma":[0.99735814,0.00038921586,0.00029782,0.00009690967,0.001696642,0.0001612582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087134604,0.00015609014,0.00018602626,0.000273486,0.0002682643,0.00024449758,0.0010252824,0.00003791687,0.0005183846],"category_scores_gemma":[0.00067422306,0.00015271049,0.000102013124,0.00037377482,0.00005848561,0.00073311577,0.00020742505,0.0001422332,0.0000992416],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041439885,0.0014602515,0.8120068,0.000004015261,0.0022515736,0.000008806338,0.075812005,0.00011518873,0.00045559954,0.07696595,0.0035133518,0.026992092],"study_design_scores_gemma":[0.00040032793,0.000033588167,0.9597842,0.00043285286,0.00003979293,6.227337e-7,0.015852509,0.0000012788034,0.00028250722,0.0051928097,0.017833132,0.00014636417],"about_ca_topic_score_codex":0.0009394299,"about_ca_topic_score_gemma":0.0005675097,"teacher_disagreement_score":0.14777745,"about_ca_system_score_codex":0.0056494433,"about_ca_system_score_gemma":0.0013197543,"threshold_uncertainty_score":0.9981677},"labels":[],"label_agreement":null},{"id":"W7117361401","doi":"10.51798/sijis.v6i4.1177","title":"Validation of tests using an argument-based approach: a review based on the PRISMA model","year":2025,"lang":"","type":"article","venue":"Sapienza International Journal of Interdisciplinary Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Barrie Urology Group","funders":"","keywords":"Relevance (law); Empirical research; Reliability (semiconductor); Quality (philosophy); Process (computing); Test (biology)","score_opus":0.11653760396115638,"score_gpt":0.45201481181218167,"score_spread":0.3354772078510253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117361401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71148354,0.04007259,0.065837726,0.122608155,0.013392646,0.0036246153,0.00015663804,0.00006043145,0.042763636],"genre_scores_gemma":[0.9913061,0.0028087723,0.0032871922,0.0018346295,0.00042561602,0.000023911713,0.000008694201,0.000020027943,0.00028503366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945016,0.0006999021,0.0018918552,0.00040265403,0.002156923,0.00034706635],"domain_scores_gemma":[0.9933897,0.00090592157,0.0023172863,0.0003699039,0.002920329,0.00009683471],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0038679326,0.0004169752,0.00087300636,0.00064159493,0.00068770413,0.0001618985,0.001932162,0.0001135105,0.00012937264],"category_scores_gemma":[0.0007245151,0.0002865442,0.0006798645,0.0007379271,0.0007865354,0.0006394699,0.00073247775,0.00050425436,0.0000033442982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006984767,0.030596698,0.033876106,0.005818815,0.02025162,0.00016096883,0.13417006,0.6522951,0.0032941783,0.035098962,0.058254242,0.019198481],"study_design_scores_gemma":[0.00573656,0.0030845343,0.004441535,0.06189773,0.0029232246,0.000016148266,0.12404771,0.77462924,0.0026084243,0.018511828,0.00083974155,0.0012633223],"about_ca_topic_score_codex":0.000007693577,"about_ca_topic_score_gemma":0.000008325504,"teacher_disagreement_score":0.27982256,"about_ca_system_score_codex":0.00080542685,"about_ca_system_score_gemma":0.0008896493,"threshold_uncertainty_score":0.9999587},"labels":[],"label_agreement":null},{"id":"W7124146263","doi":"10.31986/issn.2995-8288_vol3iss2.4","title":"“The Being of Being Creative” in Assessment: Learning from the Creative and Performing Arts","year":2025,"lang":"","type":"article","venue":"Turning toward being :","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Foregrounding; Formative assessment; Creativity; Performing arts; Experiential learning; Memorization; Narrative; Value (mathematics); Quality (philosophy)","score_opus":0.02363586033746035,"score_gpt":0.33832485041748234,"score_spread":0.314688990080022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124146263","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8389283,0.0015897334,0.0008422288,0.003502563,0.0007823271,0.00065445714,0.0000019371607,0.000058832327,0.15363966],"genre_scores_gemma":[0.9919882,0.0025868828,0.000905853,0.000119130855,0.0003761721,0.000046055367,0.00000931019,0.000035375364,0.00393301],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99457556,0.0014419652,0.0011052241,0.0008076379,0.0010313836,0.0010382048],"domain_scores_gemma":[0.99249136,0.0060350643,0.00075431314,0.0003586036,0.00024194732,0.0001186929],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0047994214,0.00052658434,0.0008155957,0.00023941998,0.004409093,0.00092116994,0.0009726615,0.00027246974,0.00017738451],"category_scores_gemma":[0.0015975304,0.00039235424,0.0002350472,0.0013867237,0.0011949335,0.00065888383,0.0008548899,0.001779051,0.0000057137718],"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":[0.00007425094,0.000061634855,0.65218234,0.00005031827,0.00035378218,0.000010464565,0.2792943,0.00019371799,0.0005607061,0.022044286,0.000059344762,0.045114856],"study_design_scores_gemma":[0.0012192519,0.00015643254,0.70244765,0.003021297,0.00039853834,6.7449383e-7,0.26779062,0.0075163976,0.00042087896,0.011673442,0.004842064,0.00051273825],"about_ca_topic_score_codex":0.0055601387,"about_ca_topic_score_gemma":0.00055948045,"teacher_disagreement_score":0.15305994,"about_ca_system_score_codex":0.0004374772,"about_ca_system_score_gemma":0.0005182537,"threshold_uncertainty_score":0.99985284},"labels":[],"label_agreement":null},{"id":"W7125351318","doi":"","title":"A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Undergraduate Education; Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"CLARITY; Technical writing; Perspective (graphical); Preference; Course (navigation); Scalability; Quality (philosophy); Peer feedback","score_opus":0.17140721702955675,"score_gpt":0.5004576099750087,"score_spread":0.3290503929454519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125351318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897833,0.0004764628,0.00007010782,0.0007921614,0.00047058653,0.0018755166,0.000002813506,0.000040461593,0.0064886254],"genre_scores_gemma":[0.9987895,0.00013498843,0.0004350943,0.00011961588,0.00025556175,0.000049998955,8.020323e-7,0.000010462685,0.00020400515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9937808,0.0011354606,0.0012846544,0.0013007103,0.0017690874,0.00072930136],"domain_scores_gemma":[0.9973765,0.0009359418,0.0004962091,0.0004987856,0.0005618408,0.00013072033],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.005750337,0.00039420885,0.0010054936,0.0005003331,0.0013314311,0.00033012862,0.0010382812,0.00014865147,0.000055816163],"category_scores_gemma":[0.00026607537,0.00039468642,0.00010845031,0.0023940096,0.0020145362,0.00045478155,0.0010595126,0.0006680851,0.000010030126],"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":[0.00005576789,0.0026534488,0.74345523,0.000031686293,0.00008180312,0.000003507133,0.2459283,0.000058614984,0.00065701234,0.00566879,0.000011534662,0.0013943226],"study_design_scores_gemma":[0.0014249685,0.00095501315,0.5945923,0.0002677475,0.000059162863,1.0732278e-7,0.40211698,0.00023650406,0.000038179147,0.00008708939,0.0000071207996,0.00021486376],"about_ca_topic_score_codex":0.000780908,"about_ca_topic_score_gemma":0.0018136543,"teacher_disagreement_score":0.15618868,"about_ca_system_score_codex":0.00062285835,"about_ca_system_score_gemma":0.0004845805,"threshold_uncertainty_score":0.9999687},"labels":[],"label_agreement":null},{"id":"W7127392540","doi":"10.1109/ccece64018.2025.11364447","title":"Automated Grading of Scratch Card Based Immediate Feedback Assessment Technique (IFAT)","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Scratch; Grading (engineering); Process (computing); Automation; Usability","score_opus":0.018134071906542287,"score_gpt":0.36203799488045996,"score_spread":0.3439039229739177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127392540","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09215008,0.0005244014,0.018635541,0.01298994,0.0057470966,0.0057979613,0.00007267728,0.0018661862,0.8622161],"genre_scores_gemma":[0.9776817,0.0003806526,0.012344883,0.0006213731,0.0001844652,0.00021607394,0.000027607033,0.0000385284,0.008504706],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940805,0.00079846836,0.0014585133,0.0009392857,0.0015633319,0.0011599013],"domain_scores_gemma":[0.9971654,0.0007069119,0.0006235072,0.0007006705,0.0005272168,0.00027631473],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030554594,0.00062384555,0.0011356305,0.0006790056,0.0008765087,0.00035164427,0.0013157533,0.00060407474,0.0019188705],"category_scores_gemma":[0.00011709643,0.00061670836,0.000560911,0.003069216,0.0008533892,0.0004518889,0.00038653804,0.000563575,0.000057814905],"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":[0.00033997782,0.0042628753,0.49891874,0.0017516542,0.0024446503,0.000060687824,0.008275537,0.00029755072,0.1191445,0.1505487,0.20055449,0.013400634],"study_design_scores_gemma":[0.015445971,0.0018204724,0.5305779,0.005428455,0.0031783963,0.0000013323646,0.090655476,0.09922931,0.1890024,0.015359132,0.043508504,0.0057926453],"about_ca_topic_score_codex":0.002736571,"about_ca_topic_score_gemma":0.00041902126,"teacher_disagreement_score":0.88553166,"about_ca_system_score_codex":0.0008126448,"about_ca_system_score_gemma":0.002587983,"threshold_uncertainty_score":0.9996284},"labels":[],"label_agreement":null},{"id":"W7130683390","doi":"10.1109/swc65939.2025.00073","title":"Can Question Validation Criteria Improve the Quality of LLM-Generated Multiple-Choice Questions?","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Athabasca University","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Athabasca University","keywords":"Formative assessment; Quality (philosophy); Set (abstract data type); Subject-matter expert; Quality assurance; Key (lock); Subject (documents)","score_opus":0.05532363522220222,"score_gpt":0.43079302854945173,"score_spread":0.3754693933272495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130683390","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9262179,0.00039756796,0.0024292073,0.022022152,0.0054484126,0.0017854248,0.000084845575,0.00014101379,0.04147348],"genre_scores_gemma":[0.98258543,0.0003090357,0.0003265987,0.0003846992,0.00040933237,0.00006527746,0.000053969878,0.000010916636,0.015854718],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947898,0.0023945563,0.0011108074,0.0005164699,0.0007538666,0.00043454062],"domain_scores_gemma":[0.9957663,0.0021435271,0.00055076956,0.0004913048,0.00095400994,0.00009411677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038229146,0.00028693833,0.00042204358,0.00014247703,0.001127361,0.0003962437,0.00061524764,0.00028119094,0.00080582785],"category_scores_gemma":[0.0033521429,0.00022514978,0.00019455708,0.0014153998,0.00059299904,0.00041532805,0.00017355982,0.00026465364,0.000018921433],"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":[0.00021511588,0.0014943035,0.4630763,0.00023562241,0.0004873687,4.7384495e-7,0.016819058,0.00007945485,0.13640033,0.36059913,0.007651573,0.012941279],"study_design_scores_gemma":[0.0023603733,0.00026192286,0.92416084,0.00027095576,0.00044408016,1.1912506e-7,0.024083542,0.0052468968,0.02711844,0.0072195847,0.008086176,0.0007470579],"about_ca_topic_score_codex":0.077283755,"about_ca_topic_score_gemma":0.026957832,"teacher_disagreement_score":0.46108454,"about_ca_system_score_codex":0.00030558175,"about_ca_system_score_gemma":0.00061592076,"threshold_uncertainty_score":0.99079764},"labels":[],"label_agreement":null},{"id":"W7130688282","doi":"10.1109/swc65939.2025.00060","title":"Automated Grading: Methods, Implementations, and Opportunities in Higher Education","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Innovation Fund; Government of Alberta","keywords":"Grading (engineering); Workflow; Automation; Higher education","score_opus":0.17804031274985058,"score_gpt":0.5101519021792482,"score_spread":0.33211158942939767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130688282","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07199609,0.004006597,0.00019922512,0.05881608,0.004604949,0.0010287854,0.0000057768502,0.0002968792,0.8590456],"genre_scores_gemma":[0.7875844,0.0040040333,0.0071729654,0.0020461362,0.00012264226,0.000088437286,0.000023182276,0.000008851966,0.1989493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9980768,0.00059564173,0.00047092352,0.00030749594,0.00021675682,0.0003323917],"domain_scores_gemma":[0.9992519,0.00033034853,0.00011370925,0.00012261418,0.00009045124,0.00009096483],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012441047,0.00016963697,0.00023557291,0.00041995317,0.00044901762,0.00035316296,0.00019551965,0.000111716494,0.004958665],"category_scores_gemma":[0.000028891143,0.00017653807,0.00004322787,0.00077105546,0.00021954902,0.0004479818,0.00011611535,0.00010859885,0.000008200418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000699074,0.00020699222,0.060731772,0.000040977397,0.00006392636,6.3922425e-7,0.008135544,2.0144287e-7,0.00010629786,0.82326907,0.043853987,0.063583575],"study_design_scores_gemma":[0.0008586159,0.000042821488,0.4169882,0.0001403867,0.00014842722,2.1262123e-7,0.21934454,0.0006289387,0.000059836446,0.024046564,0.33735096,0.00039046796],"about_ca_topic_score_codex":0.0021425248,"about_ca_topic_score_gemma":0.00062627986,"teacher_disagreement_score":0.7992225,"about_ca_system_score_codex":0.00019432975,"about_ca_system_score_gemma":0.00087848166,"threshold_uncertainty_score":0.99595094},"labels":[],"label_agreement":null},{"id":"W7132913430","doi":"","title":"Conflicts and challenges of testing: Differences between novice and experienced teachers&apos; preparation practices for large-scale assessments","year":2008,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Set (abstract data type); Test (biology); Sample (material); Educational measurement","score_opus":0.22750643072695254,"score_gpt":0.5093735031714349,"score_spread":0.2818670724444824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132913430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971254,0.0050344523,0.00008262192,0.0005218019,0.00033188428,0.0018480443,0.000020289583,0.00004312687,0.020863768],"genre_scores_gemma":[0.9766228,0.013580468,0.0025058677,0.000014391028,0.0003570569,0.00023828153,0.00009970773,0.00003456789,0.006546832],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.996383,0.0003633044,0.0006768872,0.0009941987,0.0009818685,0.00060072565],"domain_scores_gemma":[0.993988,0.0021862646,0.0027648197,0.00024989614,0.0005730139,0.00023805744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001075691,0.00052941154,0.00095966394,0.00016392929,0.0011308453,0.00026378498,0.0003976107,0.0005856809,0.000042535758],"category_scores_gemma":[0.0009186757,0.00052905886,0.00009454961,0.00033248853,0.0003819033,0.0008008837,0.000102166014,0.00030370202,0.0000021185915],"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":[0.0001981967,0.0003031237,0.1464459,0.0005161372,0.00023228057,8.5540887e-7,0.844487,3.2493043e-7,0.0015930565,0.00056006724,0.00003791276,0.0056251558],"study_design_scores_gemma":[0.0012868097,0.0013509471,0.2932833,0.00032564066,0.0004027492,9.930476e-7,0.69736683,0.0003322482,0.00044256277,0.000067328714,0.004575304,0.0005652519],"about_ca_topic_score_codex":0.0017147821,"about_ca_topic_score_gemma":0.0025344517,"teacher_disagreement_score":0.14712015,"about_ca_system_score_codex":0.000055641827,"about_ca_system_score_gemma":0.00034228215,"threshold_uncertainty_score":0.9997161},"labels":[],"label_agreement":null},{"id":"W7132923481","doi":"","title":"Exploring Perspective-taking in Peer Assessment","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Association for the Study of Adult Education","funders":"","keywords":"Peer assessment; Rubric; Peer feedback; Operationalization; Judgement; Peer group; Peer evaluation; Peer review","score_opus":0.2197275793622576,"score_gpt":0.5054941032321677,"score_spread":0.2857665238699101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132923481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66599506,0.0001850039,0.000014175348,0.0025556092,0.0077153733,0.0008360383,0.0000017383879,0.00018456485,0.32251245],"genre_scores_gemma":[0.8164203,0.0022643057,0.0002416493,0.000029099201,0.0013774112,0.00038455124,0.000085151776,0.00011458976,0.17908292],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9936857,0.00043110314,0.00065375725,0.001162388,0.002865185,0.0012018256],"domain_scores_gemma":[0.9974554,0.0004802309,0.0007704641,0.0003820074,0.00070032733,0.00021157225],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024485842,0.00063083175,0.00079426786,0.0007584663,0.00090623525,0.00056062086,0.00083729037,0.00039742925,0.0018175956],"category_scores_gemma":[0.0006056646,0.0007408723,0.0003391512,0.0025806562,0.00014732928,0.0007126897,0.00016376078,0.0012369805,0.00073175743],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056917823,0.00025660056,0.041131083,0.000097398435,0.00016446997,0.0000814412,0.9288428,0.00006859273,0.00025493873,0.026381733,0.0007268137,0.0019372521],"study_design_scores_gemma":[0.00044084084,0.00005497796,0.34538317,0.0003827657,0.00006910734,1.3803317e-7,0.6498601,0.00012297393,0.00001872941,0.00029694717,0.0028343208,0.0005359227],"about_ca_topic_score_codex":0.033636168,"about_ca_topic_score_gemma":0.023151826,"teacher_disagreement_score":0.3042521,"about_ca_system_score_codex":0.0019980196,"about_ca_system_score_gemma":0.0009070182,"threshold_uncertainty_score":0.9995042},"labels":[],"label_agreement":null},{"id":"W7132932718","doi":"","title":"Large scale performance-based assessment: Dentification of individual student gaps with implications for teacher content knowledge","year":2004,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nature versus nurture; Literacy; Population; Construct (python library); Scale (ratio); Pace; Knowledge acquisition; Task (project management); Interpretation (philosophy)","score_opus":0.06807253949039363,"score_gpt":0.436790008042412,"score_spread":0.36871746855201837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132932718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.966263,0.0006511409,0.0037052452,0.00070016994,0.0008684458,0.0049047563,0.00014951875,0.00008374503,0.022673974],"genre_scores_gemma":[0.9666165,0.00029819523,0.0017777729,0.000031156538,0.00030528713,0.0016236713,0.0029486928,0.00008915675,0.026309565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955102,0.00024797965,0.0010034611,0.0009912665,0.0013373272,0.0009097464],"domain_scores_gemma":[0.9956895,0.0002482074,0.0015526676,0.00066230976,0.001592415,0.00025490441],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0019119661,0.0006545972,0.0008596467,0.00039701263,0.0015419185,0.00036981364,0.001282937,0.00051708706,0.0004162898],"category_scores_gemma":[0.000036992817,0.0006249898,0.00037888417,0.0010385531,0.00036632345,0.00035768305,0.000084473286,0.00047756213,0.000037953818],"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":[0.00053761684,0.009550278,0.5263824,0.0015313759,0.0011489454,5.128051e-7,0.44299185,0.00014987153,0.0035595016,0.010285514,0.0009312186,0.0029309257],"study_design_scores_gemma":[0.004031721,0.0006578234,0.73450375,0.0006107473,0.0011334056,3.1596858e-7,0.2550493,0.00013937395,0.0010678261,0.00004313917,0.0021244963,0.00063811673],"about_ca_topic_score_codex":0.00019370065,"about_ca_topic_score_gemma":0.0032609394,"teacher_disagreement_score":0.20812134,"about_ca_system_score_codex":0.00069437566,"about_ca_system_score_gemma":0.0026648159,"threshold_uncertainty_score":0.99975795},"labels":[],"label_agreement":null},{"id":"W7132982053","doi":"","title":"Reforming Language Teaching through Learner Portfolio Assessment: The Complexity of Practitioners’ Experiences","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; University of Toronto","keywords":"Authentic assessment; Data collection; Agency (philosophy); Exploratory factor analysis; Metacognition; Language assessment; Language education; Portfolio; Self-assessment; Qualitative research","score_opus":0.06834876892462345,"score_gpt":0.4694674329827249,"score_spread":0.4011186640581015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132982053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5829803,0.000634295,0.000046030356,0.0012436383,0.0016627172,0.0006795854,0.000006852644,0.000054025648,0.41269258],"genre_scores_gemma":[0.9348727,0.0005834447,0.0007993856,0.0001539079,0.00047767436,0.0002502655,0.00038973507,0.000045528584,0.0624274],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9940545,0.0013270852,0.0007839481,0.00069290015,0.0024547325,0.00068684155],"domain_scores_gemma":[0.9967805,0.0004351771,0.0019619006,0.0005813829,0.00014354344,0.000097468066],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026397891,0.00048427485,0.0006889267,0.0001355321,0.0044745845,0.00028099364,0.0013577639,0.0002481089,0.02091963],"category_scores_gemma":[0.00022344403,0.00038389338,0.00039947833,0.00081014895,0.0012635096,0.0009086548,0.00030298944,0.0017016903,0.00002262055],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050764793,0.00026379953,0.0010592116,0.00006230152,0.00016838223,0.000010398588,0.948587,0.000011885707,0.0006740972,0.047121316,0.0010035778,0.0009872447],"study_design_scores_gemma":[0.00030680513,0.00015130235,0.0035806953,0.000098946475,0.000187253,0.0000023162704,0.96019053,0.000065271,0.00018875657,0.00042191974,0.03436196,0.00044423304],"about_ca_topic_score_codex":0.032148775,"about_ca_topic_score_gemma":0.0018950196,"teacher_disagreement_score":0.35189238,"about_ca_system_score_codex":0.0003817068,"about_ca_system_score_gemma":0.00073036057,"threshold_uncertainty_score":0.9998613},"labels":[],"label_agreement":null},{"id":"W7133013582","doi":"","title":"Teaching methodologies and assessment strategies of Ontario grade 9 mathematics teachers","year":2004,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Teaching method; Evaluation methods; Alternative assessment; Connected Mathematics; Program evaluation","score_opus":0.1199004617813298,"score_gpt":0.4912382694024263,"score_spread":0.3713378076210965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133013582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.763414,0.0005745193,0.0011269683,0.00046258522,0.0007522863,0.00079205795,0.0000021993983,0.00007023659,0.23280513],"genre_scores_gemma":[0.6708625,0.00094616803,0.23627505,0.00001812057,0.00020930136,0.00005994634,0.000083106024,0.00007264371,0.09147318],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99601316,0.0006444022,0.00082397804,0.00064765016,0.001236294,0.000634487],"domain_scores_gemma":[0.99727446,0.00084058836,0.0012370698,0.0003477984,0.00014268975,0.00015737466],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029916533,0.000638343,0.0011565065,0.00022701758,0.00083182,0.00045686765,0.00064766477,0.00062596484,0.00042926913],"category_scores_gemma":[0.00017288912,0.0006165232,0.00027618112,0.0002465518,0.00054692314,0.0004813814,0.00013934984,0.0014974447,0.000006165589],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015906573,0.00032876438,0.0039458917,0.00044694013,0.00037399723,0.0000047381154,0.89797676,0.00004120304,0.0014867416,0.09304585,0.00004394232,0.0022892845],"study_design_scores_gemma":[0.0005906642,0.00025532718,0.045320503,0.000545376,0.00055956544,0.0000012052697,0.93075943,0.000017249145,0.00017627595,0.019258125,0.0019717808,0.00054452324],"about_ca_topic_score_codex":0.33217472,"about_ca_topic_score_gemma":0.23960587,"teacher_disagreement_score":0.23514807,"about_ca_system_score_codex":0.0011341928,"about_ca_system_score_gemma":0.004826714,"threshold_uncertainty_score":0.9996286},"labels":[],"label_agreement":null},{"id":"W7133083716","doi":"","title":"Teachers Navigating Their Experiences of &quot;Going Gradeless&quot; in Ontario, Canada","year":2020,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rubric; Curriculum; Qualitative research; National curriculum; Process (computing); Task (project management); Hidden curriculum; Politics; Conceptual framework","score_opus":0.030177475987947074,"score_gpt":0.3594132025837606,"score_spread":0.3292357265958135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133083716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96001863,0.00059538265,0.000004006292,0.00060212304,0.0020502931,0.00069117895,0.000002242788,0.000030135616,0.036006026],"genre_scores_gemma":[0.9863767,0.00014501196,0.00018459119,0.000091878,0.00019569145,0.00010091396,0.00011336875,0.000045488894,0.012746342],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99519,0.00037250147,0.0010220094,0.00087749114,0.0016311778,0.0009067984],"domain_scores_gemma":[0.99773633,0.00040711666,0.0011323653,0.00027302705,0.0001560411,0.00029509066],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00066638,0.00064818165,0.0010788514,0.00009424373,0.0006113691,0.00017238535,0.001157287,0.00039852143,0.0016710868],"category_scores_gemma":[0.00018363462,0.00066809775,0.00024138439,0.001147068,0.0002942879,0.00029876488,0.00011910805,0.0015545457,0.0000075780117],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042962518,0.00006239372,0.07845035,0.00006836845,0.00007741551,0.000018841296,0.919023,0.000020632917,0.0005008476,0.00017349079,0.00037069275,0.0011909964],"study_design_scores_gemma":[0.0004418817,0.00008722529,0.01803742,0.00083758065,0.000054002005,3.054075e-7,0.97535706,0.00015197584,0.0011724732,0.000027035627,0.0031742149,0.00065882853],"about_ca_topic_score_codex":0.99592954,"about_ca_topic_score_gemma":0.9995412,"teacher_disagreement_score":0.060412932,"about_ca_system_score_codex":0.0013794552,"about_ca_system_score_gemma":0.0074949167,"threshold_uncertainty_score":0.99957705},"labels":[],"label_agreement":null},{"id":"W7140392809","doi":"10.1333/s00897050976a","title":"The Art of Good Grading—A Training Seminar for Graduate Students","year":2005,"lang":"en","type":"article","venue":"The Chemical Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cheating; Grading (engineering); Graduate students; Task (project management); Orientation (vector space)","score_opus":0.08500414879889394,"score_gpt":0.41575166508023165,"score_spread":0.3307475162813377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140392809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97064555,0.00014810108,0.0000073607807,0.017878568,0.00049046986,0.00038593967,0.0000034346667,0.000028439952,0.010412156],"genre_scores_gemma":[0.9916415,0.00007651673,0.00031835667,0.00021163872,0.0011254889,0.00007342554,0.0000027696378,0.000011231711,0.006539034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876535,0.000047625712,0.00020089082,0.00013745233,0.0005001412,0.00034852707],"domain_scores_gemma":[0.9988771,0.00069555937,0.00010338502,0.00017302555,0.00006255117,0.000088357425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011221075,0.000092599505,0.00013860717,0.000013754563,0.0004848361,0.00007967638,0.00083924073,0.000046840338,0.000043341443],"category_scores_gemma":[0.00027116545,0.000055406334,0.00011612837,0.00015473997,0.00037487445,0.00006559589,0.000062136634,0.00012378418,0.000032887332],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019139265,0.0011065772,0.018492702,0.000037450533,0.0004099196,4.2146823e-7,0.37089568,0.0000012527737,0.029990822,0.07002269,0.46261734,0.04623375],"study_design_scores_gemma":[0.00089143816,0.0000652802,0.0035218014,0.00005473573,0.0001395828,0.0000010539014,0.12770694,0.000020432755,0.02296676,0.0061588767,0.8381458,0.0003272989],"about_ca_topic_score_codex":0.000024078623,"about_ca_topic_score_gemma":0.00002702995,"teacher_disagreement_score":0.37552845,"about_ca_system_score_codex":0.00007517366,"about_ca_system_score_gemma":0.00014705777,"threshold_uncertainty_score":0.37290165},"labels":[],"label_agreement":null},{"id":"W7155756298","doi":"","title":"Assessing Core Competencies in British Columbia","year":2021,"lang":"en","type":"dissertation","venue":"KU ScholarWorks (The University of Kansas)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"CLARITY; Curriculum; Social skills; Skills management; Life skills; Core competency; Plan (archaeology); Academic skills","score_opus":0.027029602601231065,"score_gpt":0.2932933160606973,"score_spread":0.26626371345946626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7155756298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9378645,0.0009678088,0.000021091686,0.00013624622,0.0007311757,0.00029393303,0.000009057582,0.000040664112,0.05993556],"genre_scores_gemma":[0.9180268,0.0014015475,0.00083328295,0.000045698827,0.0001286225,7.101278e-7,0.00025025988,0.00002021784,0.07929285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99807924,0.0003006065,0.00021454175,0.00034360748,0.00072943664,0.00033254712],"domain_scores_gemma":[0.9988579,0.00021478943,0.00028750123,0.000228613,0.0003299963,0.00008115625],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007877555,0.00012682256,0.0003922198,0.00008151027,0.0014459088,0.0010116593,0.00088225363,0.00042637336,0.002364485],"category_scores_gemma":[0.00014431636,0.00021596208,0.00020385055,0.00075533043,0.0003108219,0.0007251952,0.00007909904,0.00085868355,0.000019637668],"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":[0.000041758205,0.0004167625,0.83818924,0.0002032832,0.00028195718,0.0004817723,0.105060495,0.000037203685,0.00026537673,0.0011231665,0.016353019,0.03754594],"study_design_scores_gemma":[0.00036527106,0.000009258793,0.54165614,0.0007262105,0.000090249625,7.627515e-7,0.4331242,0.000014433081,0.0000013387095,0.00017435192,0.023611197,0.00022658428],"about_ca_topic_score_codex":0.11853436,"about_ca_topic_score_gemma":0.8996782,"teacher_disagreement_score":0.78114384,"about_ca_system_score_codex":0.00022826908,"about_ca_system_score_gemma":0.00063139107,"threshold_uncertainty_score":0.9998541},"labels":[],"label_agreement":null},{"id":"W7160501424","doi":"10.66281/70130/8718","title":"Global perspectives on School-Based Assessment (SBA): A systematic review of international practices and challenges","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Consistency (knowledge bases); Foundation (evidence); Nexus (standard); Policy analysis; Systematic review; Key (lock)","score_opus":0.048523417659662615,"score_gpt":0.4380889449965813,"score_spread":0.3895655273369187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160501424","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001078174,0.39231482,0.0001275796,0.06350947,0.00082427607,0.001968053,0.000013999021,0.000037444293,0.5401262],"genre_scores_gemma":[0.41290066,0.5837595,0.00059067184,0.00091356697,0.00009082308,0.00008733978,0.000002219359,0.000005194154,0.001650066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"systematic_review","domain_scores_codex":[0.99603903,0.0009109261,0.00083017844,0.0006078534,0.0013322909,0.00027972506],"domain_scores_gemma":[0.9965754,0.00094451284,0.0014125434,0.0003466994,0.0005952844,0.00012552693],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002768042,0.0002944372,0.0008756745,0.00015762556,0.00025799303,0.00024995478,0.00067925267,0.00012797372,0.0011616636],"category_scores_gemma":[0.002627582,0.00024138505,0.00021309398,0.0006028943,0.00033625774,0.00041984048,0.00017762068,0.00017680005,0.000017827762],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059255406,0.0012494089,0.014201647,0.4778341,0.0011910581,0.0000039723463,0.0025132764,0.000001305989,0.000002615102,0.50152785,0.0011100336,0.00030547156],"study_design_scores_gemma":[0.0016051589,0.00055904454,0.05374057,0.604226,0.0020333093,0.0000010267651,0.3335927,0.00051490456,0.0000048132783,0.00077025156,0.0024187628,0.0005334282],"about_ca_topic_score_codex":0.00022145282,"about_ca_topic_score_gemma":0.00024531936,"teacher_disagreement_score":0.5384761,"about_ca_system_score_codex":0.0006325058,"about_ca_system_score_gemma":0.00090320694,"threshold_uncertainty_score":0.9997514},"labels":[],"label_agreement":null},{"id":"W7161986211","doi":"10.82308/37465","title":"Does self-assessment with specific criteria enhance graduate level ESL students' writing?","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Control (management); English as a second language; Graduate students; Qualitative research; Second language; Language proficiency; Note-taking","score_opus":0.04555487175482572,"score_gpt":0.43876116485543487,"score_spread":0.39320629310060917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161986211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64714205,0.00010408567,0.00041852245,0.00031745093,0.0035496636,0.0012402851,0.000018821873,0.00042345576,0.34678566],"genre_scores_gemma":[0.8290974,0.0015609129,0.012813504,0.00018262408,0.0017028783,0.00013867291,0.0004481263,0.000099338846,0.15395652],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99430835,0.0001888496,0.0006555485,0.0008843838,0.0030749552,0.00088792207],"domain_scores_gemma":[0.9981498,0.0002004232,0.00046522327,0.00039516756,0.00055353297,0.00023586417],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016411543,0.00055686664,0.00059441855,0.0002636376,0.00097047596,0.001058554,0.0011270492,0.00036969502,0.0023886058],"category_scores_gemma":[0.000012029465,0.00036669287,0.00016838462,0.000568404,0.00012169923,0.00040411486,0.000069338705,0.0005724447,0.00015901981],"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":[0.0012357702,0.0065004504,0.48451507,0.0010541955,0.002979953,0.0005195488,0.2889161,0.0000012407919,0.0024690055,0.07612785,0.087397076,0.048283737],"study_design_scores_gemma":[0.0011600511,0.0002350518,0.7275052,0.0004678016,0.0002482566,6.7442005e-7,0.21846502,0.0000026571095,0.0009655757,0.00059915584,0.048680115,0.0016704275],"about_ca_topic_score_codex":0.0012156856,"about_ca_topic_score_gemma":0.014104349,"teacher_disagreement_score":0.24299015,"about_ca_system_score_codex":0.00052970153,"about_ca_system_score_gemma":0.0005186743,"threshold_uncertainty_score":0.9999784},"labels":[],"label_agreement":null},{"id":"W7161994237","doi":"10.82308/45504","title":"In the service of the stakeholder: a critical, mixed-method program of research in high-stakes language assessment","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Certification; Stakeholder; Language assessment; Language proficiency; Perception; Task (project management); Service (business); Field (mathematics)","score_opus":0.15716927244799214,"score_gpt":0.5265548475892885,"score_spread":0.36938557514129633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161994237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78283316,0.00016897701,0.0000044184762,0.002243186,0.0005527579,0.0019033086,0.000015365826,0.000019895213,0.21225892],"genre_scores_gemma":[0.98913693,0.00008797697,0.0035044502,0.00008519189,0.000097487085,0.00035061216,0.000042829615,0.000019579435,0.006674937],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9946705,0.0023104264,0.0005172209,0.0002987173,0.0017417843,0.00046135532],"domain_scores_gemma":[0.99735045,0.0015546845,0.0001749212,0.00043434667,0.00044856686,0.000037027734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006148646,0.00016204655,0.00035644695,0.00026758816,0.00018541998,0.00008730188,0.0013940525,0.0002726598,0.00047550965],"category_scores_gemma":[0.00026609952,0.000096981,0.00009619072,0.0019527521,0.00026146098,0.00015144431,0.00007371409,0.0007328272,0.0000046768437],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013061876,0.0040753344,0.03949874,0.0014259855,0.00008267741,0.000023183064,0.44301313,0.0000016896036,0.0010975567,0.4940521,0.0029148306,0.013684152],"study_design_scores_gemma":[0.0003555201,0.00011480532,0.23388329,0.00037598226,0.000033784607,1.2938453e-7,0.7591874,0.000011232186,0.0004935815,0.0042938762,0.0010951492,0.00015522754],"about_ca_topic_score_codex":0.07215026,"about_ca_topic_score_gemma":0.26402417,"teacher_disagreement_score":0.48975822,"about_ca_system_score_codex":0.000085042804,"about_ca_system_score_gemma":0.0006446353,"threshold_uncertainty_score":0.9340284},"labels":[],"label_agreement":null},{"id":"W761528972","doi":"10.71781/5733","title":"Noticeability of corrective feedback, L2 development and learner beliefs","year":2012,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corrective feedback; Psychology; Cognitive psychology; Mathematics education","score_opus":0.058032085151739826,"score_gpt":0.3894859929590068,"score_spread":0.331453907807267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W761528972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6683079,0.00014394437,9.412645e-7,0.00003865268,0.00054964714,0.00054446195,0.0000037039554,0.0000011484733,0.3304096],"genre_scores_gemma":[0.90124047,0.000035821642,0.002243733,0.000007787306,0.00016192513,0.000029636854,0.00015951323,0.000015328005,0.096105814],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9985149,0.00012807541,0.0002991322,0.00031834163,0.0004477242,0.00029185895],"domain_scores_gemma":[0.9991369,0.00014587074,0.00028885412,0.000136033,0.00017375217,0.000118542],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011547693,0.00016925856,0.0003351352,0.000060826245,0.00032422075,0.00014390709,0.00042901502,0.00023587159,0.004271591],"category_scores_gemma":[0.00011727341,0.0001631268,0.00004305309,0.00017036997,0.00012575841,0.00027814042,0.0001020541,0.00018237218,0.0001951892],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015039099,0.00034964483,0.0948512,0.000048687583,0.00016401213,0.0000010909891,0.52716595,2.8973636e-7,0.00013996163,0.0002645314,0.00049939996,0.37636486],"study_design_scores_gemma":[0.0003330974,0.000033208868,0.76893765,0.00011112155,0.00009125243,1.06282826e-7,0.1147269,5.0222627e-7,0.0012784405,0.000037569025,0.114142574,0.0003075689],"about_ca_topic_score_codex":0.0011916709,"about_ca_topic_score_gemma":0.01928544,"teacher_disagreement_score":0.67408645,"about_ca_system_score_codex":0.000124744,"about_ca_system_score_gemma":0.0006183997,"threshold_uncertainty_score":0.99861},"labels":[],"label_agreement":null},{"id":"W783986","doi":"10.1023/a:1013022527681","title":"Accountability Testing Without Accountability?","year":2001,"lang":"en","type":"article","venue":"Interchange","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"","keywords":"Philosophy of education; Political science; Higher education; Law","score_opus":0.1549698558271588,"score_gpt":0.41791797016587584,"score_spread":0.262948114338717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W783986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79823786,0.000053703083,0.00009302621,0.0009397581,0.0005918534,0.0003048774,0.000003351097,0.00019181521,0.19958372],"genre_scores_gemma":[0.9960446,0.000032662127,0.00050842355,0.00038106882,0.00080512924,0.000045938395,0.0000027660917,0.000013135881,0.0021663245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99841434,0.00015155076,0.0002090078,0.0003103744,0.00046626123,0.00044847126],"domain_scores_gemma":[0.9990436,0.00030780307,0.000070374765,0.0002616561,0.00020719365,0.00010938135],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012385362,0.00013150054,0.00017251808,0.000064605745,0.00036123776,0.00016850201,0.00044662377,0.00009860918,0.0017947872],"category_scores_gemma":[0.00048278001,0.00012464887,0.000070055394,0.0004390703,0.00027607128,0.00048696453,0.00013813775,0.0001719011,0.00035471798],"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":[0.000022411381,0.00009303086,0.95870006,0.000006013001,0.000010678752,0.0000028832278,0.023402372,1.2387854e-7,0.00018268333,0.00044430766,0.00059896323,0.016536443],"study_design_scores_gemma":[0.00067986414,0.00012938373,0.62056375,0.00009283505,0.000041358617,0.0000058033784,0.05372221,0.00010667956,0.00005979748,0.0033007036,0.32071954,0.00057807274],"about_ca_topic_score_codex":0.010725414,"about_ca_topic_score_gemma":0.018316329,"teacher_disagreement_score":0.33813635,"about_ca_system_score_codex":0.00028575628,"about_ca_system_score_gemma":0.00007915661,"threshold_uncertainty_score":0.99959683},"labels":[],"label_agreement":null},{"id":"W870701221","doi":"","title":"Improving effectiveness of learning through class activity assessment : a case study","year":2010,"lang":"en","type":"book-chapter","venue":"Sunway Institutional Repository (Sunway University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Matriculation; Class (philosophy); Mathematics education; Curriculum; TRIPS architecture; Creativity; Process (computing); Pedagogy; Psychology; Computer science","score_opus":0.022662941449848477,"score_gpt":0.29380806370281526,"score_spread":0.2711451222529668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W870701221","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25849527,0.00003080481,0.00075103954,0.00001252713,0.001515855,0.001285791,0.000016317941,0.00012873128,0.73776364],"genre_scores_gemma":[0.84036255,0.000031107782,0.00027493757,0.0000029802818,0.00038268455,0.0000062172194,0.000014258035,0.00003146885,0.1588938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99642396,0.0006322417,0.0003662697,0.0008303675,0.0013239058,0.00042325017],"domain_scores_gemma":[0.99735826,0.0006802903,0.0007156783,0.00042584407,0.00062418357,0.00019573681],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0011128328,0.0004884462,0.000703235,0.0004340215,0.0038543101,0.00012733128,0.0006222147,0.00070070813,0.00013384175],"category_scores_gemma":[0.00008367939,0.00056321383,0.0004098852,0.0002498892,0.0013582199,0.0008172966,0.0003127522,0.0016455888,0.000012725306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006087236,0.0013927909,0.0239125,0.00041783578,0.0014702432,0.02492143,0.0092540905,0.0003976245,0.012371377,0.92333037,0.000016945325,0.0019060822],"study_design_scores_gemma":[0.011959056,0.003714611,0.013591723,0.0020435182,0.0045294533,0.0013049596,0.09109159,0.00019116179,0.0037518283,0.003340277,0.8585956,0.0058862283],"about_ca_topic_score_codex":0.007893243,"about_ca_topic_score_gemma":0.0022572828,"teacher_disagreement_score":0.91999006,"about_ca_system_score_codex":0.0015152107,"about_ca_system_score_gemma":0.0030143105,"threshold_uncertainty_score":0.99968195},"labels":[],"label_agreement":null},{"id":"W98146743","doi":"10.1007/978-94-007-5902-2_16","title":"Authentic Assessment, Teacher Judgment and Moderation in a Context of High Accountability","year":2014,"lang":"en","type":"book-chapter","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Accountability; Moderation; Context (archaeology); Psychology; Political science; Social psychology; History; Law; Archaeology","score_opus":0.030514511894305606,"score_gpt":0.3371362410140897,"score_spread":0.3066217291197841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W98146743","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31744078,0.0008931434,0.0057579177,0.0030750942,0.0023581623,0.005043742,0.000088737885,0.00012414462,0.6652183],"genre_scores_gemma":[0.95796627,0.00023202188,0.0004891652,0.000113107264,0.0001314654,0.00005064488,0.000030936986,0.000045965906,0.040940423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961929,0.00028486352,0.0010586826,0.00061110355,0.0014300972,0.00042238086],"domain_scores_gemma":[0.997518,0.0004493717,0.0009984577,0.0006196297,0.00031324793,0.00010127805],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034709407,0.0004250066,0.0009102262,0.00027783867,0.00027965993,0.00015792545,0.00054697006,0.00039034348,0.000777158],"category_scores_gemma":[0.000025721354,0.00035614436,0.00021031863,0.00011008405,0.0006266482,0.00019026679,0.00024311985,0.0006233383,0.0000055628284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015053188,0.0008335209,0.029019542,0.00041404046,0.00075213826,0.0000058334895,0.030892376,0.000094481955,0.0004079991,0.9210027,0.0014444622,0.014982393],"study_design_scores_gemma":[0.017006407,0.0032906309,0.26400355,0.004862257,0.0029910763,0.000006771932,0.13058701,0.007001617,0.0001909516,0.23155555,0.33214045,0.006363742],"about_ca_topic_score_codex":0.0034473022,"about_ca_topic_score_gemma":0.0057401485,"teacher_disagreement_score":0.6894471,"about_ca_system_score_codex":0.00058958394,"about_ca_system_score_gemma":0.000637068,"threshold_uncertainty_score":0.9998891},"labels":[],"label_agreement":null}]}