{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":26,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":26,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"07872ab30370","filters":{"venue":"Journal of Educational Measurement"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07125507419111203,"gpt":0.3600736602404125,"spread":0.2888185860493005,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053388,0.0001216808,0.0001475823,0.0001698699,0.0005247165,0.0002540381,0.0005471855,0.00002952504,0.000003998411],"category_scores_gemma":[0.001425247,0.00008380952,0.0001410137,0.0003889668,0.00004287358,0.0004816583,0.00004368345,0.0002044646,0.00000524282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005758718,"about_ca_system_score_gemma":0.002131916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007079577,"about_ca_topic_score_gemma":0.000002884218,"domain_scores_codex":[0.9976724,0.0001904358,0.0003773985,0.0002304568,0.001279693,0.0002496372],"domain_scores_gemma":[0.9958755,0.0009166847,0.0004894481,0.000149382,0.002447706,0.0001213076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001303658,0.001908129,0.000464932,0.0000382443,0.0003747516,0.000001796087,0.003808049,0.002784024,0.00596438,0.9224432,0.002125616,0.05995654],"study_design_scores_gemma":[0.006608015,0.002132897,0.3489941,0.0008693729,0.0002284567,0.0002271843,0.001924714,0.008050513,0.005724699,0.6109089,0.01356352,0.0007676001],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001089146,0.0001718711,0.9573165,0.03844449,0.0008641282,0.0003716354,0.000003918523,0.000005580534,0.00173275],"genre_scores_gemma":[0.6548647,0.00002439577,0.3435433,0.0008477939,0.0005264711,0.00009371241,0.000002918593,0.000006886733,0.00008982245],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6537756,"threshold_uncertainty_score":0.4035748,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1150924720928353,"gpt":0.3772707718796586,"spread":0.2621782997868233,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007984227,0.0001530323,0.0003185724,0.0004542944,0.0001177871,0.00003856665,0.0001484054,0.00006511803,0.003709968],"category_scores_gemma":[0.00008939466,0.0001220973,0.0002025453,0.0004279836,0.00006406619,0.00009299398,0.000009012395,0.0002199711,0.00001475571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001175531,"about_ca_system_score_gemma":0.0001256486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003594412,"about_ca_topic_score_gemma":0.00001248289,"domain_scores_codex":[0.9977776,0.0002025134,0.000765374,0.0002061363,0.0008710651,0.0001773043],"domain_scores_gemma":[0.9982283,0.0002782333,0.0006548234,0.000143037,0.0005492137,0.0001464292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005123285,0.005390733,0.9758137,0.00003159089,0.00341109,0.000003238735,0.002754431,0.0001015901,0.004483393,0.004450032,0.001243605,0.001804268],"study_design_scores_gemma":[0.000835889,0.0004334509,0.9936495,0.00009764355,0.0005231142,0.00004271355,0.00116241,0.000007491401,0.0001037705,0.001342653,0.001685005,0.0001163467],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911334,0.001207251,0.0007280028,0.003457356,0.001278171,0.0001194905,0.000005399778,0.000004260842,0.002066663],"genre_scores_gemma":[0.9987305,0.00003428314,0.0001983477,0.0002078788,0.0003507569,0.000016782,0.000008495153,0.000008613352,0.0004443417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01783581,"threshold_uncertainty_score":0.9972008,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7019996993223337,"gpt":0.5564925005972196,"spread":0.1455071987251142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01755881,0.00009367985,0.0002330406,0.0003115727,0.0002003283,0.00012535,0.0001975389,0.00003293531,0.0001190171],"category_scores_gemma":[0.5315195,0.00006586008,0.00008713041,0.0003670149,0.00006919448,0.0004380513,0.00002605825,0.0001229945,0.000004801077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528478,"about_ca_system_score_gemma":0.0004917271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001702537,"about_ca_topic_score_gemma":5.771904e-7,"domain_scores_codex":[0.9969359,0.0003369854,0.0009243715,0.0001474239,0.001463652,0.0001916889],"domain_scores_gemma":[0.8499768,0.1428482,0.002138834,0.0001841655,0.004572833,0.0002790968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003328297,0.0004873956,0.7835364,0.000024465,0.00008520448,1.890232e-7,0.0004842632,0.00003324269,0.0009818539,0.007219022,0.006334284,0.2007804],"study_design_scores_gemma":[0.0004115498,0.0001155497,0.9614446,0.0001241555,0.00006172591,0.00004966875,0.001449265,0.0005093646,0.00006075354,0.03462409,0.001068881,0.00008043635],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5866523,0.006511315,0.377991,0.01699307,0.007250973,0.000722372,0.00001514055,0.000007064599,0.003856766],"genre_scores_gemma":[0.82965,0.00001558952,0.169406,0.00012705,0.0007489567,0.00002573635,0.000001017775,0.00000455033,0.00002108308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5139607,"threshold_uncertainty_score":0.6085567,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1755289445562674,"gpt":0.3829384330597237,"spread":0.2074094885034563,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00550987,0.0001391763,0.0001962573,0.000169431,0.0003720663,0.0002119199,0.0003611003,0.00003798917,0.0000074997],"category_scores_gemma":[0.002608317,0.00009551973,0.00008085746,0.0002214061,0.00004469721,0.0003773465,0.00008478374,0.0003044947,0.000002139271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002542503,"about_ca_system_score_gemma":0.0005992535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002300186,"about_ca_topic_score_gemma":0.000006464323,"domain_scores_codex":[0.9979032,0.0002022521,0.000495345,0.0001749461,0.000961702,0.000262598],"domain_scores_gemma":[0.9952865,0.002267187,0.0005984638,0.0001137958,0.001633003,0.0001010778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00010046,0.000674339,0.2050159,0.0001718073,0.0009540168,0.00003696462,0.02814809,0.0961597,0.01227468,0.6148562,0.0006772376,0.04093064],"study_design_scores_gemma":[0.00167872,0.0006942618,0.8165991,0.008043489,0.0004399923,0.001410597,0.006812615,0.09644426,0.01127169,0.04331274,0.01190875,0.001383775],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06530953,0.002625868,0.9273871,0.003753263,0.0006611432,0.0001270242,0.00000166931,0.000005178392,0.0001291809],"genre_scores_gemma":[0.9317951,0.00002970626,0.06738267,0.0001907997,0.0004908615,0.000003091204,2.947782e-7,0.000006422064,0.0001010177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8664856,"threshold_uncertainty_score":0.3895182,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6245000768597356,"gpt":0.5087043214551444,"spread":0.1157957554045912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04481614,0.0001217269,0.0003037101,0.0008840276,0.0002322329,0.00007878846,0.000685219,0.00006131805,0.0001734544],"category_scores_gemma":[0.04865053,0.00007390974,0.0001562452,0.002692367,0.0002159721,0.0003290494,0.0000260863,0.0002299741,0.000002538178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003231888,"about_ca_system_score_gemma":0.001392651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007506497,"about_ca_topic_score_gemma":0.000005807261,"domain_scores_codex":[0.9928173,0.0008380974,0.001543714,0.0002350922,0.00438582,0.0001799354],"domain_scores_gemma":[0.9770635,0.01532736,0.002165742,0.0003874993,0.004859741,0.0001961962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004795206,0.00244027,0.7611208,0.00004385879,0.000240159,0.000002470654,0.002607666,0.1001654,0.0745033,0.03010797,0.003045087,0.02524352],"study_design_scores_gemma":[0.0004428792,0.0001648045,0.8532051,0.00004274281,0.00004001799,0.00003818879,0.001191709,0.005316137,0.003720192,0.1355324,0.000198944,0.0001068892],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7064911,0.0004805414,0.2904174,0.001305201,0.0008899372,0.0001309356,0.000003273301,0.000002229893,0.0002794167],"genre_scores_gemma":[0.7780539,0.000001269151,0.2212734,0.0003114999,0.0003443653,0.000001689126,0.000003203673,0.000004540766,0.000006103734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1054244,"threshold_uncertainty_score":0.9835628,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1652812041663947,"gpt":0.4007072928289228,"spread":0.2354260886625281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004198944,0.0001011866,0.0001303092,0.0001155191,0.0005550703,0.0002334841,0.0004748007,0.00001993072,0.00001366766],"category_scores_gemma":[0.007341212,0.00007000956,0.0001281228,0.0002321692,0.00005754289,0.000413838,0.00002253157,0.000161823,0.000003397437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003027019,"about_ca_system_score_gemma":0.00225328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001706401,"about_ca_topic_score_gemma":0.000003498966,"domain_scores_codex":[0.9977563,0.0001402136,0.0003797745,0.0001721257,0.001314553,0.0002370377],"domain_scores_gemma":[0.9932671,0.002800136,0.0004387652,0.0001203639,0.00325746,0.0001161974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007603015,0.001114014,0.010724,0.00002977175,0.0002356174,0.000004667561,0.003519446,0.0002007189,0.004232158,0.0816862,0.008263847,0.8899136],"study_design_scores_gemma":[0.001607031,0.001908273,0.8999675,0.0007508715,0.00009794776,0.00009858675,0.002374199,0.006202675,0.0005211028,0.08420184,0.001996834,0.0002731636],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08587495,0.004212194,0.6740158,0.2208119,0.004737523,0.001773295,0.000006910279,0.0000199529,0.008547397],"genre_scores_gemma":[0.9887915,0.0000294264,0.009702053,0.0009985249,0.0003714122,0.00003303161,4.985511e-7,0.000002662263,0.00007092646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9029165,"threshold_uncertainty_score":0.8788646,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1922588375550472,"gpt":0.3347692788854235,"spread":0.1425104413303763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002062045,0.0001627022,0.0004471068,0.0002322376,0.00007994171,0.00003267341,0.0001159128,0.00004135804,0.0001309329],"category_scores_gemma":[0.003400728,0.0001026004,0.0001915139,0.0003573504,0.0001076509,0.0001337873,0.00002263696,0.0001492522,0.000001329383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001375057,"about_ca_system_score_gemma":0.0003671988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005274156,"about_ca_topic_score_gemma":0.00004555111,"domain_scores_codex":[0.9973786,0.0002596602,0.0008447567,0.0001658312,0.001200213,0.0001509394],"domain_scores_gemma":[0.9965903,0.00166457,0.0008222197,0.0001189463,0.0007220987,0.00008191307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006696903,0.005536254,0.9179581,0.0005992561,0.002011573,0.00000345712,0.005227889,0.00001083348,0.004416131,0.06377377,0.00007838444,0.0003173146],"study_design_scores_gemma":[0.0007461687,0.00003491132,0.7684693,0.0008761649,0.0006503886,0.00001973133,0.00170922,0.00003698169,0.01884035,0.2084856,0.000001180264,0.0001299604],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929036,0.000418966,0.004929757,0.000806627,0.000121198,0.0004170298,0.000005590927,0.000001918546,0.0003953483],"genre_scores_gemma":[0.9893895,0.00001069717,0.01046066,0.00005861876,0.00002027391,0.00001895054,0.000001032671,0.000007672893,0.00003255847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1494888,"threshold_uncertainty_score":0.4183921,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7841432219145653,"gpt":0.5727164674921034,"spread":0.2114267544224619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03056061,0.0001496708,0.0003809989,0.0009740175,0.0001778882,0.0001525601,0.0007516015,0.00005307499,0.0005150815],"category_scores_gemma":[0.5533034,0.00008913259,0.0001193665,0.001946201,0.00009943532,0.0002297983,0.00009893554,0.0003518991,0.00001520472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002344875,"about_ca_system_score_gemma":0.0006584713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008189293,"about_ca_topic_score_gemma":0.0000262229,"domain_scores_codex":[0.9938505,0.001845697,0.001284473,0.0002780237,0.002413646,0.0003276401],"domain_scores_gemma":[0.7824945,0.2095029,0.001143965,0.0004333998,0.005976571,0.0004487057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008297951,0.0007735586,0.8810499,0.0000113536,0.0000875634,0.00001818726,0.005708713,0.0003041783,0.0008558539,0.00600862,0.001206692,0.1038925],"study_design_scores_gemma":[0.0002291249,0.0001745855,0.9399502,0.0004299094,0.00003981531,0.00009720986,0.003136207,0.00005977749,0.0005320975,0.05482684,0.0004018724,0.0001223458],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5697789,0.001561583,0.4150631,0.006477321,0.003065339,0.000381001,0.00001213186,0.000004992206,0.003655622],"genre_scores_gemma":[0.8300468,0.00001632539,0.1691128,0.0004305319,0.0003407778,0.00001111135,2.269185e-7,0.000006313997,0.00003501343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5227428,"threshold_uncertainty_score":0.9982418,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04422115994093499,"gpt":0.3915110005329427,"spread":0.3472898405920077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006115943,0.000168122,0.0003868715,0.0002487875,0.000355028,0.0002466688,0.0005827642,0.00008322528,0.0004700358],"category_scores_gemma":[0.0003544473,0.0001449626,0.0002924267,0.000239251,0.0001271632,0.0007422632,0.00005117879,0.000251736,0.00001246446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001070672,"about_ca_system_score_gemma":0.002848503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087722,"about_ca_topic_score_gemma":0.0004748238,"domain_scores_codex":[0.995474,0.0001820447,0.001095565,0.000172083,0.002752556,0.0003237982],"domain_scores_gemma":[0.9954891,0.0004965866,0.001549905,0.0001456254,0.002182166,0.0001365984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003848315,0.002420381,0.8234078,0.0002676347,0.001319487,4.463347e-7,0.08745815,0.0001834305,0.003449654,0.05331847,0.01073874,0.01705095],"study_design_scores_gemma":[0.003961822,0.001385762,0.7998704,0.002154008,0.0004413656,0.000004275848,0.06936435,0.0004430992,0.0004683149,0.05751652,0.06378975,0.0006003206],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9360783,0.006732543,0.01412554,0.02709391,0.008364882,0.002444989,0.00002459211,0.00001584727,0.005119411],"genre_scores_gemma":[0.9927164,0.0007210757,0.005298373,0.0002120163,0.0006573194,0.0000393593,0.000006514173,0.00001551615,0.0003334492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05663809,"threshold_uncertainty_score":0.5911402,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5837310786203939,"gpt":0.5286242359275425,"spread":0.05510684269285138,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02112191,0.00009286151,0.0002737568,0.000531066,0.0000740884,0.0001001808,0.0002432279,0.0000323214,0.0001484668],"category_scores_gemma":[0.3367896,0.00006583975,0.0000707345,0.0008722415,0.00003853377,0.0002127243,0.00001869677,0.0002304264,0.000002322548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003046106,"about_ca_system_score_gemma":0.0007044513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006256136,"about_ca_topic_score_gemma":0.000004031095,"domain_scores_codex":[0.9961172,0.0005253797,0.0009385429,0.0002200351,0.002034838,0.0001640152],"domain_scores_gemma":[0.9511813,0.04551667,0.0007525489,0.0001719441,0.002221085,0.000156478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003370823,0.0004617622,0.9561409,0.000003884233,0.000008330788,0.00000346668,0.00007467283,0.0004665818,0.0003350218,0.0001839963,0.0008130461,0.04147459],"study_design_scores_gemma":[0.0005618648,0.0002431501,0.9651242,0.0001987946,0.00001190488,0.00001381959,0.0003007777,0.0001266743,0.000113542,0.03307238,0.0001658617,0.00006697637],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9744365,0.001075571,0.01081723,0.01174392,0.0007947328,0.0001553412,0.000002338877,0.000002188052,0.0009722412],"genre_scores_gemma":[0.9821661,0.00002274182,0.01731291,0.0003096823,0.0001711918,0.000003746451,3.454425e-7,0.000002145833,0.00001119492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3156677,"threshold_uncertainty_score":0.7320475,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1420175177625125,"gpt":0.3951489073590436,"spread":0.2531313895965311,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005318041,0.00008888663,0.0001826601,0.00007420543,0.0002811415,0.00002651245,0.0003814414,0.00007704745,0.001375443],"category_scores_gemma":[0.002033487,0.00007723266,0.0001046239,0.0003418667,0.0001417959,0.0006314307,0.00001579104,0.0003802791,0.00003523715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005928137,"about_ca_system_score_gemma":0.002541902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001676734,"about_ca_topic_score_gemma":0.0003844034,"domain_scores_codex":[0.9972385,0.0001525805,0.0006004803,0.0001020686,0.001642064,0.0002643067],"domain_scores_gemma":[0.9972358,0.0001491756,0.000544275,0.0001347909,0.001703119,0.0002328109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001072525,0.000150638,0.9911696,0.00002296176,0.00002820432,2.146223e-7,0.003066647,0.00002832877,0.001201716,0.0001587037,0.002478409,0.001587351],"study_design_scores_gemma":[0.0003046601,0.00009140778,0.9713179,0.0001523566,0.00001797279,0.00001115406,0.002314812,0.000003763161,0.001765113,0.0003861057,0.02354339,0.00009129481],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866773,0.001176389,0.00001291613,0.006095618,0.00090166,0.0001079876,0.000002319721,0.000003277922,0.005022503],"genre_scores_gemma":[0.9965719,0.001071169,0.0001349416,0.0001446262,0.001855618,0.000005533917,6.254604e-7,0.000005242447,0.0002103517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02106498,"threshold_uncertainty_score":0.9995374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6020280900847433,"gpt":0.4600375066203918,"spread":0.1419905834643515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04212425,0.0001413637,0.0002961473,0.0004604501,0.0001558609,0.0001962084,0.0008703302,0.00004122983,0.00005347324],"category_scores_gemma":[0.1223419,0.00006653568,0.0001215612,0.001230427,0.00008188427,0.0003409214,0.00005188826,0.000256572,0.00002092975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003165869,"about_ca_system_score_gemma":0.001448221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007289361,"about_ca_topic_score_gemma":0.000002807548,"domain_scores_codex":[0.9919619,0.001862132,0.000728255,0.0002216217,0.005000205,0.0002259122],"domain_scores_gemma":[0.9642231,0.02929565,0.001064414,0.000427619,0.004683754,0.0003054469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.003142198,0.001445362,0.01330512,0.00001507063,0.0004589419,0.00003962592,0.003934831,0.007917592,0.001812829,0.004634058,0.5210873,0.442207],"study_design_scores_gemma":[0.002815478,0.002226306,0.6282098,0.0002584265,0.0001315697,0.0009258711,0.00770352,0.003890016,0.001193401,0.3105756,0.04164381,0.0004261646],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5485995,0.008544053,0.3465171,0.08312626,0.007715065,0.0005823873,0.000005556436,0.00001679009,0.004893261],"genre_scores_gemma":[0.8692098,0.00000923224,0.128939,0.0004969473,0.0006752289,0.00001333938,2.122615e-7,0.00001087541,0.0006453835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6149047,"threshold_uncertainty_score":0.9863347,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5348286662951659,"gpt":0.5307739533614363,"spread":0.00405471293372961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01309391,0.0001922666,0.0004104144,0.000543511,0.0004388388,0.0003990021,0.0008269869,0.00004481585,0.0003827564],"category_scores_gemma":[0.01729727,0.0001097194,0.0001573092,0.0005971931,0.0001394506,0.0005455063,0.0002057493,0.0002829366,0.00002492711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002209879,"about_ca_system_score_gemma":0.0004899083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001539231,"about_ca_topic_score_gemma":0.00001265634,"domain_scores_codex":[0.9925035,0.001160385,0.00109898,0.0004101282,0.004579271,0.0002477637],"domain_scores_gemma":[0.990968,0.004523772,0.0007148724,0.0003130704,0.003221233,0.0002589787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009305493,0.001962275,0.7430373,0.00002848317,0.0006746833,0.00004619008,0.0326384,0.0002721522,0.09658835,0.001157331,0.03472285,0.08794147],"study_design_scores_gemma":[0.0004855337,0.0001302948,0.9815819,0.0003930096,0.00005757972,0.0007018356,0.002185552,0.0001520956,0.002108671,0.0104538,0.001568522,0.0001812397],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8142627,0.0007105923,0.1751042,0.007978208,0.001535077,0.0003270525,0.000012513,0.000002583699,0.00006713387],"genre_scores_gemma":[0.9600752,0.00001913873,0.03857353,0.0006987232,0.0005055739,0.00001074348,4.889051e-7,0.00001050942,0.0001060865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2385446,"threshold_uncertainty_score":0.9909804,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3249506735001434,"gpt":0.4596520375010046,"spread":0.1347013640008612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008859063,0.0001247831,0.0004129211,0.001426987,0.00008324292,0.00004119215,0.000459321,0.00005667575,0.00004765914],"category_scores_gemma":[0.211383,0.00008334225,0.0001210855,0.004073711,0.00007461554,0.0001144562,0.00004439354,0.0002195073,0.000003761507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001457562,"about_ca_system_score_gemma":0.0003763035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001886066,"about_ca_topic_score_gemma":0.00005292482,"domain_scores_codex":[0.9944184,0.0003060032,0.001543609,0.0002436639,0.003319919,0.0001684235],"domain_scores_gemma":[0.9664418,0.02611924,0.002071205,0.0003012055,0.004923602,0.0001429472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001327094,0.0006661367,0.76439,0.00001767012,0.00002301591,5.708511e-7,0.00003622641,0.001338829,0.0311418,0.001936294,0.01586521,0.1844516],"study_design_scores_gemma":[0.0002219026,0.0003402174,0.9390656,0.0001466325,0.00002561969,0.00004628023,0.00006508327,0.0002903151,0.001406758,0.05806874,0.0002494303,0.00007338991],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6878451,0.001358305,0.3032012,0.002095768,0.002840487,0.0003689249,0.00001203012,0.000007337359,0.002270819],"genre_scores_gemma":[0.8660614,0.000001883039,0.1335632,0.00002543,0.000308507,0.000007125321,0.000001091097,0.00000590706,0.00002548496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2025239,"threshold_uncertainty_score":0.7952599,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2134094557378299,"gpt":0.4190955226912946,"spread":0.2056860669534647,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00154343,0.0000524349,0.0001432712,0.00004717665,0.00005328668,0.0000163779,0.00009722285,0.00001743693,0.00002234366],"category_scores_gemma":[0.01056521,0.00003128716,0.00003055247,0.00008002178,0.00005949227,0.00003705541,0.000006693314,0.0000965449,1.417452e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006761886,"about_ca_system_score_gemma":0.0001860575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001585871,"about_ca_topic_score_gemma":0.00003304491,"domain_scores_codex":[0.998835,0.0001357871,0.0004929721,0.0000559013,0.0004055569,0.00007482992],"domain_scores_gemma":[0.9976238,0.001479431,0.0002768584,0.00009726955,0.0004779885,0.00004467433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003754599,0.0002603862,0.07222807,0.00002733818,0.000007377956,1.642128e-7,0.0002595087,0.000003939411,0.001127246,0.8972977,0.0003406866,0.02841004],"study_design_scores_gemma":[0.00006177272,0.00004658162,0.4811238,0.0000766587,0.000007301063,0.000002677064,0.0000323633,0.00001365543,0.00006204005,0.5185385,0.00001715864,0.00001756016],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.888183,0.0009747212,0.0888762,0.02092907,0.0003707434,0.0002148055,0.000007724353,0.00000194842,0.0004417799],"genre_scores_gemma":[0.789229,0.0000261952,0.2106634,0.00001698978,0.00005529121,0.000001519612,1.057521e-7,0.0000013947,0.000006127712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4088957,"threshold_uncertainty_score":0.9977692,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.350099387849287,"gpt":0.4756613456886337,"spread":0.1255619578393468,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05578407,0.0001807229,0.0004767511,0.001283956,0.00008681726,0.00007395583,0.0005396931,0.0001052494,0.00008853376],"category_scores_gemma":[0.07638445,0.0001413136,0.0001521713,0.0008572129,0.00004928675,0.0005888185,0.00006782785,0.000295611,0.000009865677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005170518,"about_ca_system_score_gemma":0.002325693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005891902,"about_ca_topic_score_gemma":0.00001196162,"domain_scores_codex":[0.9917957,0.00136527,0.002431893,0.0004500733,0.003697344,0.0002597151],"domain_scores_gemma":[0.9824462,0.01102217,0.001748991,0.0006100449,0.003984898,0.0001877255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006825726,0.001083887,0.1804753,0.00001399544,0.00003551924,0.000003553484,0.0008742341,0.6942161,0.1137998,0.0002955133,0.00009466513,0.002281692],"study_design_scores_gemma":[0.0007728226,0.0002045258,0.4788581,0.00008810813,0.00001219309,0.00009770285,0.000711058,0.5131901,0.0004598898,0.005344548,0.0001292176,0.0001317267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9653252,0.0003350355,0.03279902,0.0006694063,0.0005237919,0.000267706,0.000008876688,0.000005011892,0.00006589627],"genre_scores_gemma":[0.8661616,0.000003777808,0.1335813,0.00007178998,0.00009883042,0.00001175848,0.000001227034,0.0000118323,0.00005790061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2983828,"threshold_uncertainty_score":0.972269,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3012466859744121,"gpt":0.4266774629592089,"spread":0.1254307769847969,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00122307,0.0001127994,0.0001600125,0.00009566949,0.0001444082,0.0001233955,0.0007954196,0.00003241562,0.00002829815],"category_scores_gemma":[0.002315039,0.0000940699,0.00002493966,0.0000977119,0.00005550198,0.0006383612,0.0001410543,0.0001679152,0.000001209594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001955785,"about_ca_system_score_gemma":0.000508424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001889237,"about_ca_topic_score_gemma":0.0000236476,"domain_scores_codex":[0.9979215,0.0001294302,0.0005878019,0.0002517785,0.0009724339,0.0001370047],"domain_scores_gemma":[0.9973162,0.0004777885,0.0005579561,0.0004987031,0.001070416,0.00007893364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000666389,0.0004994089,0.004566924,0.0001199168,0.0001236716,0.000004515683,0.0003674093,0.001314704,0.2164056,0.5066014,0.03164512,0.2382847],"study_design_scores_gemma":[0.0003591166,0.0001552405,0.1301535,0.0001307253,0.00004648382,0.0001372823,0.0000172654,0.1084135,0.0006776497,0.7581525,0.001558922,0.000197747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007680226,0.0006416244,0.9828984,0.008206801,0.0002442407,0.0001564742,0.00002245093,0.00001538385,0.0001344282],"genre_scores_gemma":[0.5241539,0.000006222013,0.4756151,0.0000759272,0.0001302349,0.000002109538,0.000009014055,0.00000370066,0.000003716478],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5164737,"threshold_uncertainty_score":0.3836059,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6842492147562678,"gpt":0.529819503327333,"spread":0.1544297114289348,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01895082,0.00008853992,0.0003911719,0.0006583376,0.000275096,0.00004406178,0.0006119709,0.00002002647,0.0004649803],"category_scores_gemma":[0.1505744,0.00006447136,0.0002217139,0.001204847,0.0000555772,0.00008341571,0.00004305578,0.0001781681,0.000001520206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002171558,"about_ca_system_score_gemma":0.0009982039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007568528,"about_ca_topic_score_gemma":0.000002715785,"domain_scores_codex":[0.9947153,0.0009318049,0.001198713,0.0001542066,0.002866399,0.0001335339],"domain_scores_gemma":[0.9580836,0.03766682,0.001899433,0.0002452324,0.001983688,0.0001212769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005644303,0.001653287,0.7779037,0.00006694494,0.0001984594,4.980901e-7,0.0009492635,0.05203756,0.02159172,0.006310406,0.1122784,0.0264453],"study_design_scores_gemma":[0.003874741,0.004676634,0.7382927,0.000157792,0.0002124151,0.00003105726,0.003768564,0.006675349,0.01444881,0.1730152,0.05449144,0.0003552587],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9480686,0.001715119,0.02715563,0.01742548,0.003949674,0.0005232892,0.00003112977,0.000005636044,0.001125414],"genre_scores_gemma":[0.9549753,7.219386e-7,0.04459525,0.000139375,0.0001703093,0.0000410286,0.000001993457,0.000005366847,0.00007065936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1667048,"threshold_uncertainty_score":0.8565807,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7529540980675968,"gpt":0.4796196803409436,"spread":0.2733344177266532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008058826,0.00007989928,0.0002415795,0.000402391,0.00004820295,0.00003962346,0.000471546,0.00003235048,0.001177689],"category_scores_gemma":[0.01666983,0.00005668306,0.00008133424,0.0005419796,0.00003362056,0.000194784,0.00001564193,0.0001285421,0.0000492205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001686499,"about_ca_system_score_gemma":0.0006504118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002589893,"about_ca_topic_score_gemma":5.970788e-7,"domain_scores_codex":[0.9960083,0.0001535621,0.0008529919,0.0001470224,0.002717496,0.000120587],"domain_scores_gemma":[0.9914179,0.003660943,0.001275297,0.0002622162,0.003299369,0.00008428025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003259794,0.001036471,0.6190682,0.00008985038,0.0001842954,3.722452e-7,0.001416414,0.1701382,0.02813555,0.02166417,0.0733558,0.08458471],"study_design_scores_gemma":[0.0004109372,0.0002556197,0.9447799,0.00006640283,0.00002382397,0.0000204139,0.00114099,0.02984292,0.0006597081,0.0217014,0.0009865317,0.0001113041],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9530818,0.000552744,0.03478964,0.002992226,0.001445564,0.000112098,0.000008475073,0.000001748896,0.007015693],"genre_scores_gemma":[0.9067581,0.00003277836,0.09219344,0.00007008282,0.0001338315,0.000001086741,5.114379e-7,0.000004749691,0.0008054746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3257118,"threshold_uncertainty_score":0.9997354,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8135852760237042,"gpt":0.547201763889805,"spread":0.2663835121338992,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05667346,0.0001905845,0.0004038898,0.0009897898,0.0006091819,0.0002646892,0.0007596324,0.00005671128,0.0001024974],"category_scores_gemma":[0.3496663,0.0001461823,0.0001706395,0.002572598,0.00003266046,0.0003834127,0.0001349397,0.0002986209,0.00002728157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005020077,"about_ca_system_score_gemma":0.001058621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001080212,"about_ca_topic_score_gemma":0.00000762559,"domain_scores_codex":[0.9934541,0.0008953885,0.001609396,0.0003814826,0.003267982,0.0003916512],"domain_scores_gemma":[0.9104707,0.08028877,0.003507366,0.0003349282,0.005177811,0.0002204175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002539931,0.001599948,0.6261827,0.00008904078,0.0003316661,0.00001809686,0.003654623,0.02319495,0.03623732,0.002528484,0.05043581,0.2554734],"study_design_scores_gemma":[0.002373858,0.001847803,0.6918802,0.0006326229,0.0001087484,0.0000441738,0.01641327,0.07280599,0.001679935,0.2075657,0.004099534,0.0005481233],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07395511,0.0003500554,0.9180561,0.002275494,0.003142479,0.0007315764,0.00001534141,0.00003264646,0.001441255],"genre_scores_gemma":[0.5209432,0.000002339123,0.4783773,0.00007950716,0.0004355258,0.00003613986,0.000001157821,0.00001195869,0.0001128372],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4469881,"threshold_uncertainty_score":0.9713532,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics education; Natural language processing; Computer science; Psychology; Linguistics; Artificial intelligence; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.0603400789110201,"gpt":0.3634531269538653,"spread":0.3031130480428452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001102068,0.0001387808,0.0001619733,0.0006667032,0.00005993382,0.0002923589,0.0007003304,0.00004925052,0.00005033983],"category_scores_gemma":[0.0008987308,0.0001131882,0.00006712338,0.0007852433,0.00001965469,0.0006381894,0.00007587326,0.0002432007,0.0000129128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007342731,"about_ca_system_score_gemma":0.003160986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000397938,"about_ca_topic_score_gemma":0.00008423333,"domain_scores_codex":[0.9980659,0.00005126423,0.0004649051,0.0002267284,0.00099195,0.0001992339],"domain_scores_gemma":[0.9986936,0.000107439,0.0001549158,0.0001724255,0.0007522161,0.0001193593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008792432,0.001947171,0.03756291,0.001448024,0.0003726188,0.0001348939,0.007767938,0.002945095,0.2279967,0.5953418,0.09334922,0.03104571],"study_design_scores_gemma":[0.0008710664,0.0004514336,0.1640259,0.01567071,0.0001263697,0.002465985,0.0003995183,0.0379039,0.0263518,0.7483385,0.001868346,0.001526378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3117565,0.1270766,0.2627513,0.2867894,0.006964274,0.001536591,0.00001426534,0.000789537,0.002321594],"genre_scores_gemma":[0.7424302,0.000005522385,0.2567846,0.0002916866,0.0004289958,0.00001361513,9.531548e-7,0.00001024614,0.00003419501],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4306737,"threshold_uncertainty_score":0.5607453,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Library science; Curriculum; Christian ministry; Citation; Sociology; Political science; Computer science; Law; Pedagogy","retraction":null,"screen_n_in":null,"score":{"opus":0.2646006784507445,"gpt":0.5359710732399001,"spread":0.2713703947891556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01274795,0.0002171106,0.0006433449,0.0004668273,0.0001703864,0.0001184793,0.001222322,0.0001461417,0.001344955],"category_scores_gemma":[0.00127166,0.0001977466,0.0002015162,0.0004194893,0.0003253647,0.001003487,0.0002223656,0.0003142237,0.000006814988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004619776,"about_ca_system_score_gemma":0.004435346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008765811,"about_ca_topic_score_gemma":0.002426635,"domain_scores_codex":[0.9941118,0.0009550806,0.001377924,0.000373659,0.002875248,0.0003062319],"domain_scores_gemma":[0.9927987,0.0005647423,0.001505396,0.0005349906,0.00420022,0.0003958842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007192523,0.009434647,0.275816,0.0001965614,0.006314106,0.000002391492,0.01374417,0.0002510526,0.007412273,0.03518944,0.6379415,0.01297858],"study_design_scores_gemma":[0.001269218,0.0001961914,0.03516963,0.0001994334,0.001133053,0.0000158219,0.004877959,0.00006751272,0.0003644636,0.008367374,0.9480168,0.0003225482],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.0929963,0.3745171,0.2462174,0.1539546,0.02477576,0.003919349,0.001560368,0.00009909857,0.1019601],"genre_scores_gemma":[0.3929185,0.009596073,0.5875651,0.0004005759,0.003603125,0.00005590264,0.0005332574,0.00005239111,0.005275086],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.364921,"threshold_uncertainty_score":0.9995679,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3090948321123259,"gpt":0.4135517798954063,"spread":0.1044569477830803,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007525971,0.0001133221,0.0001611242,0.000433503,0.0001285067,0.0002213884,0.0003355138,0.00004041821,0.000004024763],"category_scores_gemma":[0.005787502,0.0001034885,0.00008798638,0.0004082581,0.00001425022,0.00096632,0.00003122394,0.0001519068,0.000001007347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008594862,"about_ca_system_score_gemma":0.001116206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004275144,"about_ca_topic_score_gemma":0.00003149608,"domain_scores_codex":[0.9978583,0.0002880432,0.0008091516,0.0002516231,0.0006480083,0.0001448783],"domain_scores_gemma":[0.9967602,0.001588733,0.0003741854,0.0002554495,0.0009385707,0.00008279008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001949505,0.01338958,0.3256512,0.001999299,0.001208868,0.0004280433,0.04773556,0.003149619,0.06710986,0.06462865,0.1498084,0.3229414],"study_design_scores_gemma":[0.0048801,0.005222192,0.6825269,0.002294685,0.0002627446,0.005961016,0.003437563,0.1511058,0.009784258,0.11055,0.02295389,0.001020757],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4610288,0.0002685058,0.5216942,0.01327293,0.001923183,0.001709633,0.00004401473,0.00005221256,0.000006516774],"genre_scores_gemma":[0.8706062,0.000002870036,0.1285308,0.0000658822,0.0004168789,0.0003397839,0.000008872392,0.000009769979,0.00001886494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4095775,"threshold_uncertainty_score":0.6928598,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8252373857984466,"gpt":0.5741859983791489,"spread":0.2510513874192978,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08857544,0.0003005321,0.0005705344,0.002309283,0.000298708,0.000897821,0.001660986,0.0001547786,0.0002535734],"category_scores_gemma":[0.2158653,0.0002266179,0.0002402783,0.001895032,0.0001625407,0.00130985,0.0003711816,0.0007098416,0.00002775071],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00113073,"about_ca_system_score_gemma":0.00654843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004539399,"about_ca_topic_score_gemma":0.00001652638,"domain_scores_codex":[0.9883168,0.002517258,0.002773235,0.0008899459,0.00499263,0.0005101099],"domain_scores_gemma":[0.9629046,0.03172566,0.0008491926,0.001156823,0.003013131,0.0003506152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01432725,0.0005581788,0.01819198,0.00002984713,0.0001244314,0.00006370104,0.0006863978,0.8537162,0.104743,0.0007528346,0.002930626,0.003875586],"study_design_scores_gemma":[0.0008695648,0.0001045443,0.1029048,0.0004256305,0.0000310238,0.0002176871,0.0005461132,0.8854753,0.0001912497,0.008191646,0.0008041426,0.0002382626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9304871,0.002790425,0.05987651,0.004344729,0.002127482,0.0001745742,0.00005095852,0.0000125895,0.000135615],"genre_scores_gemma":[0.8831483,0.00001344105,0.1158791,0.0001217988,0.0004293578,0.000005618737,0.000002874583,0.00002586491,0.000373648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1272899,"threshold_uncertainty_score":0.9990835,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03195175338742903,"gpt":0.3215903201546934,"spread":0.2896385667672643,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003500008,0.0001218142,0.0002594304,0.0002008538,0.0001632009,0.0000269859,0.0001682639,0.00004573296,0.00004963975],"category_scores_gemma":[0.0004779042,0.00008043722,0.00009153772,0.0001137051,0.00005935326,0.00005898158,0.00002377437,0.0001402715,0.000002884276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001579466,"about_ca_system_score_gemma":0.0006457237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001529572,"about_ca_topic_score_gemma":0.000003821161,"domain_scores_codex":[0.9985147,0.0002703744,0.0006421682,0.0001291696,0.0002937381,0.0001498134],"domain_scores_gemma":[0.9979714,0.0008409782,0.0003097685,0.0001473552,0.0006697879,0.00006073579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005578117,0.002580104,0.01890376,0.00195445,0.007791587,0.00008976,0.07649899,0.002528487,0.001763991,0.7607893,0.02438014,0.0971413],"study_design_scores_gemma":[0.05957355,0.001468451,0.1935163,0.01501396,0.004176045,0.01045167,0.02833325,0.008305037,0.008683035,0.4617766,0.2061529,0.002549233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9132726,0.01911639,0.04654428,0.01088608,0.003889988,0.001150539,0.000005647509,0.00000745303,0.005127086],"genre_scores_gemma":[0.9923044,0.00002045473,0.006412505,0.0003625013,0.0001256542,0.00006468423,0.000001943899,0.000009759895,0.0006981378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2990127,"threshold_uncertainty_score":0.3280135,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.233287845927402,"gpt":0.3977295805474502,"spread":0.1644417346200483,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009613713,0.0002767582,0.0004306461,0.0003503606,0.0003155564,0.0002124061,0.0008065459,0.00005291634,0.00001684954],"category_scores_gemma":[0.0001097058,0.00021361,0.0001215317,0.0005743017,0.00003140869,0.001061306,0.000155767,0.0002229646,4.207604e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234514,"about_ca_system_score_gemma":0.001503505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006126718,"about_ca_topic_score_gemma":0.0001810554,"domain_scores_codex":[0.9968321,0.0001796928,0.0007347908,0.0004591639,0.001418256,0.0003760063],"domain_scores_gemma":[0.995916,0.0002785983,0.0006007354,0.0005045338,0.002444106,0.0002559946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001419331,0.01015389,0.2059343,0.0002469596,0.002774913,0.00002032935,0.0005128519,0.2555192,0.07425781,0.3959546,0.02599247,0.02721333],"study_design_scores_gemma":[0.003717344,0.002788671,0.785786,0.001590485,0.0005863298,0.00006055098,0.00007309904,0.1324154,0.006550907,0.0640351,0.001398489,0.0009976801],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3063923,0.00006488577,0.6906399,0.001643788,0.0005885716,0.0006257754,0.000007957929,0.00001831677,0.00001855511],"genre_scores_gemma":[0.5438488,0.000001277604,0.4554617,0.0004260677,0.0001272462,0.00006143313,0.000004529093,0.000009584684,0.00005937689],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5798516,"threshold_uncertainty_score":0.8710763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}