{"meta":{"query_hash":"07872ab30370","filters":{"venue":"Journal of Educational Measurement"},"cohort_total":26,"direct_labels_cover":0,"predictions_cover":26,"exported":26,"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/07872ab30370","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Educational+Measurement"},"results":[{"id":"W1595860368","doi":"10.1111/jedm.12072","title":"Extended Mixed‐Effects Item Response Models With the MH‐RM Algorithm","year":2015,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Item response theory; Random effects model; Curse of dimensionality; Rasch model; Mixed model; Mathematics; Algorithm; Statistics; Monte Carlo method; Linear regression; Generalized linear mixed model; Computer science; Econometrics; Psychometrics; Meta-analysis","score_opus":0.6020280900847433,"score_gpt":0.46003750662039183,"score_spread":0.1419905834643515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595860368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5485995,0.008544053,0.34651715,0.08312626,0.0077150655,0.0005823873,0.0000055564365,0.000016790094,0.0048932605],"genre_scores_gemma":[0.86920977,0.00000923224,0.128939,0.0004969473,0.0006752289,0.000013339377,2.1226145e-7,0.0000108754075,0.0006453835],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9919619,0.0018621321,0.000728255,0.00022162174,0.005000205,0.00022591223],"domain_scores_gemma":[0.9642231,0.029295655,0.001064414,0.00042761897,0.004683754,0.0003054469],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042124245,0.00014136368,0.0002961473,0.00046045007,0.00015586088,0.00019620844,0.0008703302,0.000041229832,0.00005347324],"category_scores_gemma":[0.12234189,0.00006653568,0.000121561214,0.001230427,0.00008188427,0.00034092143,0.00005188826,0.00025657198,0.000020929749],"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":[0.0031421983,0.0014453618,0.01330512,0.000015070629,0.00045894188,0.000039625917,0.0039348314,0.007917592,0.0018128294,0.0046340576,0.52108735,0.44220704],"study_design_scores_gemma":[0.002815478,0.002226306,0.6282098,0.00025842653,0.0001315697,0.00092587114,0.0077035204,0.0038900159,0.0011934007,0.31057557,0.04164381,0.0004261646],"about_ca_topic_score_codex":0.000007289361,"about_ca_topic_score_gemma":0.0000028075478,"teacher_disagreement_score":0.6149047,"about_ca_system_score_codex":0.0003165869,"about_ca_system_score_gemma":0.0014482212,"threshold_uncertainty_score":0.9863347},"labels":[],"label_agreement":null},{"id":"W1968457467","doi":"10.1111/j.1745-3984.2006.00019.x","title":"Testing Features of Graphical DIF: Application of a Regression Correction to Three Nonparametric Statistical Tests","year":2006,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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 Alberta","funders":"","keywords":"Differential item functioning; Nonparametric statistics; Statistics; Statistical hypothesis testing; Context (archaeology); Mathematics; Statistical power; Item response theory; Matching (statistics); Test (biology); Regression analysis; Econometrics; Computer science; Psychometrics","score_opus":0.32495067350014345,"score_gpt":0.45965203750100464,"score_spread":0.1347013640008612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968457467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6878451,0.0013583046,0.30320123,0.0020957678,0.0028404866,0.00036892487,0.000012030116,0.0000073373585,0.0022708192],"genre_scores_gemma":[0.8660614,0.0000018830392,0.1335632,0.000025430001,0.00030850703,0.000007125321,0.0000010910973,0.00000590706,0.000025484964],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944184,0.00030600317,0.0015436087,0.00024366392,0.0033199186,0.00016842355],"domain_scores_gemma":[0.9664418,0.026119238,0.0020712046,0.00030120552,0.0049236016,0.00014294717],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0088590635,0.0001247831,0.0004129211,0.0014269868,0.00008324292,0.000041192154,0.00045932102,0.00005667575,0.000047659145],"category_scores_gemma":[0.21138297,0.00008334225,0.00012108552,0.0040737106,0.00007461554,0.00011445616,0.000044393542,0.00021950727,0.0000037615073],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013270942,0.0006661367,0.76439,0.000017670123,0.00002301591,5.708511e-7,0.000036226415,0.0013388293,0.0311418,0.001936294,0.015865209,0.18445155],"study_design_scores_gemma":[0.00022190258,0.00034021743,0.93906564,0.00014663252,0.000025619693,0.00004628023,0.00006508327,0.00029031507,0.0014067581,0.058068745,0.0002494303,0.00007338991],"about_ca_topic_score_codex":0.00018860663,"about_ca_topic_score_gemma":0.000052924825,"teacher_disagreement_score":0.2025239,"about_ca_system_score_codex":0.0001457562,"about_ca_system_score_gemma":0.00037630348,"threshold_uncertainty_score":0.7952599},"labels":[],"label_agreement":null},{"id":"W1991537194","doi":"10.1111/j.1745-3984.2007.00042.x","title":"Making Diagnostic Inferences About Cognitive Attributes Using the Rule‐Space Model and Attribute Hierarchy Method","year":2007,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":82,"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":"Hierarchy; Computer science; Artificial intelligence; Cognition; Space (punctuation); Machine learning; Task (project management); Data mining; Psychology","score_opus":0.17552894455626744,"score_gpt":0.3829384330597237,"score_spread":0.20740948850345625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991537194","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":[0.06530953,0.0026258684,0.9273871,0.003753263,0.00066114316,0.00012702422,0.0000016693095,0.0000051783923,0.00012918089],"genre_scores_gemma":[0.9317951,0.000029706258,0.06738267,0.0001907997,0.0004908615,0.000003091204,2.9477823e-7,0.0000064220635,0.000101017744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99790317,0.00020225214,0.000495345,0.0001749461,0.00096170197,0.00026259795],"domain_scores_gemma":[0.99528646,0.0022671872,0.0005984638,0.00011379576,0.0016330029,0.00010107776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00550987,0.00013917626,0.00019625729,0.00016943096,0.0003720663,0.00021191992,0.00036110028,0.000037989168,0.0000074997],"category_scores_gemma":[0.0026083174,0.00009551973,0.00008085746,0.00022140605,0.000044697208,0.00037734653,0.00008478374,0.00030449472,0.0000021392707],"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":[0.000100460005,0.00067433895,0.20501591,0.00017180729,0.0009540168,0.00003696462,0.02814809,0.0961597,0.012274682,0.6148562,0.0006772376,0.040930636],"study_design_scores_gemma":[0.0016787197,0.0006942618,0.81659913,0.008043489,0.0004399923,0.0014105968,0.006812615,0.09644426,0.011271689,0.043312743,0.011908745,0.0013837755],"about_ca_topic_score_codex":0.000023001861,"about_ca_topic_score_gemma":0.0000064643227,"teacher_disagreement_score":0.8664856,"about_ca_system_score_codex":0.00025425028,"about_ca_system_score_gemma":0.0005992535,"threshold_uncertainty_score":0.38951817},"labels":[],"label_agreement":null},{"id":"W1991728049","doi":"10.1111/j.1745-3984.2009.00091.x","title":"The Hierarchy Consistency Index: Evaluating Person Fit for Cognitive Diagnostic Assessment","year":2009,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":66,"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":"Statistic; Consistency (knowledge bases); Cognition; Hierarchy; Computer science; Item response theory; Goodness of fit; Psychology; Statistics; Cognitive psychology; Artificial intelligence; Mathematics; Machine learning; Psychometrics","score_opus":0.16528120416639475,"score_gpt":0.4007072928289228,"score_spread":0.23542608866252807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991728049","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":[0.08587495,0.004212194,0.6740158,0.22081195,0.004737523,0.001773295,0.000006910279,0.0000199529,0.008547397],"genre_scores_gemma":[0.98879147,0.000029426405,0.009702053,0.000998525,0.00037141223,0.00003303161,4.9855106e-7,0.0000026622631,0.000070926464],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977563,0.00014021358,0.00037977452,0.00017212566,0.0013145532,0.00023703766],"domain_scores_gemma":[0.99326706,0.0028001363,0.00043876516,0.0001203639,0.0032574602,0.00011619738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004198944,0.00010118661,0.00013030923,0.00011551906,0.0005550703,0.00023348405,0.00047480073,0.000019930718,0.0000136676645],"category_scores_gemma":[0.0073412117,0.000070009555,0.00012812276,0.00023216917,0.000057542893,0.000413838,0.000022531573,0.00016182305,0.0000033974375],"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":[0.00007603015,0.0011140143,0.010723997,0.000029771754,0.00023561744,0.000004667561,0.0035194457,0.00020071895,0.0042321584,0.0816862,0.008263847,0.88991356],"study_design_scores_gemma":[0.0016070311,0.0019082725,0.8999675,0.00075087155,0.00009794776,0.00009858675,0.0023741985,0.006202675,0.0005211028,0.084201835,0.0019968336,0.00027316358],"about_ca_topic_score_codex":0.0000017064008,"about_ca_topic_score_gemma":0.0000034989662,"teacher_disagreement_score":0.9029165,"about_ca_system_score_codex":0.0003027019,"about_ca_system_score_gemma":0.0022532805,"threshold_uncertainty_score":0.87886465},"labels":[],"label_agreement":null},{"id":"W1995404757","doi":"10.1111/j.1745-3984.2009.01067.x","title":"The Reliability of Difference Scores in Populations and Samples","year":2009,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":17,"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":"Reliability (semiconductor); Statistics; Population; Variance (accounting); Mathematics; Sample (material); Sample size determination; Standard deviation; Econometrics; Demography; Physics","score_opus":0.21340945573782985,"score_gpt":0.4190955226912946,"score_spread":0.20568606695346472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995404757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.888183,0.00097472116,0.088876195,0.020929072,0.00037074342,0.0002148055,0.000007724353,0.0000019484196,0.00044177988],"genre_scores_gemma":[0.789229,0.0000261952,0.2106634,0.000016989785,0.000055291206,0.0000015196124,1.0575212e-7,0.0000013947,0.0000061277124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883497,0.00013578712,0.00049297215,0.000055901295,0.0004055569,0.00007482992],"domain_scores_gemma":[0.9976238,0.0014794308,0.00027685837,0.00009726955,0.00047798848,0.00004467433],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015434303,0.0000524349,0.00014327122,0.000047176654,0.000053286683,0.000016377895,0.00009722285,0.000017436932,0.000022343664],"category_scores_gemma":[0.010565213,0.000031287156,0.00003055247,0.00008002178,0.000059492268,0.000037055408,0.000006693314,0.0000965449,1.4174516e-7],"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":[0.000037545993,0.00026038624,0.072228074,0.00002733818,0.0000073779556,1.6421275e-7,0.0002595087,0.0000039394113,0.0011272463,0.8972977,0.00034068662,0.028410042],"study_design_scores_gemma":[0.00006177272,0.00004658162,0.48112378,0.0000766587,0.000007301063,0.0000026770635,0.000032363296,0.000013655432,0.000062040046,0.5185385,0.000017158636,0.000017560162],"about_ca_topic_score_codex":0.000015858712,"about_ca_topic_score_gemma":0.00003304491,"teacher_disagreement_score":0.4088957,"about_ca_system_score_codex":0.000067618865,"about_ca_system_score_gemma":0.00018605747,"threshold_uncertainty_score":0.99776924},"labels":[],"label_agreement":null},{"id":"W1996977567","doi":"10.1111/j.1745-3984.2001.tb01114.x","title":"Stability of School Academic Performance Across Subject Areas","year":2001,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"School Choice and Performance","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","funders":"","keywords":"Mathematics education; Context (archaeology); Subject (documents); Academic achievement; Multilevel model; Psychology; Reading (process); School climate; Statistical analysis; Multivariate analysis; Geography; Computer science; Mathematics; Political science; Statistics","score_opus":0.14201751776251245,"score_gpt":0.39514890735904357,"score_spread":0.25313138959653114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996977567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98667735,0.0011763892,0.000012916134,0.006095618,0.00090165995,0.00010798763,0.0000023197208,0.000003277922,0.005022503],"genre_scores_gemma":[0.9965719,0.0010711687,0.0001349416,0.00014462619,0.0018556182,0.000005533917,6.254604e-7,0.0000052424466,0.0002103517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972385,0.00015258047,0.0006004803,0.00010206855,0.0016420644,0.00026430673],"domain_scores_gemma":[0.99723583,0.0001491756,0.000544275,0.00013479094,0.0017031194,0.00023281093],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053180414,0.00008888663,0.00018266012,0.000074205425,0.0002811415,0.000026512445,0.0003814414,0.00007704745,0.0013754431],"category_scores_gemma":[0.0020334867,0.00007723266,0.00010462386,0.0003418667,0.00014179587,0.0006314307,0.00001579104,0.0003802791,0.000035237146],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010725246,0.00015063799,0.9911696,0.000022961762,0.000028204324,2.1462226e-7,0.0030666466,0.000028328768,0.0012017159,0.00015870365,0.0024784086,0.0015873509],"study_design_scores_gemma":[0.00030466015,0.00009140778,0.97131795,0.0001523566,0.000017972787,0.000011154064,0.0023148116,0.0000037631612,0.0017651125,0.00038610568,0.023543386,0.00009129481],"about_ca_topic_score_codex":0.00016767341,"about_ca_topic_score_gemma":0.0003844034,"teacher_disagreement_score":0.021064976,"about_ca_system_score_codex":0.00059281365,"about_ca_system_score_gemma":0.0025419015,"threshold_uncertainty_score":0.9995374},"labels":[],"label_agreement":null},{"id":"W2024075312","doi":"10.1111/j.1745-3984.2009.00082.x","title":"Reliability and Attribute‐Based Scoring in Cognitive Diagnostic Assessment","year":2009,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"University of Alberta","funders":"","keywords":"Reliability (semiconductor); Variance (accounting); Cognition; Set (abstract data type); Strengths and weaknesses; Computer science; Test (biology); Sample (material); Psychology; Statistics; Natural language processing; Artificial intelligence; Mathematics; Social psychology","score_opus":0.5837310786203939,"score_gpt":0.5286242359275425,"score_spread":0.05510684269285138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024075312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97443646,0.0010755707,0.010817226,0.011743916,0.00079473277,0.00015534121,0.0000023388768,0.000002188052,0.0009722412],"genre_scores_gemma":[0.98216605,0.000022741822,0.017312909,0.00030968228,0.00017119183,0.0000037464506,3.4544246e-7,0.000002145833,0.000011194924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961172,0.0005253797,0.00093854294,0.00022003507,0.0020348376,0.00016401517],"domain_scores_gemma":[0.9511813,0.045516673,0.0007525489,0.00017194415,0.0022210854,0.000156478],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02112191,0.00009286151,0.0002737568,0.00053106603,0.0000740884,0.00010018078,0.0002432279,0.000032321397,0.0001484668],"category_scores_gemma":[0.33678958,0.00006583975,0.0000707345,0.0008722415,0.000038533773,0.00021272428,0.00001869677,0.0002304264,0.000002322548],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033708227,0.00046176225,0.95614094,0.0000038842327,0.000008330788,0.0000034666796,0.000074672826,0.00046658175,0.00033502182,0.0001839963,0.0008130461,0.04147459],"study_design_scores_gemma":[0.0005618648,0.00024315013,0.96512425,0.00019879459,0.000011904876,0.000013819588,0.0003007777,0.00012667429,0.000113541995,0.03307238,0.00016586174,0.00006697637],"about_ca_topic_score_codex":0.000006256136,"about_ca_topic_score_gemma":0.000004031095,"teacher_disagreement_score":0.31566766,"about_ca_system_score_codex":0.00030461058,"about_ca_system_score_gemma":0.0007044513,"threshold_uncertainty_score":0.7320475},"labels":[],"label_agreement":null},{"id":"W2108611097","doi":"10.1111/j.1745-3984.2004.tb01163.x","title":"The Attribute Hierarchy Method for Cognitive Assessment: A Variation on Tatsuoka's Rule‐Space Approach","year":2004,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":393,"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":"Cognition; Space (punctuation); Hierarchy; Task (project management); Psychology; Syllogism; Domain (mathematical analysis); Variation (astronomy); Cognitive psychology; Computer science; Artificial intelligence; Mathematics; Epistemology","score_opus":0.07125507419111203,"score_gpt":0.36007366024041254,"score_spread":0.2888185860493005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108611097","genre_codex":"methods","genre_gemma":"empirical","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":[0.0010891455,0.00017187108,0.95731646,0.038444493,0.0008641282,0.00037163543,0.0000039185234,0.0000055805344,0.00173275],"genre_scores_gemma":[0.6548647,0.000024395775,0.3435433,0.00084779394,0.0005264711,0.00009371241,0.0000029185926,0.0000068867334,0.000089822446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976724,0.00019043579,0.0003773985,0.0002304568,0.0012796926,0.00024963717],"domain_scores_gemma":[0.9958755,0.0009166847,0.00048944814,0.000149382,0.0024477064,0.00012130758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053387997,0.0001216808,0.00014758234,0.00016986988,0.00052471645,0.00025403814,0.00054718554,0.000029525045,0.000003998411],"category_scores_gemma":[0.0014252468,0.00008380952,0.00014101375,0.00038896684,0.000042873584,0.00048165832,0.000043683445,0.00020446464,0.00000524282],"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":[0.00013036579,0.0019081288,0.000464932,0.000038244296,0.00037475163,0.0000017960867,0.0038080495,0.0027840245,0.0059643798,0.92244315,0.0021256157,0.05995654],"study_design_scores_gemma":[0.006608015,0.0021328973,0.34899414,0.00086937286,0.00022845675,0.0002271843,0.0019247136,0.008050513,0.0057246992,0.61090887,0.013563516,0.00076760014],"about_ca_topic_score_codex":0.000007079577,"about_ca_topic_score_gemma":0.0000028842178,"teacher_disagreement_score":0.6537756,"about_ca_system_score_codex":0.00057587185,"about_ca_system_score_gemma":0.002131916,"threshold_uncertainty_score":0.40357476},"labels":[],"label_agreement":null},{"id":"W2139990047","doi":"10.1111/j.1745-3984.2011.00158.x","title":"Estimating Classification Consistency and Accuracy for Cognitive Diagnostic Assessment","year":2012,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":90,"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":"Consistency (knowledge bases); Reliability (semiconductor); Computation; Subtraction; Statistical inference; Fraction (chemistry); Inference; Sampling (signal processing); Computer science; Statistics; Cognitive test; Artificial intelligence; Cognition; Mathematics; Data mining; Pattern recognition (psychology); Algorithm; Psychology; Arithmetic","score_opus":0.7019996993223337,"score_gpt":0.5564925005972196,"score_spread":0.1455071987251142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139990047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58665234,0.006511315,0.377991,0.016993066,0.007250973,0.00072237203,0.000015140549,0.0000070645992,0.0038567658],"genre_scores_gemma":[0.82965004,0.000015589521,0.16940598,0.00012705004,0.0007489567,0.000025736348,0.0000010177753,0.00000455033,0.000021083082],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969359,0.00033698537,0.00092437153,0.00014742394,0.0014636525,0.00019168895],"domain_scores_gemma":[0.84997684,0.14284824,0.0021388344,0.00018416549,0.004572833,0.00027909677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017558808,0.000093679846,0.00023304056,0.0003115727,0.00020032827,0.00012535001,0.0001975389,0.00003293531,0.000119017066],"category_scores_gemma":[0.5315195,0.00006586008,0.000087130415,0.00036701487,0.00006919448,0.00043805133,0.000026058246,0.00012299452,0.000004801077],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033282966,0.00048739565,0.7835364,0.000024465002,0.000085204476,1.8902321e-7,0.00048426323,0.00003324269,0.0009818539,0.007219022,0.006334284,0.20078039],"study_design_scores_gemma":[0.0004115498,0.00011554969,0.96144456,0.00012415549,0.000061725914,0.000049668753,0.0014492653,0.0005093646,0.000060753544,0.03462409,0.0010688805,0.00008043635],"about_ca_topic_score_codex":0.0000017025367,"about_ca_topic_score_gemma":5.771904e-7,"teacher_disagreement_score":0.51396066,"about_ca_system_score_codex":0.00015284776,"about_ca_system_score_gemma":0.00049172714,"threshold_uncertainty_score":0.60855675},"labels":[],"label_agreement":null},{"id":"W2146894730","doi":"10.1111/j.1745-3984.2011.00142.x","title":"Using the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees’ Cognitive Skills in Critical Reading","year":2011,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":57,"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":"Cognition; Reading (process); Psychology; Reading comprehension; Set (abstract data type); Test (biology); Sample (material); Cognitive psychology; Hierarchy; Comprehension; Natural language processing; Computer science; Artificial intelligence; Linguistics","score_opus":0.7841432219145653,"score_gpt":0.5727164674921034,"score_spread":0.21142675442246195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146894730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5697789,0.0015615835,0.41506308,0.0064773206,0.0030653388,0.00038100104,0.000012131861,0.000004992206,0.0036556215],"genre_scores_gemma":[0.83004683,0.000016325388,0.16911285,0.00043053186,0.0003407778,0.000011111352,2.2691854e-7,0.0000063139973,0.000035013432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938505,0.0018456966,0.0012844728,0.00027802368,0.0024136463,0.00032764007],"domain_scores_gemma":[0.7824945,0.20950288,0.0011439653,0.00043339978,0.005976571,0.00044870572],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030560607,0.00014967081,0.00038099886,0.00097401754,0.00017788821,0.00015256008,0.0007516015,0.00005307499,0.0005150815],"category_scores_gemma":[0.5533034,0.00008913259,0.00011936652,0.001946201,0.00009943532,0.0002297983,0.00009893554,0.00035189907,0.000015204718],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008297951,0.0007735586,0.8810499,0.000011353601,0.0000875634,0.00001818726,0.005708713,0.00030417828,0.0008558539,0.0060086204,0.0012066922,0.10389246],"study_design_scores_gemma":[0.00022912491,0.00017458553,0.9399502,0.0004299094,0.000039815313,0.000097209864,0.0031362067,0.00005977749,0.00053209753,0.054826837,0.0004018724,0.00012234577],"about_ca_topic_score_codex":0.00008189293,"about_ca_topic_score_gemma":0.000026222899,"teacher_disagreement_score":0.5227428,"about_ca_system_score_codex":0.00023448748,"about_ca_system_score_gemma":0.00065847125,"threshold_uncertainty_score":0.99824184},"labels":[],"label_agreement":null},{"id":"W2151713426","doi":"10.1111/j.1745-3984.2007.00052.x","title":"Using the Attribute Hierarchy Method to Identify and Interpret Cognitive Skills that Produce Group Differences","year":2008,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Multi-Criteria Decision Making","field":"Decision 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 Alberta","funders":"","keywords":"Cognition; Set (abstract data type); Task (project management); Hierarchy; Test (biology); Psychology; Group (periodic table); Sample (material); Artificial intelligence; Natural language processing; Computer science; Cognitive psychology; Machine learning","score_opus":0.5348286662951659,"score_gpt":0.5307739533614363,"score_spread":0.0040547129337296095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151713426","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8142627,0.0007105923,0.17510417,0.007978208,0.0015350775,0.00032705252,0.000012513,0.0000025836991,0.00006713387],"genre_scores_gemma":[0.9600752,0.000019138726,0.038573533,0.00069872325,0.00050557393,0.000010743477,4.8890513e-7,0.000010509422,0.00010608655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99250346,0.0011603845,0.0010989798,0.00041012824,0.004579271,0.0002477637],"domain_scores_gemma":[0.99096805,0.0045237723,0.00071487244,0.0003130704,0.0032212331,0.00025897872],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013093909,0.00019226663,0.00041041442,0.000543511,0.00043883885,0.00039900214,0.0008269869,0.00004481585,0.0003827564],"category_scores_gemma":[0.017297274,0.000109719425,0.00015730923,0.0005971931,0.00013945055,0.0005455063,0.0002057493,0.00028293658,0.000024927109],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009305493,0.001962275,0.7430373,0.000028483173,0.0006746833,0.000046190078,0.0326384,0.00027215222,0.09658835,0.0011573308,0.034722853,0.08794147],"study_design_scores_gemma":[0.00048553367,0.00013029482,0.98158187,0.0003930096,0.000057579724,0.00070183555,0.002185552,0.00015209557,0.0021086712,0.0104538025,0.0015685222,0.00018123965],"about_ca_topic_score_codex":0.000015392314,"about_ca_topic_score_gemma":0.0000126563355,"teacher_disagreement_score":0.2385446,"about_ca_system_score_codex":0.00022098789,"about_ca_system_score_gemma":0.00048990827,"threshold_uncertainty_score":0.99098045},"labels":[],"label_agreement":null},{"id":"W2153172866","doi":"10.1111/j.1745-3984.2006.00016.x","title":"Evaluating DETECT Classification Accuracy and Consistency When Data Display Complex Structure","year":2006,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Curse of dimensionality; Correlation; Consistency (knowledge bases); Sample (material); Sample size determination; Dimension (graph theory); Nonparametric statistics; Statistics; Computer science; Pattern recognition (psychology); Artificial intelligence; Data mining; Mathematics","score_opus":0.30124668597441207,"score_gpt":0.42667746295920894,"score_spread":0.12543077698479688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153172866","genre_codex":"methods","genre_gemma":"empirical","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":[0.0076802257,0.0006416244,0.98289835,0.008206801,0.00024424068,0.00015647415,0.000022450926,0.000015383854,0.00013442822],"genre_scores_gemma":[0.52415395,0.000006222013,0.4756151,0.0000759272,0.00013023493,0.000002109538,0.000009014055,0.0000037006605,0.0000037164777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979215,0.00012943023,0.00058780186,0.00025177855,0.00097243395,0.00013700474],"domain_scores_gemma":[0.9973162,0.00047778848,0.0005579561,0.0004987031,0.0010704158,0.00007893364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00122307,0.0001127994,0.00016001253,0.00009566949,0.00014440823,0.0001233955,0.0007954196,0.000032415617,0.000028298147],"category_scores_gemma":[0.0023150393,0.0000940699,0.000024939658,0.0000977119,0.000055501983,0.0006383612,0.00014105426,0.00016791519,0.0000012095942],"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":[0.000066638895,0.0004994089,0.0045669237,0.00011991684,0.00012367159,0.0000045156826,0.00036740932,0.0013147044,0.21640562,0.5066014,0.031645115,0.23828466],"study_design_scores_gemma":[0.00035911656,0.0001552405,0.13015352,0.0001307253,0.000046483823,0.00013728232,0.000017265396,0.10841353,0.0006776497,0.7581525,0.0015589225,0.000197747],"about_ca_topic_score_codex":0.000018892373,"about_ca_topic_score_gemma":0.0000236476,"teacher_disagreement_score":0.5164737,"about_ca_system_score_codex":0.00019557848,"about_ca_system_score_gemma":0.000508424,"threshold_uncertainty_score":0.38360593},"labels":[],"label_agreement":null},{"id":"W2153713169","doi":"10.1111/j.1745-3984.2003.tb01148.x","title":"Identifying Content and Cognitive Skills that Produce Gender Differences in Mathematics: A Demonstration of the Multidimensionality‐Based DIF Analysis Paradigm","year":2003,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","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":"University of Alberta","funders":"","keywords":"Cognition; Curriculum; Psychology; Mathematics education; Content analysis; Test (biology); Strengths and weaknesses; Social psychology; Pedagogy; Social science","score_opus":0.19225883755504722,"score_gpt":0.3347692788854235,"score_spread":0.1425104413303763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153713169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929036,0.000418966,0.004929757,0.000806627,0.00012119803,0.0004170298,0.000005590927,0.0000019185459,0.0003953483],"genre_scores_gemma":[0.98938954,0.000010697166,0.010460658,0.000058618756,0.000020273908,0.000018950537,0.0000010326709,0.000007672893,0.000032558466],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973786,0.00025966018,0.00084475667,0.00016583115,0.0012002129,0.00015093938],"domain_scores_gemma":[0.99659026,0.0016645698,0.0008222197,0.00011894627,0.00072209875,0.000081913066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020620448,0.00016270223,0.00044710675,0.00023223761,0.00007994171,0.000032673408,0.000115912815,0.00004135804,0.00013093294],"category_scores_gemma":[0.0034007276,0.00010260036,0.0001915139,0.00035735042,0.00010765087,0.00013378727,0.000022636956,0.00014925217,0.0000013293833],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066969034,0.005536254,0.91795814,0.00059925613,0.0020115732,0.0000034571199,0.005227889,0.000010833475,0.004416131,0.063773766,0.000078384444,0.00031731458],"study_design_scores_gemma":[0.00074616866,0.000034911318,0.76846933,0.00087616494,0.0006503886,0.000019731331,0.0017092199,0.00003698169,0.018840346,0.2084856,0.0000011802645,0.0001299604],"about_ca_topic_score_codex":0.000005274156,"about_ca_topic_score_gemma":0.00004555111,"teacher_disagreement_score":0.14948884,"about_ca_system_score_codex":0.00013750569,"about_ca_system_score_gemma":0.00036719884,"threshold_uncertainty_score":0.41839212},"labels":[],"label_agreement":null},{"id":"W2166083835","doi":"10.1111/j.1745-3984.2001.tb01121.x","title":"Identifying Sources of Differential Item and Bundle Functioning on Translated Achievement Tests: A Confirmatory Analysis","year":2001,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":118,"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; International Association for the Evaluation of Educational Achievement; University of Alberta","keywords":"Differential item functioning; Psychology; Categorization; Item analysis; Set (abstract data type); Achievement test; Test (biology); Item response theory; Social psychology; Standardized test; Mathematics education; Psychometrics; Developmental psychology; Computer science; Artificial intelligence","score_opus":0.11509247209283534,"score_gpt":0.37727077187965863,"score_spread":0.2621782997868233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166083835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911334,0.001207251,0.0007280028,0.003457356,0.001278171,0.00011949051,0.0000053997783,0.0000042608417,0.0020666628],"genre_scores_gemma":[0.9987305,0.000034283144,0.00019834768,0.0002078788,0.00035075692,0.000016782004,0.0000084951525,0.000008613352,0.00044434168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977776,0.00020251336,0.00076537405,0.00020613628,0.00087106513,0.00017730432],"domain_scores_gemma":[0.99822825,0.0002782333,0.0006548234,0.000143037,0.0005492137,0.00014642923],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079842267,0.00015303226,0.0003185724,0.00045429444,0.00011778711,0.00003856665,0.00014840544,0.00006511803,0.0037099677],"category_scores_gemma":[0.00008939466,0.00012209732,0.00020254526,0.00042798356,0.00006406619,0.00009299398,0.000009012395,0.00021997106,0.000014755711],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005123285,0.0053907325,0.9758137,0.000031590895,0.00341109,0.0000032387352,0.0027544312,0.000101590114,0.004483393,0.004450032,0.0012436048,0.0018042683],"study_design_scores_gemma":[0.00083588896,0.0004334509,0.9936495,0.000097643555,0.00052311417,0.00004271355,0.0011624105,0.0000074914005,0.00010377049,0.0013426527,0.0016850055,0.00011634671],"about_ca_topic_score_codex":0.00003594412,"about_ca_topic_score_gemma":0.000012482894,"teacher_disagreement_score":0.017835813,"about_ca_system_score_codex":0.000117553136,"about_ca_system_score_gemma":0.00012564857,"threshold_uncertainty_score":0.9972008},"labels":[],"label_agreement":null},{"id":"W2171625237","doi":"10.1111/j.1745-3984.2007.00024.x","title":"An Investigation into the Dimensionality of TOEFL Using Conditional Covariance‐Based Nonparametric Approach","year":2007,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":82,"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":"Test of English as a Foreign Language; Reading comprehension; Curse of dimensionality; Psychology; Covariance; Nonparametric statistics; Natural language processing; Computer science; Reading (process); Artificial intelligence; Statistics; Mathematics education; Mathematics; Linguistics; Language assessment","score_opus":0.6245000768597356,"score_gpt":0.5087043214551444,"score_spread":0.1157957554045912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171625237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70649105,0.00048054144,0.2904174,0.0013052009,0.00088993716,0.00013093563,0.0000032733008,0.0000022298934,0.0002794167],"genre_scores_gemma":[0.7780539,0.0000012691513,0.22127344,0.00031149993,0.00034436528,0.0000016891257,0.0000032036726,0.0000045407664,0.0000061037344],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99281734,0.0008380974,0.0015437144,0.0002350922,0.00438582,0.00017993542],"domain_scores_gemma":[0.9770635,0.015327364,0.0021657422,0.00038749928,0.004859741,0.00019619615],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044816136,0.000121726895,0.00030371005,0.0008840276,0.00023223291,0.00007878846,0.000685219,0.000061318045,0.00017345442],"category_scores_gemma":[0.04865053,0.000073909745,0.0001562452,0.0026923667,0.00021597208,0.0003290494,0.000026086298,0.00022997412,0.0000025381783],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004795206,0.0024402698,0.7611208,0.00004385879,0.00024015902,0.000002470654,0.0026076664,0.10016535,0.0745033,0.030107968,0.0030450874,0.025243523],"study_design_scores_gemma":[0.00044287916,0.00016480451,0.8532051,0.000042742813,0.000040017985,0.000038188788,0.001191709,0.0053161373,0.003720192,0.1355324,0.00019894404,0.00010688915],"about_ca_topic_score_codex":0.00007506497,"about_ca_topic_score_gemma":0.0000058072615,"teacher_disagreement_score":0.10542442,"about_ca_system_score_codex":0.0003231888,"about_ca_system_score_gemma":0.0013926508,"threshold_uncertainty_score":0.98356277},"labels":[],"label_agreement":null},{"id":"W2258138870","doi":"10.1111/jedm.12095","title":"Rutkowski, L., vonDavier, M., & Rutkowski, D. (Eds.). (2014). Handbook of International Large‐Scale Assessments: Background, Technical Issues, and Methods of Data Analysis. Boca Raton, FL: CRC Press.","year":2015,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Educational Assessment and Pedagogy","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 Victoria","funders":"","keywords":"Library science; Curriculum; Christian ministry; Citation; Sociology; Political science; Computer science; Law; Pedagogy","score_opus":0.2646006784507445,"score_gpt":0.5359710732399001,"score_spread":0.27137039478915564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2258138870","genre_codex":"review","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":[0.0929963,0.37451705,0.24621737,0.15395463,0.024775758,0.003919349,0.0015603679,0.00009909857,0.10196009],"genre_scores_gemma":[0.39291847,0.009596073,0.5875651,0.0004005759,0.0036031255,0.000055902638,0.00053325744,0.00005239111,0.0052750865],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99411184,0.0009550806,0.0013779238,0.00037365904,0.0028752482,0.00030623187],"domain_scores_gemma":[0.99279875,0.0005647423,0.0015053959,0.0005349906,0.00420022,0.00039588424],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012747953,0.00021711063,0.0006433449,0.00046682727,0.00017038643,0.00011847928,0.0012223216,0.00014614171,0.0013449551],"category_scores_gemma":[0.0012716599,0.00019774659,0.00020151623,0.0004194893,0.00032536467,0.0010034868,0.00022236559,0.00031422373,0.000006814988],"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":[0.00071925233,0.009434647,0.275816,0.00019656144,0.0063141063,0.000002391492,0.013744172,0.00025105264,0.0074122734,0.035189442,0.63794154,0.012978579],"study_design_scores_gemma":[0.0012692177,0.00019619137,0.035169635,0.00019943342,0.0011330529,0.000015821903,0.0048779594,0.00006751272,0.00036446357,0.008367374,0.94801676,0.00032254824],"about_ca_topic_score_codex":0.0008765811,"about_ca_topic_score_gemma":0.002426635,"teacher_disagreement_score":0.36492097,"about_ca_system_score_codex":0.00046197762,"about_ca_system_score_gemma":0.0044353455,"threshold_uncertainty_score":0.9995679},"labels":[],"label_agreement":null},{"id":"W2920811067","doi":"10.1111/jedm.12205","title":"Modeling Response Styles in Cross‐Country Self‐Reports: An Application of a Multilevel Multidimensional Nominal Response Model","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"McGill University","funders":"","keywords":"Comparability; Psychology; Multilevel model; Structural equation modeling; Econometrics; Social psychology; Cross-cultural; Computer science; Statistics; Mathematics; Political science","score_opus":0.35009938784928696,"score_gpt":0.4756613456886337,"score_spread":0.12556195783934676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920811067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96532524,0.0003350355,0.032799017,0.00066940626,0.0005237919,0.00026770603,0.000008876688,0.0000050118915,0.00006589627],"genre_scores_gemma":[0.8661616,0.000003777808,0.13358127,0.00007178998,0.00009883042,0.000011758476,0.0000012270335,0.000011832301,0.00005790061],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917957,0.0013652701,0.002431893,0.00045007328,0.0036973439,0.00025971507],"domain_scores_gemma":[0.9824462,0.011022172,0.0017489906,0.00061004487,0.0039848983,0.00018772545],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05578407,0.00018072293,0.00047675113,0.0012839555,0.00008681726,0.00007395583,0.00053969305,0.00010524938,0.00008853376],"category_scores_gemma":[0.07638445,0.00014131359,0.00015217128,0.0008572129,0.00004928675,0.00058881845,0.00006782785,0.00029561095,0.000009865677],"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":[0.0068257265,0.0010838874,0.18047534,0.000013995444,0.00003551924,0.000003553484,0.0008742341,0.6942161,0.11379981,0.0002955133,0.000094665134,0.0022816923],"study_design_scores_gemma":[0.00077282265,0.00020452579,0.4788581,0.00008810813,0.000012193091,0.00009770285,0.00071105803,0.5131901,0.0004598898,0.0053445483,0.00012921756,0.00013172675],"about_ca_topic_score_codex":0.00005891902,"about_ca_topic_score_gemma":0.000011961621,"teacher_disagreement_score":0.29838276,"about_ca_system_score_codex":0.0005170518,"about_ca_system_score_gemma":0.002325693,"threshold_uncertainty_score":0.972269},"labels":[],"label_agreement":null},{"id":"W2956271099","doi":"10.1111/jedm.12207","title":"Performance of Person‐Fit Statistics Under Model Misspecification","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"McGill University","funders":"","keywords":"Statistic; Econometrics; Item response theory; Inference; Latent variable; Latent variable model; Parametric statistics; Statistics; Statistical inference; Goodness of fit; Parametric model; Computer science; Variable (mathematics); Specification; Empirical research; Aggregate (composite); Mathematics; Psychometrics; Artificial intelligence","score_opus":0.7529540980675968,"score_gpt":0.4796196803409436,"score_spread":0.27333441772665323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956271099","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9530818,0.000552744,0.03478964,0.0029922256,0.0014455643,0.00011209803,0.000008475073,0.0000017488962,0.007015693],"genre_scores_gemma":[0.90675807,0.00003277836,0.09219344,0.00007008282,0.00013383149,0.0000010867408,5.1143786e-7,0.0000047496906,0.0008054746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99600834,0.00015356211,0.00085299194,0.00014702242,0.0027174964,0.00012058696],"domain_scores_gemma":[0.9914179,0.0036609431,0.001275297,0.00026221623,0.003299369,0.00008428025],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008058826,0.00007989928,0.00024157955,0.00040239102,0.000048202946,0.000039623457,0.000471546,0.000032350476,0.0011776886],"category_scores_gemma":[0.016669834,0.00005668306,0.00008133424,0.00054197956,0.000033620563,0.00019478399,0.000015641932,0.00012854207,0.000049220496],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003259794,0.0010364715,0.6190682,0.00008985038,0.00018429542,3.7224518e-7,0.0014164136,0.1701382,0.028135547,0.021664172,0.0733558,0.08458471],"study_design_scores_gemma":[0.0004109372,0.00025561973,0.94477993,0.000066402834,0.000023823966,0.0000204139,0.0011409904,0.029842919,0.00065970805,0.021701397,0.0009865317,0.00011130413],"about_ca_topic_score_codex":0.000002589893,"about_ca_topic_score_gemma":5.970788e-7,"teacher_disagreement_score":0.32571176,"about_ca_system_score_codex":0.00016864992,"about_ca_system_score_gemma":0.00065041176,"threshold_uncertainty_score":0.99973536},"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":"W4308426657","doi":"10.1111/jedm.12347","title":"A Unified Comparison of IRT‐Based Effect Sizes for DIF Investigations","year":2022,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"York University","funders":"","keywords":"Differential item functioning; Estimator; Statistics; Item response theory; Sample size determination; Differential (mechanical device); Population; Sample (material); Monte Carlo method; Econometrics; Computer science; Mathematics; Psychometrics","score_opus":0.6842492147562678,"score_gpt":0.529819503327333,"score_spread":0.1544297114289348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308426657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9480686,0.0017151192,0.027155632,0.017425476,0.0039496743,0.0005232892,0.00003112977,0.0000056360436,0.0011254137],"genre_scores_gemma":[0.9549753,7.2193865e-7,0.04459525,0.00013937496,0.0001703093,0.0000410286,0.000001993457,0.0000053668473,0.000070659364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99471533,0.0009318049,0.0011987125,0.00015420657,0.0028663988,0.00013353393],"domain_scores_gemma":[0.95808357,0.037666816,0.0018994329,0.00024523243,0.0019836884,0.000121276935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018950822,0.00008853992,0.00039117187,0.0006583376,0.000275096,0.00004406178,0.0006119709,0.000020026471,0.00046498032],"category_scores_gemma":[0.15057439,0.00006447136,0.00022171393,0.0012048474,0.000055577202,0.00008341571,0.00004305578,0.00017816812,0.0000015202055],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005644303,0.001653287,0.7779037,0.000066944944,0.00019845937,4.980901e-7,0.0009492635,0.052037563,0.021591717,0.006310406,0.11227844,0.026445301],"study_design_scores_gemma":[0.0038747406,0.0046766335,0.7382927,0.00015779196,0.00021241506,0.00003105726,0.0037685642,0.0066753486,0.01444881,0.17301524,0.054491438,0.0003552587],"about_ca_topic_score_codex":0.0000075685284,"about_ca_topic_score_gemma":0.0000027157846,"teacher_disagreement_score":0.16670482,"about_ca_system_score_codex":0.00021715576,"about_ca_system_score_gemma":0.0009982039,"threshold_uncertainty_score":0.8565807},"labels":[],"label_agreement":null},{"id":"W4388574245","doi":"10.1111/jedm.12380","title":"Incorporating Test‐Taking Engagement into Multistage Adaptive Testing Design for Large‐Scale Assessments","year":2023,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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 Alberta","funders":"","keywords":"Operationalization; Computerized adaptive testing; Test (biology); Item response theory; Premise; Scale (ratio); Computer science; Test design; Reliability (semiconductor); Psychology; Applied psychology; Reliability engineering; Psychometrics; Statistics; Test method; Mathematics; Engineering; Clinical psychology","score_opus":0.8135852760237042,"score_gpt":0.547201763889805,"score_spread":0.2663835121338992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388574245","genre_codex":"methods","genre_gemma":"empirical","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":[0.07395511,0.00035005537,0.9180561,0.002275494,0.0031424793,0.0007315764,0.000015341413,0.000032646458,0.0014412553],"genre_scores_gemma":[0.5209432,0.0000023391226,0.4783773,0.00007950716,0.00043552584,0.00003613986,0.0000011578211,0.0000119586875,0.000112837224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934541,0.0008953885,0.0016093957,0.00038148265,0.0032679816,0.00039165118],"domain_scores_gemma":[0.9104707,0.08028877,0.0035073657,0.00033492822,0.005177811,0.00022041751],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056673456,0.0001905845,0.0004038898,0.0009897898,0.00060918194,0.00026468924,0.00075963244,0.000056711284,0.00010249743],"category_scores_gemma":[0.34966627,0.00014618225,0.00017063945,0.0025725982,0.000032660464,0.00038341267,0.00013493974,0.0002986209,0.000027281565],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025399314,0.0015999478,0.6261827,0.00008904078,0.00033166615,0.000018096856,0.0036546227,0.023194948,0.03623732,0.0025284835,0.05043581,0.2554734],"study_design_scores_gemma":[0.0023738577,0.0018478034,0.6918802,0.0006326229,0.00010874836,0.000044173805,0.016413268,0.07280599,0.0016799355,0.20756572,0.0040995344,0.00054812327],"about_ca_topic_score_codex":0.000010802124,"about_ca_topic_score_gemma":0.0000076255897,"teacher_disagreement_score":0.4469881,"about_ca_system_score_codex":0.0005020077,"about_ca_system_score_gemma":0.001058621,"threshold_uncertainty_score":0.9713532},"labels":[],"label_agreement":null},{"id":"W4399234968","doi":"10.1111/jedm.12401","title":"Modeling Response Styles in Cross‐Classified Data Using a Cross‐Classified Multidimensional Nominal Response Model","year":2024,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"Covariate; Item response theory; Cross-validation; Computer science; Data set; Statistics; Multilevel model; Set (abstract data type); Econometrics; Psychology; Mathematics; Psychometrics","score_opus":0.8252373857984466,"score_gpt":0.5741859983791489,"score_spread":0.2510513874192978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399234968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9304871,0.0027904252,0.05987651,0.0043447292,0.0021274819,0.00017457422,0.000050958515,0.000012589505,0.00013561502],"genre_scores_gemma":[0.8831483,0.000013441046,0.115879096,0.00012179876,0.00042935775,0.000005618737,0.0000028745828,0.000025864914,0.00037364796],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98831683,0.0025172578,0.0027732346,0.00088994595,0.0049926303,0.00051010994],"domain_scores_gemma":[0.9629046,0.031725656,0.00084919255,0.0011568231,0.0030131314,0.00035061524],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08857544,0.00030053215,0.00057053444,0.0023092832,0.00029870804,0.000897821,0.0016609865,0.00015477855,0.00025357344],"category_scores_gemma":[0.21586531,0.0002266179,0.0002402783,0.0018950322,0.00016254073,0.0013098498,0.0003711816,0.00070984155,0.000027750713],"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":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014327251,0.00055817876,0.018191976,0.000029847131,0.00012443138,0.00006370104,0.00068639783,0.8537162,0.104743004,0.0007528346,0.0029306263,0.0038755855],"study_design_scores_gemma":[0.00086956477,0.00010454428,0.10290483,0.00042563045,0.000031023796,0.0002176871,0.00054611324,0.88547534,0.00019124974,0.008191646,0.00080414256,0.00023826257],"about_ca_topic_score_codex":0.000045393987,"about_ca_topic_score_gemma":0.000016526385,"teacher_disagreement_score":0.12728988,"about_ca_system_score_codex":0.0011307298,"about_ca_system_score_gemma":0.0065484303,"threshold_uncertainty_score":0.9990835},"labels":[],"label_agreement":null},{"id":"W4400898279","doi":"10.1111/jedm.12406","title":"Using Automated Procedures to Score Educational Essays Written in Three Languages","year":2024,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Natural Language Processing Techniques","field":"Computer Science","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 Alberta","funders":"","keywords":"Mathematics education; Natural language processing; Computer science; Psychology; Linguistics; Artificial intelligence; Philosophy","score_opus":0.0603400789110201,"score_gpt":0.3634531269538653,"score_spread":0.30311304804284517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400898279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31175646,0.12707658,0.26275128,0.28678942,0.0069642738,0.0015365906,0.00001426534,0.000789537,0.0023215937],"genre_scores_gemma":[0.7424302,0.0000055223854,0.25678456,0.0002916866,0.00042899585,0.00001361513,9.531548e-7,0.000010246137,0.000034195014],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980659,0.000051264225,0.00046490514,0.00022672844,0.00099195,0.00019923385],"domain_scores_gemma":[0.99869365,0.00010743904,0.00015491579,0.00017242547,0.00075221615,0.00011935935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011020681,0.0001387808,0.00016197331,0.00066670316,0.000059933816,0.0002923589,0.00070033036,0.000049250524,0.00005033983],"category_scores_gemma":[0.00089873077,0.00011318819,0.00006712338,0.0007852433,0.00001965469,0.00063818943,0.000075873264,0.0002432007,0.000012912798],"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":[0.000087924316,0.001947171,0.03756291,0.0014480242,0.00037261884,0.00013489394,0.007767938,0.0029450953,0.22799668,0.5953418,0.09334922,0.031045709],"study_design_scores_gemma":[0.0008710664,0.00045143356,0.16402595,0.01567071,0.00012636968,0.0024659846,0.0003995183,0.037903897,0.026351802,0.7483385,0.0018683461,0.0015263775],"about_ca_topic_score_codex":0.000039793802,"about_ca_topic_score_gemma":0.00008423333,"teacher_disagreement_score":0.43067375,"about_ca_system_score_codex":0.0007342731,"about_ca_system_score_gemma":0.0031609857,"threshold_uncertainty_score":0.5607453},"labels":[],"label_agreement":null},{"id":"W4403847593","doi":"10.1111/jedm.12420","title":"Algorithmic Bias in BERT for Response Accuracy Prediction: A Case Study for Investigating Population Validity","year":2024,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","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":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Item response theory; Population; Psychology; Test validity; Predictive validity; Statistics; Computer science; Econometrics; Psychometrics; Mathematics; Clinical psychology; Demography","score_opus":0.3090948321123259,"score_gpt":0.41355177989540626,"score_spread":0.10445694778308035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403847593","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":[0.46102875,0.0002685058,0.52169424,0.013272935,0.0019231833,0.001709633,0.000044014734,0.000052212563,0.000006516774],"genre_scores_gemma":[0.87060624,0.0000028700356,0.12853085,0.000065882195,0.00041687893,0.00033978393,0.000008872392,0.000009769979,0.000018864945],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978583,0.0002880432,0.0008091516,0.00025162313,0.0006480083,0.00014487834],"domain_scores_gemma":[0.99676025,0.0015887332,0.00037418545,0.0002554495,0.0009385707,0.00008279008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075259707,0.00011332205,0.00016112425,0.00043350304,0.00012850674,0.00022138843,0.00033551382,0.000040418206,0.0000040247633],"category_scores_gemma":[0.0057875016,0.00010348855,0.00008798638,0.0004082581,0.000014250218,0.00096632,0.000031223943,0.00015190682,0.0000010073475],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019495047,0.013389576,0.32565123,0.001999299,0.0012088675,0.00042804328,0.047735557,0.0031496189,0.06710986,0.06462865,0.14980842,0.32294136],"study_design_scores_gemma":[0.0048801005,0.005222192,0.68252695,0.0022946848,0.00026274464,0.0059610163,0.0034375633,0.15110584,0.009784258,0.11055002,0.022953892,0.0010207568],"about_ca_topic_score_codex":0.00004275144,"about_ca_topic_score_gemma":0.00003149608,"teacher_disagreement_score":0.4095775,"about_ca_system_score_codex":0.00085948623,"about_ca_system_score_gemma":0.001116206,"threshold_uncertainty_score":0.69285977},"labels":[],"label_agreement":null},{"id":"W4406376912","doi":"10.1111/jedm.12424","title":"Using Multilabel Neural Network to Score High‐Dimensional Assessments for Different Use Foci: An Example with College Major Preference Assessment","year":2025,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Advanced Text Analysis Techniques","field":"Computer Science","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":"Preference; Artificial neural network; Artificial intelligence; Psychology; Machine learning; Computer science; Evaluation methods; Statistics; Mathematics; Reliability engineering","score_opus":0.23328784592740195,"score_gpt":0.3977295805474502,"score_spread":0.16444173462004827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406376912","genre_codex":"methods","genre_gemma":"empirical","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":[0.3063923,0.00006488577,0.69063985,0.001643788,0.0005885716,0.00062577537,0.0000079579295,0.000018316772,0.000018555109],"genre_scores_gemma":[0.5438488,0.0000012776038,0.4554617,0.00042606774,0.0001272462,0.00006143313,0.000004529093,0.000009584684,0.00005937689],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9968321,0.00017969278,0.00073479075,0.00045916392,0.0014182557,0.00037600627],"domain_scores_gemma":[0.995916,0.00027859834,0.00060073537,0.00050453376,0.0024441062,0.00025599462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009613713,0.00027675822,0.00043064612,0.00035036064,0.00031555645,0.00021240611,0.0008065459,0.000052916337,0.00001684954],"category_scores_gemma":[0.00010970584,0.00021361002,0.00012153168,0.0005743017,0.000031408686,0.0010613062,0.00015576705,0.00022296465,4.2076036e-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":[0.001419331,0.010153891,0.20593435,0.00024695956,0.0027749133,0.000020329353,0.0005128519,0.2555192,0.07425781,0.39595458,0.025992468,0.027213331],"study_design_scores_gemma":[0.0037173436,0.002788671,0.785786,0.0015904852,0.0005863298,0.000060550985,0.00007309904,0.1324154,0.0065509067,0.064035095,0.0013984891,0.0009976801],"about_ca_topic_score_codex":0.00006126718,"about_ca_topic_score_gemma":0.00018105537,"teacher_disagreement_score":0.5798516,"about_ca_system_score_codex":0.0012345143,"about_ca_system_score_gemma":0.0015035053,"threshold_uncertainty_score":0.87107635},"labels":[],"label_agreement":null},{"id":"W4409353748","doi":"10.1111/jedm.12433","title":"Theory‐Driven IRT Modeling of Vocabulary Development: Matthew Effects and the Case for Unipolar IRT","year":2025,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Reading and Literacy Development","field":"Psychology","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":"Item response theory; Vocabulary; Psychology; Econometrics; Psychometrics; Natural language processing; Mathematics education; Computer science; Linguistics; Mathematics; Developmental psychology; Philosophy","score_opus":0.031951753387429026,"score_gpt":0.32159032015469335,"score_spread":0.28963856676726435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409353748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91327256,0.019116392,0.04654428,0.010886081,0.003889988,0.0011505393,0.0000056475087,0.00000745303,0.0051270863],"genre_scores_gemma":[0.9923044,0.00002045473,0.006412505,0.00036250128,0.00012565425,0.00006468423,0.0000019438987,0.000009759895,0.0006981378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985147,0.00027037438,0.00064216816,0.00012916957,0.00029373812,0.00014981338],"domain_scores_gemma":[0.99797136,0.00084097823,0.00030976854,0.00014735524,0.00066978787,0.00006073579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035000078,0.00012181423,0.0002594304,0.00020085377,0.00016320094,0.000026985897,0.00016826393,0.00004573296,0.00004963975],"category_scores_gemma":[0.0004779042,0.000080437225,0.000091537724,0.000113705115,0.000059353257,0.000058981583,0.000023774368,0.00014027151,0.0000028842762],"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":[0.005578117,0.0025801037,0.018903758,0.0019544498,0.0077915867,0.000089760004,0.076498985,0.002528487,0.0017639911,0.76078933,0.024380136,0.0971413],"study_design_scores_gemma":[0.059573546,0.0014684505,0.19351625,0.015013965,0.004176045,0.010451673,0.028333252,0.008305037,0.008683035,0.46177664,0.20615286,0.0025492334],"about_ca_topic_score_codex":0.000015295716,"about_ca_topic_score_gemma":0.000003821161,"teacher_disagreement_score":0.29901266,"about_ca_system_score_codex":0.00015794659,"about_ca_system_score_gemma":0.00064572366,"threshold_uncertainty_score":0.32801348},"labels":[],"label_agreement":null}]}