{"meta":{"query_hash":"4ea3f51b9638","filters":{"venue":"Assessing Writing"},"cohort_total":25,"direct_labels_cover":0,"predictions_cover":25,"exported":25,"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/4ea3f51b9638","api":"https://metacan.xera.ac/api/v1/cohort?venue=Assessing+Writing"},"results":[{"id":"W1984249886","doi":"10.1016/j.asw.2008.10.002","title":"How accurate are ESL students’ holistic writing scores on large-scale assessments?—A generalizability theory approach","year":2008,"lang":"en","type":"article","venue":"Assessing Writing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta; Francis Crick Institute","keywords":"Generalizability theory; Reliability (semiconductor); Variance components; Psychology; Variance (accounting); Rating scale; Scale (ratio); Mathematics education; Variation (astronomy); Statistics; Mathematics; Developmental psychology; Accounting; Geography","score_opus":0.13302029387377687,"score_gpt":0.35942210998721913,"score_spread":0.22640181611344226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984249886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94472826,0.00028409093,0.00989984,0.00021138364,0.00042767084,0.00022886317,0.000026715603,0.0005181329,0.043675024],"genre_scores_gemma":[0.98980093,0.00001314849,0.0030615423,0.00067271385,0.001895853,0.00004424292,0.00008053925,0.00010284481,0.0043281866],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99579895,0.0010902297,0.00057061244,0.0008054897,0.00085234205,0.00088238367],"domain_scores_gemma":[0.9978193,0.00075858535,0.0005263423,0.0005282813,0.00021429427,0.0001531985],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028584276,0.00045040256,0.00053696503,0.00018920466,0.004088159,0.0032024588,0.00052602874,0.00012146956,0.00013924665],"category_scores_gemma":[0.0005540972,0.0004173171,0.00020619556,0.00011214341,0.00035272798,0.001116696,0.00021493465,0.0011265867,0.000023420855],"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":[0.000090267975,0.0027744384,0.7152587,0.0010099995,0.00038859673,0.00033581178,0.07983955,0.0018019988,0.0006580344,0.17750156,0.0026396622,0.017701358],"study_design_scores_gemma":[0.005564654,0.00055055873,0.30713284,0.0041435254,0.00047499195,0.00023825106,0.5994053,0.036373544,0.0003661023,0.0056355833,0.03546541,0.0046492275],"about_ca_topic_score_codex":0.00007664643,"about_ca_topic_score_gemma":0.00002852087,"teacher_disagreement_score":0.51956576,"about_ca_system_score_codex":0.00015153157,"about_ca_system_score_gemma":0.00007573103,"threshold_uncertainty_score":0.99982786},"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":"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":"W2011139860","doi":"10.1016/j.asw.2013.05.001","title":"Assessing cohesion in children’s writing: Development of a checklist","year":2013,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":50,"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":"","keywords":"Cohesion (chemistry); Checklist; Inter-rater reliability; Writing assessment; Psychology; Internal consistency; Consistency (knowledge bases); Discriminative model; Mathematics education; Computer science; Applied psychology; Psychometrics; Rating scale; Cognitive psychology; Clinical psychology; Developmental psychology; Artificial intelligence","score_opus":0.03760340143721072,"score_gpt":0.3669574726933187,"score_spread":0.32935407125610794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011139860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96237636,0.00012708448,0.00039026025,0.00058088073,0.00012002074,0.00027848774,4.939319e-7,0.00014429027,0.0359821],"genre_scores_gemma":[0.9682068,0.000008366118,0.031071514,0.00007822562,0.0004002069,0.00005018333,0.0000172358,0.000029386396,0.00013808125],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997239,0.00032793937,0.00087351503,0.0003788767,0.00054733,0.0006333268],"domain_scores_gemma":[0.9985252,0.0004557157,0.00042118467,0.00017528291,0.00029199626,0.00013058864],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025976235,0.00017896264,0.00030371404,0.0002727582,0.0011320492,0.0011198639,0.0002698178,0.00016424074,0.0000986102],"category_scores_gemma":[0.00095665053,0.000207195,0.0000634418,0.0005840379,0.00019529584,0.0015735431,0.00006810775,0.00031916975,0.000025513113],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010074668,0.00020774684,0.76822406,0.00008045324,0.000012963792,0.0000015466625,0.012051096,0.000007733297,0.010304444,0.0017577283,0.00014184443,0.20720936],"study_design_scores_gemma":[0.00039680433,0.000008090785,0.9045373,0.0017335848,0.000011926281,0.0000058146607,0.08806507,0.00019138065,0.0039286725,0.00045874403,0.00028850848,0.00037410686],"about_ca_topic_score_codex":0.0026833385,"about_ca_topic_score_gemma":0.00022842547,"teacher_disagreement_score":0.20683526,"about_ca_system_score_codex":0.00029047302,"about_ca_system_score_gemma":0.0007793403,"threshold_uncertainty_score":0.9999171},"labels":[],"label_agreement":null},{"id":"W2030114591","doi":"10.1016/j.asw.2008.08.001","title":"ESL students’ perceptions and experiences of standardized English writing tests","year":2008,"lang":"en","type":"article","venue":"Assessing Writing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":45,"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":"Perception; Mathematics education; Report writing; Psychology; Writing assessment; Computer science; Pedagogy; Library science","score_opus":0.046513956045689954,"score_gpt":0.32831528546991157,"score_spread":0.2818013294242216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030114591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9692195,0.00032254806,0.00011569069,0.000028110477,0.00020212363,0.0000641209,0.000003273357,0.0001762438,0.029868377],"genre_scores_gemma":[0.99708056,0.000019006522,0.001607569,0.000053613116,0.00075485435,0.000013572364,0.0000053711938,0.000024650324,0.00044082582],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9985513,0.00015742712,0.0003979267,0.00024799607,0.0003701615,0.00027519112],"domain_scores_gemma":[0.99902576,0.00039441,0.00018686279,0.00012932549,0.00020109965,0.00006252814],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00074978004,0.00014725937,0.0002635195,0.000105753046,0.0018406803,0.00055580586,0.00014746455,0.000041032497,0.0002949738],"category_scores_gemma":[0.00044049468,0.0001425972,0.00006417285,0.000049848906,0.0004411326,0.00062134326,0.00008309812,0.00031049774,0.0000025190905],"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":[0.0000037725988,0.00006460582,0.094365515,0.00005789252,0.000023371143,0.000015191401,0.89576817,0.0000070311103,0.00064489065,0.0023115333,0.00015558151,0.0065824767],"study_design_scores_gemma":[0.00048318953,0.000058582955,0.018682048,0.0005336116,0.000024242177,0.000022846069,0.97748506,0.00014273117,0.000106084226,0.000039732076,0.0021656011,0.00025625815],"about_ca_topic_score_codex":0.000087552486,"about_ca_topic_score_gemma":0.00001733542,"teacher_disagreement_score":0.08171693,"about_ca_system_score_codex":0.000024649977,"about_ca_system_score_gemma":0.0000445254,"threshold_uncertainty_score":0.9994588},"labels":[],"label_agreement":null},{"id":"W2054609865","doi":"10.1016/j.asw.2009.01.001","title":"Drawing a line in the sand: Identifying the borderzone between self and other in EL1 and EL2 citation practices","year":2009,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":42,"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":"Citation; Reading (process); Computer science; Confusion; Mathematics education; Bounding overwatch; Psychology; Linguistics; Artificial intelligence; World Wide Web","score_opus":0.08522387649035286,"score_gpt":0.4273070635142424,"score_spread":0.34208318702388957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054609865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97612375,0.0009015016,0.00046807536,0.014215015,0.000030209017,0.00014939734,7.070116e-7,0.000026057738,0.008085267],"genre_scores_gemma":[0.99668926,0.00010214372,0.0018039874,0.001095104,0.00028928957,0.000002829248,0.0000011746034,0.0000044414933,0.000011762989],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99840117,0.000712222,0.00023145322,0.00015941655,0.00026348405,0.00023227918],"domain_scores_gemma":[0.99712986,0.0025260744,0.0002334451,0.000059695165,0.000029206918,0.000021698728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076193665,0.00007354927,0.00010925288,0.00007531873,0.0007924952,0.0007313596,0.00014283406,0.00018418008,0.000003513474],"category_scores_gemma":[0.0018312528,0.00005220249,0.000012916887,0.00034145307,0.000090278016,0.0008922994,0.000019384364,0.0009225411,6.558041e-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":[0.000005820722,0.000037514437,0.62295544,0.000031970103,0.000014405007,0.000011375538,0.2547852,0.000008173397,0.00055725494,0.011100421,0.000049708764,0.110442735],"study_design_scores_gemma":[0.00046583315,0.000021837213,0.7478644,0.0006603954,0.00005015106,0.0000070848955,0.22434221,0.0012679384,0.000039513492,0.020824024,0.0042291316,0.00022744677],"about_ca_topic_score_codex":0.002805779,"about_ca_topic_score_gemma":0.00081586256,"teacher_disagreement_score":0.124909006,"about_ca_system_score_codex":0.000029838982,"about_ca_system_score_gemma":0.0000571484,"threshold_uncertainty_score":0.70525175},"labels":[],"label_agreement":null},{"id":"W2090334593","doi":"10.1016/j.asw.2005.02.001","title":"Differences in written discourse in independent and integrated prototype tasks for next generation TOEFL","year":2005,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Educational Strategies and Epistemologies","field":"Psychology","cited_by":334,"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; University of Toronto","funders":"Educational Testing Service","keywords":"Test of English as a Foreign Language; Linguistics; Argument (complex analysis); Active listening; Computer science; Natural language processing; Reading (process); Test (biology); Psychology; Artificial intelligence; Language assessment; Communication","score_opus":0.14724768098608035,"score_gpt":0.4120701150341848,"score_spread":0.26482243404810446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090334593","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940862,0.00040120332,0.00044260517,0.0022744276,0.00015703606,0.00039949585,0.0000035303383,0.00002283258,0.0022126683],"genre_scores_gemma":[0.995907,0.000011930167,0.003185071,0.0001149189,0.00029810847,0.00031457344,0.00003904289,0.000010510178,0.00011885712],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990327,0.000090017464,0.00030167954,0.00025794483,0.00007422698,0.00024348064],"domain_scores_gemma":[0.99957836,0.00018398424,0.0000865825,0.000086926324,0.000038264134,0.000025912168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039540752,0.000106465195,0.00015565158,0.00009970579,0.00009618766,0.00025731634,0.000080592305,0.00009569255,0.00003675069],"category_scores_gemma":[0.00007364514,0.00009445318,0.00001824016,0.000121741316,0.00005337272,0.00035944136,0.000019296936,0.00017172596,0.0000027410235],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004330896,0.00026163243,0.85646,0.000050629966,0.00001747634,0.000009072796,0.00356892,0.000033451885,0.004233526,0.015985033,0.0002639577,0.11907299],"study_design_scores_gemma":[0.00061451085,0.0000835945,0.95080996,0.00015782424,0.000006570002,0.000013507452,0.04377053,0.0031856368,0.000116914445,0.00084774115,0.00020034642,0.00019285407],"about_ca_topic_score_codex":0.0007042761,"about_ca_topic_score_gemma":0.0011471787,"teacher_disagreement_score":0.11888013,"about_ca_system_score_codex":0.000070188886,"about_ca_system_score_gemma":0.00006711254,"threshold_uncertainty_score":0.38516888},"labels":[],"label_agreement":null},{"id":"W2745353075","doi":"10.1016/j.asw.2010.10.002","title":"","year":2010,"lang":"en","type":"article","venue":"Assessing Writing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","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 Ottawa","funders":"","keywords":"Task (project management); Computer science; Construct (python library); Test (biology); Term (time); Programming language; Engineering; Systems engineering","score_opus":0.03534371897042751,"score_gpt":0.29557694435065646,"score_spread":0.26023322538022897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745353075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9070356,0.000039698047,0.0003012285,0.0014360795,0.0013023281,0.00007522373,0.0000015622128,0.0008025227,0.089005746],"genre_scores_gemma":[0.988853,7.3971137e-7,0.0046130735,0.0007859981,0.004692645,0.000014685733,0.000012903803,0.00006664046,0.0009603446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9977268,0.00018809302,0.0005266255,0.0004675181,0.000356309,0.0007346621],"domain_scores_gemma":[0.9982885,0.00071606296,0.0002774686,0.00038143861,0.00017961688,0.0001569103],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020101487,0.00027926426,0.00029282997,0.00017133144,0.00411093,0.004292923,0.00034754555,0.00009103442,0.00040337883],"category_scores_gemma":[0.0007922123,0.00026823956,0.0001409635,0.000057837893,0.00038946077,0.0019613968,0.00009918003,0.0020823516,0.00002809155],"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":[0.000007288299,0.00016631641,0.080046095,0.00008676302,0.000046974295,0.00007149606,0.12861747,0.000051615814,0.07903767,0.553788,0.00023035878,0.15784998],"study_design_scores_gemma":[0.003072184,0.00025000537,0.07316445,0.0014263768,0.00020247162,0.00032537192,0.45373827,0.010554081,0.0041907644,0.0121423295,0.43743318,0.003500517],"about_ca_topic_score_codex":0.0009080186,"about_ca_topic_score_gemma":0.0014528756,"teacher_disagreement_score":0.54164565,"about_ca_system_score_codex":0.000020173344,"about_ca_system_score_gemma":0.00006259746,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W3129064581","doi":"10.1016/j.asw.2021.100524","title":"Development and validation of the Situated Academic Writing Self-Efficacy Scale (SAWSES)","year":2021,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"George & Fay Yee Centre for Healthcare Innovation; Health Sciences Centre; University of Manitoba; Red River College","funders":"","keywords":"Situated; Psychology; Situated learning; Scale (ratio); Writing assessment; Identity (music); Mathematics education; Context (archaeology); Creativity; Pedagogy; Test (biology); Discipline; Situated cognition; Social psychology; Computer science; Sociology","score_opus":0.038835730543190894,"score_gpt":0.3102553673130885,"score_spread":0.2714196367698976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129064581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9645197,0.0007188294,0.00004852014,0.00033056378,0.00010854759,0.000054605618,0.0000019466752,0.00006481053,0.034152515],"genre_scores_gemma":[0.9961395,0.000020354419,0.0030450292,0.00010894877,0.00027976715,0.0000047851954,0.00001071355,0.00001596615,0.00037488263],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99881285,0.00009632469,0.00042369415,0.00021253392,0.0002567504,0.00019784937],"domain_scores_gemma":[0.9991866,0.00020292826,0.00023232572,0.00014821763,0.00020616417,0.000023804738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004435821,0.00011901466,0.00020085396,0.000048654943,0.00084816344,0.00030680344,0.000112361675,0.000036970458,0.000087752465],"category_scores_gemma":[0.0001725231,0.000094849616,0.000058790647,0.00010810007,0.00014974756,0.00033119917,0.00019124005,0.00019972875,0.0000033731928],"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":[0.000006438552,0.0006877819,0.07111542,0.0008485304,0.0012600259,0.000057989146,0.47132152,0.0001536348,0.0376277,0.084417164,0.0006824727,0.3318213],"study_design_scores_gemma":[0.0012369867,0.00001603565,0.048087697,0.0036715034,0.0008751783,0.000042527943,0.70460093,0.0010755681,0.21936516,0.00070578844,0.019325072,0.0009975503],"about_ca_topic_score_codex":0.00001785727,"about_ca_topic_score_gemma":0.00006830461,"teacher_disagreement_score":0.33082375,"about_ca_system_score_codex":0.000031440977,"about_ca_system_score_gemma":0.00009022565,"threshold_uncertainty_score":0.6523473},"labels":[],"label_agreement":null},{"id":"W3164557766","doi":"10.1016/j.asw.2021.100543","title":"Young children’s written and verbal responses in a dynamic assessment context","year":2021,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":5,"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 Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Dynamic assessment; Mediation; Psychology; Context (archaeology); Writing assessment; Pedagogy; Developmental psychology; History; Sociology","score_opus":0.03191453582581855,"score_gpt":0.414839703847687,"score_spread":0.38292516802186843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164557766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9658997,0.0012506581,0.00028504597,0.0021967634,0.0005519777,0.00012191727,0.000015679841,0.000058910897,0.029619312],"genre_scores_gemma":[0.9945108,0.000028284272,0.0027559518,0.0010384702,0.00012685572,0.000058280042,0.00006542167,0.000023545243,0.0013923553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977801,0.0005202619,0.00044179108,0.000604995,0.00022299944,0.0004298436],"domain_scores_gemma":[0.9988163,0.00061595015,0.00012820186,0.00025697745,0.00008260968,0.00009995108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006414435,0.00019257184,0.00027132742,0.000111885,0.0002069732,0.00026797483,0.00013451112,0.00013833432,0.0005698002],"category_scores_gemma":[0.00010051234,0.00019465844,0.00005631154,0.00031079308,0.00009168778,0.00023488689,0.00008898889,0.00045405765,0.000030850737],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021600523,0.0004301709,0.93897593,0.0000122451165,0.000054258187,0.00020034876,0.001012682,7.6820874e-7,0.0015551464,0.0066431127,0.00023405916,0.05085967],"study_design_scores_gemma":[0.0009186464,0.000038075963,0.98523307,0.0001583817,0.00001648757,0.00039452923,0.011372272,0.00006128234,0.000017147291,0.0013308119,0.00023059131,0.00022870097],"about_ca_topic_score_codex":0.00018338527,"about_ca_topic_score_gemma":0.00009639489,"teacher_disagreement_score":0.05063097,"about_ca_system_score_codex":0.000118439304,"about_ca_system_score_gemma":0.0001504119,"threshold_uncertainty_score":0.7937941},"labels":[],"label_agreement":null},{"id":"W4293150134","doi":"10.1016/j.asw.2022.100652","title":"Editorial","year":2022,"lang":"en","type":"editorial","venue":"Assessing Writing","topic":"","field":"","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","funders":"","keywords":"Computer science","score_opus":0.015494018986418352,"score_gpt":0.3356426432754628,"score_spread":0.32014862428904445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293150134","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":[0.00004583168,0.0003643938,0.000017082752,0.000014231675,0.9660887,0.00019582054,0.0006450822,0.0012233852,0.031405464],"genre_scores_gemma":[0.00016378901,0.000012756631,0.0010056967,0.00001196507,0.99356663,0.0001266753,0.003450091,0.0008254908,0.0008368827],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99093837,0.00067058235,0.0009713485,0.0012643288,0.0050183567,0.0011370083],"domain_scores_gemma":[0.9921658,0.004902883,0.0011582188,0.0009139111,0.00067252124,0.00018666087],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.0038762481,0.0007200426,0.00089057384,0.00043532866,0.0015037642,0.002056367,0.0011551756,0.0014258345,0.0012266451],"category_scores_gemma":[0.009979642,0.00089778256,0.00033910328,0.00073953596,0.0001221059,0.0008837526,0.00096433697,0.0060346504,0.0011378974],"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":[0.000016759877,0.00005980218,0.000024641979,0.000119012795,0.00006809844,0.000059392645,0.000066686,0.000016116388,0.00042945685,0.000025316715,0.9973856,0.001729095],"study_design_scores_gemma":[0.0007038782,0.000038273236,0.0000029343182,0.00037539794,0.00016030771,0.0000035817789,0.0005517202,0.000038027174,0.000014210074,0.00012504747,0.9970578,0.0009288018],"about_ca_topic_score_codex":0.00026558433,"about_ca_topic_score_gemma":0.000010136862,"teacher_disagreement_score":0.030568583,"about_ca_system_score_codex":0.0015978327,"about_ca_system_score_gemma":0.0024444526,"threshold_uncertainty_score":0.99987054},"labels":[],"label_agreement":null},{"id":"W4308780555","doi":"10.1016/j.asw.2022.100677","title":"Editorial Volume 54","year":2022,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","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","funders":"","keywords":"Volume (thermodynamics); Computer science; Physics; Thermodynamics","score_opus":0.038559712156755015,"score_gpt":0.23344158319231248,"score_spread":0.19488187103555746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308780555","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":[0.07213816,0.0006278756,0.00034890953,0.00039724496,0.22722167,0.00009403851,0.00022395684,0.00012323688,0.6988249],"genre_scores_gemma":[0.93379295,0.000006854627,0.0006712098,0.00020394207,0.018681064,0.000028477858,0.000013309739,0.000019302022,0.046582893],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989294,0.0000138097785,0.0003679852,0.00035754804,0.00004944392,0.00028185337],"domain_scores_gemma":[0.9995037,0.000041380546,0.00022793429,0.00017105343,0.000016340766,0.00003963657],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010928693,0.00008412489,0.00021193082,0.00011375579,0.0009140078,0.00028203632,0.00020789495,0.000025734036,0.0095112305],"category_scores_gemma":[0.00008916925,0.00011897985,0.00008080607,0.00016820765,0.00004602609,0.00034124783,0.0002994602,0.00018091382,0.0028749593],"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":[0.0000021037467,0.000033866265,0.031472895,0.0000059917024,0.000024215446,0.0000027393908,0.000551917,0.00019776274,0.000012839896,0.030653713,0.9359942,0.0010477391],"study_design_scores_gemma":[0.00025426014,0.000012434002,0.0023119878,0.0000036625784,0.000002811433,0.0000025639436,0.0018592278,0.002188358,0.000002636944,0.002357256,0.99082845,0.00017636544],"about_ca_topic_score_codex":0.00017609692,"about_ca_topic_score_gemma":0.0000010012345,"teacher_disagreement_score":0.8616548,"about_ca_system_score_codex":0.00015703055,"about_ca_system_score_gemma":0.00002054376,"threshold_uncertainty_score":0.99790144},"labels":[],"label_agreement":null},{"id":"W4320498557","doi":"10.1016/j.asw.2022.100691","title":"Comparing summative and dynamic assessments of L2 written argumentative discourse: Microgenetic validity evidence","year":2023,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Educational and Psychological Assessments","field":"Psychology","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":"York University","funders":"","keywords":"Summative assessment; Argumentative; Dialogic; Mediation; Argumentation theory; Psychology; Argument (complex analysis); Dynamic assessment; Protocol analysis; Construct (python library); Formative assessment; Mathematics education; Cognitive psychology; Linguistics; Computer science; Pedagogy; Cognitive science; Developmental psychology; Sociology","score_opus":0.2598054623629933,"score_gpt":0.5350411908807765,"score_spread":0.2752357285177832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320498557","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99132675,0.0004242029,0.0009936207,0.00059321796,0.0004668519,0.0002323535,0.000019311194,0.00009252381,0.0058511677],"genre_scores_gemma":[0.9959097,0.000062854575,0.0032076875,0.0001073639,0.000073051284,0.00006547214,0.000054662232,0.000025043999,0.0004941727],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976772,0.00047921223,0.0005323331,0.0005405232,0.00033344078,0.00043731165],"domain_scores_gemma":[0.9976856,0.0014671003,0.0003733316,0.00025053974,0.00011792155,0.000105495616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010132558,0.0002189387,0.00036128197,0.0001576032,0.00026587496,0.00013941526,0.00024246768,0.000089776455,0.00016998447],"category_scores_gemma":[0.00010141724,0.00020656388,0.00006996513,0.0005366859,0.0002553662,0.00037814456,0.00015129251,0.00027336818,0.00006948712],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028618899,0.0003156081,0.9516743,0.00013808011,0.00022284029,0.000031991385,0.0036399262,0.00001598006,0.015119439,0.0014927709,0.000479597,0.026840858],"study_design_scores_gemma":[0.0004241585,0.00010232803,0.96845895,0.00066916447,0.000068950976,0.000018162787,0.026361985,0.0006184061,0.00038205326,0.0026390261,0.000022550545,0.0002342366],"about_ca_topic_score_codex":0.00009307525,"about_ca_topic_score_gemma":0.000006968981,"teacher_disagreement_score":0.026606621,"about_ca_system_score_codex":0.00007008985,"about_ca_system_score_gemma":0.000056130815,"threshold_uncertainty_score":0.84234303},"labels":[],"label_agreement":null},{"id":"W4385604245","doi":"10.1016/j.asw.2023.100772","title":"Editorial","year":2023,"lang":"en","type":"editorial","venue":"Assessing Writing","topic":"","field":"","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","funders":"","keywords":"Computer science; Political science","score_opus":0.022407364135061943,"score_gpt":0.36005804676003106,"score_spread":0.3376506826249691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385604245","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":[0.000033942655,0.00011085162,0.000026497319,0.000017853907,0.98588645,0.00016129011,0.00045747298,0.0035221055,0.009783558],"genre_scores_gemma":[0.00006744512,0.000018395478,0.0008142572,0.0000044324884,0.99431497,0.00006194307,0.0022769757,0.0012752615,0.0011663268],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99221605,0.00034804776,0.0010012015,0.0012114446,0.0038574748,0.001365801],"domain_scores_gemma":[0.98586506,0.0109594045,0.0009641147,0.00084429857,0.0011402965,0.00022681346],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0037134208,0.0007499485,0.00093112065,0.0004964798,0.00071316503,0.002583549,0.00090567535,0.0026529743,0.00004658351],"category_scores_gemma":[0.029355058,0.00087275595,0.00032198982,0.001009686,0.00014419512,0.00083958113,0.00049917423,0.0039021387,0.012804332],"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":[0.000009178414,0.00002575088,0.000014265078,0.00019114511,0.000074847325,0.00006525092,0.00004421322,0.0000073519086,0.000531354,0.000014526077,0.99723655,0.0017855839],"study_design_scores_gemma":[0.00058296375,0.000020303654,0.000006605851,0.0018004809,0.0001498275,8.6591007e-7,0.00023508556,0.00006926321,0.000025514208,0.00018505311,0.99603266,0.0008913887],"about_ca_topic_score_codex":0.0002846173,"about_ca_topic_score_gemma":0.000033519307,"teacher_disagreement_score":0.025641637,"about_ca_system_score_codex":0.00074921263,"about_ca_system_score_gemma":0.001743938,"threshold_uncertainty_score":0.9993723},"labels":[],"label_agreement":null},{"id":"W4391746548","doi":"10.1016/j.asw.2024.100816","title":"Editorial","year":2024,"lang":"en","type":"editorial","venue":"Assessing Writing","topic":"Multilingual Education and Policy","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","funders":"","keywords":"Computer science","score_opus":0.04970023882696859,"score_gpt":0.5174696279487043,"score_spread":0.4677693891217357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391746548","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":[0.000027397216,0.0003682237,0.000004257091,0.00042733215,0.7648223,0.00007513372,0.000021056887,0.00029225255,0.23396203],"genre_scores_gemma":[0.00046234467,0.00013858698,0.00028539688,0.000053884112,0.98054516,0.000014887645,0.00010909754,0.00006084317,0.018329768],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971563,0.00026079637,0.0003598022,0.00040399615,0.0013209926,0.0004980927],"domain_scores_gemma":[0.99685735,0.0021395439,0.00018060346,0.00019588316,0.00044947845,0.00017716397],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020354157,0.00020557558,0.00025723432,0.00016377177,0.00086686306,0.0022860079,0.0003688309,0.0011348858,0.00019936496],"category_scores_gemma":[0.008634564,0.0002264211,0.00013484902,0.0003215261,0.0001699209,0.0002872212,0.000069966954,0.0014576359,0.00046852554],"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":[7.8896164e-7,0.000012387414,0.0000028793568,0.00008068228,0.000011803304,0.0000026571768,0.006560573,1.8347173e-7,0.0000037443501,0.0013512048,0.9749626,0.017010523],"study_design_scores_gemma":[0.00006492622,0.0000037841558,6.436132e-7,0.00048871996,0.000036777663,8.714846e-8,0.00450363,0.000005672624,0.000001802236,0.0005525787,0.9940962,0.00024514252],"about_ca_topic_score_codex":0.0056868237,"about_ca_topic_score_gemma":0.00038786055,"teacher_disagreement_score":0.21572287,"about_ca_system_score_codex":0.00034661594,"about_ca_system_score_gemma":0.005505015,"threshold_uncertainty_score":0.9997161},"labels":[],"label_agreement":null},{"id":"W4393332720","doi":"10.1016/j.asw.2024.100840","title":"The assessment of writing in languages other than English (LOTE)","year":2024,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Writing and Handwriting Education","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 Ottawa","funders":"","keywords":"Computer science; Writing assessment; Psychology; Mathematics education","score_opus":0.02509129208089634,"score_gpt":0.42187727859207613,"score_spread":0.3967859865111798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393332720","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7398453,0.0016716629,0.00024004339,0.002009411,0.00056655024,0.00013657281,0.0000031893055,0.000268524,0.25525877],"genre_scores_gemma":[0.99585164,0.0000716157,0.0018945384,0.000051528543,0.0014756857,0.000020490801,0.0000032914809,0.000028943732,0.0006022671],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9979849,0.00042703596,0.00045756795,0.00026013903,0.00042096028,0.00044938756],"domain_scores_gemma":[0.99722016,0.0022888111,0.00012397957,0.00016030675,0.00015423768,0.000052487332],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0051695243,0.00011266236,0.00016048233,0.00013449967,0.0008319926,0.0011989061,0.00023957145,0.00009213934,0.000023433515],"category_scores_gemma":[0.0011758553,0.00009905746,0.00007622933,0.0005441147,0.00020825952,0.00042859014,0.000041085874,0.00035993799,0.0000031181698],"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":[0.0000023899488,0.00013171628,0.32170078,0.00039792378,0.000050314735,0.000032599317,0.05917193,0.00004350636,0.0031900567,0.34834737,0.00084448094,0.26608694],"study_design_scores_gemma":[0.00035833564,0.000033350207,0.15005602,0.0071146395,0.000049123253,0.000005908555,0.7979735,0.0028059718,0.0007661737,0.0030238382,0.03724554,0.0005675542],"about_ca_topic_score_codex":0.002158929,"about_ca_topic_score_gemma":0.0016887387,"teacher_disagreement_score":0.7388016,"about_ca_system_score_codex":0.00016052429,"about_ca_system_score_gemma":0.00045771166,"threshold_uncertainty_score":0.99983793},"labels":[],"label_agreement":null},{"id":"W4398223715","doi":"10.1016/j.asw.2024.100857","title":"Volume 60 editorial","year":2024,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Writing and Handwriting Education","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","funders":"","keywords":"Volume (thermodynamics); Computer science; Physics","score_opus":0.02832199549884386,"score_gpt":0.389593630793365,"score_spread":0.36127163529452117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398223715","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":[0.33406994,0.0017745266,0.0014753866,0.009436208,0.11926989,0.00018216757,0.000005126099,0.002341258,0.5314455],"genre_scores_gemma":[0.86132014,0.000018946108,0.0012784685,0.000061564795,0.13389872,0.000009167058,0.000006980143,0.000020915553,0.00338511],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856,0.00016044683,0.00020749465,0.00025849495,0.00043348546,0.00038007647],"domain_scores_gemma":[0.99921244,0.00043143443,0.000041523803,0.00009733761,0.00012388398,0.00009336783],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002016304,0.00008627534,0.000099181256,0.00009633702,0.0011048752,0.0021340183,0.00013867095,0.00012559471,0.00012812385],"category_scores_gemma":[0.0008458725,0.00009756118,0.00006360959,0.00036269886,0.00011964267,0.0006834229,0.00002269449,0.00028624348,0.0001830874],"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":[0.0000028435006,0.000084388805,0.00859092,0.00023422993,0.000037937094,0.000067131354,0.026879655,0.000012633438,0.0024495318,0.08296627,0.5367526,0.3419219],"study_design_scores_gemma":[0.000074129144,0.000009214575,0.0010774902,0.0007431776,0.000022592258,0.0000040482687,0.02440586,0.000534811,0.0000672109,0.0024700589,0.9703686,0.00022275958],"about_ca_topic_score_codex":0.0008235318,"about_ca_topic_score_gemma":0.00006414395,"teacher_disagreement_score":0.5280604,"about_ca_system_score_codex":0.00014529216,"about_ca_system_score_gemma":0.0005351891,"threshold_uncertainty_score":0.99890184},"labels":[],"label_agreement":null},{"id":"W4401972053","doi":"10.1016/j.asw.2024.100879","title":"Editorial","year":2024,"lang":"en","type":"editorial","venue":"Assessing Writing","topic":"","field":"","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","funders":"","keywords":"Computer science","score_opus":0.014525430278851831,"score_gpt":0.34823349385086116,"score_spread":0.33370806357200933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401972053","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":[0.000024415147,0.0013175204,0.000025421044,0.000025657606,0.9582237,0.0001632559,0.00048099278,0.0022240398,0.037514973],"genre_scores_gemma":[0.00022563958,0.000018129367,0.0011221896,0.000007422822,0.9944273,0.000049838127,0.0013782699,0.0010553141,0.0017158862],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928687,0.00025521146,0.000965389,0.0013536764,0.0034697761,0.001087236],"domain_scores_gemma":[0.99416703,0.0035056858,0.00053991494,0.00073817844,0.000851829,0.00019737189],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0027817192,0.0008097941,0.0008658107,0.000498506,0.0004495272,0.005093731,0.00076228933,0.0026400387,0.000086390995],"category_scores_gemma":[0.007335353,0.00087488285,0.0003785115,0.0007313911,0.00014542874,0.0008411978,0.0005019701,0.005470343,0.012405211],"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":[0.0000075537123,0.000026500935,0.0000037164823,0.00051889627,0.00010471138,0.00010447369,0.00006316123,0.0000024762307,0.00067763415,0.000057691148,0.99617064,0.0022625392],"study_design_scores_gemma":[0.0003340544,0.000021252476,6.813964e-7,0.0038118465,0.0003304994,0.0000039974193,0.00017263457,0.000090848574,0.000038342503,0.0006219231,0.9936704,0.0009035187],"about_ca_topic_score_codex":0.00014890509,"about_ca_topic_score_gemma":0.000014653974,"teacher_disagreement_score":0.036203586,"about_ca_system_score_codex":0.0009252859,"about_ca_system_score_gemma":0.0021970584,"threshold_uncertainty_score":0.9993702},"labels":[],"label_agreement":null},{"id":"W4405076882","doi":"10.1016/j.asw.2024.100900","title":"Editorial","year":2024,"lang":"en","type":"editorial","venue":"Assessing Writing","topic":"Educational Practices and Policies","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","funders":"","keywords":"Computer science; Political science","score_opus":0.03282349700658276,"score_gpt":0.44890205077151996,"score_spread":0.4160785537649372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405076882","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":[0.000018682356,0.0009105783,0.0000031000266,0.0020971529,0.7946409,0.00005507041,0.00002308233,0.00016055703,0.2020909],"genre_scores_gemma":[0.00038052254,0.0004958021,0.0002658531,0.00004586019,0.9881736,0.000014118044,0.00010131735,0.00004721124,0.01047572],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99727577,0.00025883573,0.00028691816,0.00031291152,0.0014559759,0.00040960815],"domain_scores_gemma":[0.9933662,0.0057229013,0.00022820692,0.00014917871,0.00042759278,0.00010591494],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002336273,0.00016966037,0.00020687318,0.00010436727,0.0010462404,0.0030884214,0.00033221312,0.00083977025,0.00011884961],"category_scores_gemma":[0.0072811726,0.00018157088,0.00010975097,0.00025599357,0.00017049762,0.00070545124,0.00007566599,0.0016371637,0.00033434317],"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":[8.254282e-7,0.000011251655,0.000005974262,0.00007659761,0.000018663664,0.00000220758,0.002736396,3.646653e-7,0.0000025805768,0.0054588416,0.990029,0.0016573117],"study_design_scores_gemma":[0.000033729473,0.000004985383,0.000001176966,0.0004629882,0.00006229063,1.3665544e-7,0.007315352,0.0000017892094,5.280042e-7,0.0022618845,0.98964673,0.00020843477],"about_ca_topic_score_codex":0.0071080653,"about_ca_topic_score_gemma":0.0005354635,"teacher_disagreement_score":0.19353272,"about_ca_system_score_codex":0.0002613528,"about_ca_system_score_gemma":0.004068429,"threshold_uncertainty_score":0.9995037},"labels":[],"label_agreement":null},{"id":"W4407175549","doi":"10.1016/j.asw.2025.100917","title":"Editorial Volume 63","year":2025,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Qualitative Comparative Analysis Research","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","funders":"","keywords":"Volume (thermodynamics); Computer science; Physics","score_opus":0.07895528228151413,"score_gpt":0.5278506201667453,"score_spread":0.44889533788523117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407175549","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":[0.046653014,0.0002840138,0.020994578,0.004873338,0.0186507,0.00015415662,0.0000016281485,0.00016683791,0.9082217],"genre_scores_gemma":[0.9546655,0.000010912196,0.0014012012,0.00013198593,0.030352438,0.000012560739,0.0000033429542,0.0000061181086,0.01341596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750847,0.0010646738,0.00022962541,0.00022576125,0.0006038839,0.00036761875],"domain_scores_gemma":[0.99813724,0.0010912495,0.0000698547,0.00012794902,0.0005077072,0.00006602558],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003067499,0.00007411091,0.0001657671,0.00016562527,0.0013395251,0.00073039974,0.00027750863,0.00007587846,0.00036016834],"category_scores_gemma":[0.0030663593,0.00007993318,0.00007397148,0.0009602745,0.00032340508,0.0005367436,0.00007896473,0.00025355114,0.00015866815],"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":[0.0000047435933,0.000050966275,0.030865109,0.000018047325,0.000060726325,0.00000250956,0.0056560175,0.000010570715,0.0024279286,0.12923065,0.81129926,0.020373452],"study_design_scores_gemma":[0.00017711335,0.000007339335,0.0053279307,0.000113312475,0.000015864482,3.7249556e-8,0.03113435,0.00058714655,0.00018525253,0.011097806,0.95121604,0.00013780854],"about_ca_topic_score_codex":0.0009608729,"about_ca_topic_score_gemma":0.00024432087,"teacher_disagreement_score":0.90801245,"about_ca_system_score_codex":0.00018134173,"about_ca_system_score_gemma":0.00057531433,"threshold_uncertainty_score":0.9999606},"labels":[],"label_agreement":null},{"id":"W4407312812","doi":"10.1016/j.asw.2025.100923","title":"Validation of the individual and collective self-efficacy scale for teaching writing in post-secondary faculty","year":2025,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Writing and Handwriting Education","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":"George & Fay Yee Centre for Healthcare Innovation; University of Manitoba","funders":"University of Manitoba","keywords":"Scale (ratio); Computer science; Mathematics education; Psychology; Pedagogy; Physics","score_opus":0.03487157859887858,"score_gpt":0.3808766912933596,"score_spread":0.34600511269448103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407312812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9686614,0.00008871998,0.00019170299,0.0019160506,0.00016515394,0.0004020597,0.000017863891,0.00007104411,0.028485954],"genre_scores_gemma":[0.9927507,0.0000032555206,0.0066287783,0.0001414129,0.00017934512,0.000031566276,0.00002037161,0.0000108790455,0.00023369752],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983687,0.00043914255,0.00040596377,0.0002585067,0.00022888984,0.00029883196],"domain_scores_gemma":[0.99773014,0.0016819688,0.00023466971,0.00009983322,0.00022031949,0.00003305597],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0035110388,0.000102076294,0.00018406108,0.00016684298,0.001856062,0.00040399257,0.00018840433,0.00011023839,0.0000028769966],"category_scores_gemma":[0.002522988,0.000101064354,0.000060642542,0.0004278974,0.00016426122,0.0004039097,0.000075122174,0.00032778972,1.6675257e-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":[0.000022589691,0.0007293757,0.48803505,0.00060837565,0.00009188365,9.090177e-7,0.17819808,0.000049710874,0.009043137,0.020287137,0.00074305857,0.3021907],"study_design_scores_gemma":[0.0013237288,0.000029562096,0.7246372,0.0019349913,0.00009379893,0.0000023324787,0.26234564,0.00034041968,0.0050530415,0.0034005484,0.00057572365,0.00026298664],"about_ca_topic_score_codex":0.00057880615,"about_ca_topic_score_gemma":0.00021377162,"teacher_disagreement_score":0.30192772,"about_ca_system_score_codex":0.00017617182,"about_ca_system_score_gemma":0.0009633936,"threshold_uncertainty_score":0.9994434},"labels":[],"label_agreement":null},{"id":"W4409342023","doi":"10.1016/j.asw.2025.100938","title":"Editorial","year":2025,"lang":"en","type":"editorial","venue":"Assessing Writing","topic":"","field":"","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","funders":"","keywords":"Computer science","score_opus":0.011465119646656878,"score_gpt":0.34411057517511945,"score_spread":0.3326454555284626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409342023","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":[0.000012207393,0.00039721339,0.000102399434,0.000021094613,0.92363006,0.00018599414,0.00038930855,0.001139869,0.074121855],"genre_scores_gemma":[0.000094984396,0.000016917153,0.0019480276,0.000014867141,0.99316955,0.000050116458,0.0016192186,0.0003560283,0.0027302883],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99355274,0.00038419123,0.0010009756,0.0011717699,0.0028408286,0.0010494995],"domain_scores_gemma":[0.990596,0.0061168987,0.00084243255,0.00087903143,0.0014148473,0.00015081975],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0025418783,0.00074837374,0.0009803221,0.00053118105,0.00071577594,0.0024614292,0.0009472561,0.0027656013,0.00006153065],"category_scores_gemma":[0.016853457,0.00087454193,0.00032143816,0.00078082905,0.00013297508,0.0007782692,0.0004946951,0.0040151644,0.0010200983],"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":[0.000013411161,0.000042718653,0.000019565197,0.0003221185,0.000085871834,0.00002227423,0.000025257743,0.000004071487,0.00034640508,0.0000535567,0.99533904,0.0037257224],"study_design_scores_gemma":[0.0007109497,0.000014984686,0.0000032546827,0.0032537866,0.00022914092,7.406868e-7,0.00013201834,0.000043763084,0.000053451204,0.00023241434,0.99455667,0.0007688402],"about_ca_topic_score_codex":0.000222652,"about_ca_topic_score_gemma":0.000017807117,"teacher_disagreement_score":0.07139157,"about_ca_system_score_codex":0.0008947085,"about_ca_system_score_gemma":0.003729686,"threshold_uncertainty_score":0.9997577},"labels":[],"label_agreement":null},{"id":"W4411867672","doi":"10.1016/j.asw.2025.100963","title":"Editorial Volume 65","year":2025,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","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","funders":"","keywords":"Volume (thermodynamics); Computer science; Physics; Thermodynamics","score_opus":0.02846164383884516,"score_gpt":0.2503316272447193,"score_spread":0.22186998340587413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411867672","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":[0.010363391,0.0005275297,0.0015656827,0.00036361467,0.12892611,0.000051774226,0.00003162056,0.00007288417,0.8580974],"genre_scores_gemma":[0.77168834,0.000031754866,0.0018239421,0.00036339005,0.02089541,0.000013740358,0.000007737105,0.000015781283,0.20515992],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989727,0.000006298076,0.0003942935,0.0003447457,0.000022923983,0.00025904423],"domain_scores_gemma":[0.999552,0.000056134137,0.0001514,0.00018009194,0.000030981635,0.000029359559],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006995546,0.00009014334,0.00023847258,0.00015440692,0.0003320209,0.00042662787,0.0001637182,0.00006494184,0.00094987475],"category_scores_gemma":[0.0002109482,0.00011571666,0.00007643104,0.00019638649,0.000067556764,0.0003834636,0.000116151394,0.00011005855,0.003829198],"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":[0.0000012144171,0.000017114151,0.031013524,0.000014371845,0.000030689713,6.5559544e-7,0.00009131606,0.0000141480705,0.0000105736435,0.096558,0.8706266,0.0016217872],"study_design_scores_gemma":[0.00028392702,0.0000036707772,0.0045683812,0.000040793086,0.0000049112846,3.0437988e-7,0.0008681794,0.0011189609,0.000013465141,0.008587454,0.9843608,0.000149145],"about_ca_topic_score_codex":0.0000846628,"about_ca_topic_score_gemma":0.0000017092934,"teacher_disagreement_score":0.76132494,"about_ca_system_score_codex":0.00008641688,"about_ca_system_score_gemma":0.000025495525,"threshold_uncertainty_score":0.9999634},"labels":[],"label_agreement":null},{"id":"W4416807726","doi":"10.1016/j.asw.2025.100992","title":"How reliable and valid is peer evaluation in adolescents’ L2 argumentative writing?","year":2025,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Writing and Handwriting Education","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":"University of British Columbia","keywords":"Argumentative; Grammar; Peer assessment; Reliability (semiconductor); Literacy; Peer feedback; Second language writing","score_opus":0.05378053516253805,"score_gpt":0.4197787474552024,"score_spread":0.3659982122926643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416807726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9203585,0.0006612993,0.00024576302,0.017910255,0.0003370977,0.00035524796,0.0000021237113,0.00011028207,0.06001944],"genre_scores_gemma":[0.99475807,0.000041395848,0.0018806946,0.0006838376,0.00032373404,0.000045700483,0.000010467992,0.000014834679,0.0022412417],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9977475,0.00036630238,0.00032970172,0.00042479095,0.00067386625,0.00045786635],"domain_scores_gemma":[0.9988355,0.00024146032,0.00017026677,0.00013784897,0.00054292846,0.00007196763],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0051207454,0.00014323808,0.00019882659,0.00024675115,0.0010813542,0.0015975806,0.00013745036,0.00013120742,0.000020249376],"category_scores_gemma":[0.0017043198,0.0001733319,0.000040804898,0.0006286618,0.00016362332,0.00083468785,0.000051576408,0.00029458597,0.0000033327417],"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":[0.000007408028,0.00016251374,0.858923,0.0002541493,0.000019639958,0.000004295859,0.022672685,0.000009535001,0.0010988424,0.010527331,0.0025828534,0.10373771],"study_design_scores_gemma":[0.0023721033,0.000033721517,0.366957,0.0103728,0.00015111805,0.0000041505195,0.5915356,0.0036314987,0.00249535,0.014178547,0.0075109983,0.0007570799],"about_ca_topic_score_codex":0.0012465597,"about_ca_topic_score_gemma":0.0003184175,"teacher_disagreement_score":0.5688629,"about_ca_system_score_codex":0.00034936628,"about_ca_system_score_gemma":0.00045837992,"threshold_uncertainty_score":0.9994389},"labels":[],"label_agreement":null},{"id":"W4416928479","doi":"10.1016/j.asw.2025.100999","title":"Editorial","year":2025,"lang":"en","type":"article","venue":"Assessing Writing","topic":"","field":"","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","funders":"","keywords":"","score_opus":0.014980696409922244,"score_gpt":0.3543906919912525,"score_spread":0.3394099955813303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416928479","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":[0.24639055,0.00025592002,0.003119997,0.0003605108,0.2078463,0.00014485067,0.0000061162386,0.0013001413,0.5405756],"genre_scores_gemma":[0.90870243,4.925532e-7,0.0037339996,0.0001037278,0.08706285,0.0000072536245,0.0000061272412,0.000032704247,0.00035041786],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99892104,0.00007607393,0.00022677402,0.00022403816,0.00024860603,0.00030346875],"domain_scores_gemma":[0.9992756,0.0002877649,0.00007381934,0.00019779312,0.00013070527,0.00003428521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006910595,0.00010192719,0.00012915207,0.0001345471,0.0003282671,0.00049358455,0.00015150789,0.00008176304,0.000024302037],"category_scores_gemma":[0.00068393187,0.00011306397,0.00004720417,0.0004910759,0.000045485373,0.0004438757,0.00008549488,0.00023579842,0.00040222864],"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":[0.0000077489285,0.00005284778,0.021651443,0.000044327684,0.000030829404,0.000007367464,0.000064167376,0.000024763116,0.09267203,0.010111203,0.8407083,0.034624986],"study_design_scores_gemma":[0.0016221236,0.00001429041,0.016323669,0.0012447299,0.000089588284,0.000006403549,0.0019199243,0.0021422566,0.012183555,0.0066294875,0.9572718,0.0005521557],"about_ca_topic_score_codex":0.000034330307,"about_ca_topic_score_gemma":0.000003156197,"teacher_disagreement_score":0.66231185,"about_ca_system_score_codex":0.000114540366,"about_ca_system_score_gemma":0.00017046637,"threshold_uncertainty_score":0.516997},"labels":[],"label_agreement":null}]}