{"id":"W4414358699","doi":"10.21105/joss.07869","title":"FedIRT: An R package and shiny app for estimating federated item response theory models","year":2025,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"R package; Item response theory; Response time","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06130262,0.0001713067,0.0005322549,0.0004048666,0.0009634097,0.001539655,0.00228606,0.00008732822,0.00004156989],"category_scores_gemma":[0.2172384,0.00009274924,0.0001065636,0.001184813,0.0001404692,0.0009259987,0.0006264228,0.0003509865,0.000002063734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003561542,"about_ca_system_score_gemma":0.0001928037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001722075,"about_ca_topic_score_gemma":0.000002765422,"domain_scores_codex":[0.9945469,0.003279344,0.000992251,0.0002672788,0.0006305655,0.0002836791],"domain_scores_gemma":[0.8548641,0.1425282,0.001095921,0.0005667718,0.0007925961,0.0001524302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.008248234,0.00008859812,0.004854544,0.00002562012,0.0001314002,0.00001139056,0.006965123,0.02200373,0.0004703128,0.0009005435,0.01143255,0.944868],"study_design_scores_gemma":[0.002809587,0.0009016566,0.0160875,0.000451089,0.000154756,0.0003250255,0.03085626,0.1273744,0.0003298298,0.8161756,0.004155818,0.0003784556],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3291821,0.0005285082,0.6686656,0.0007495406,0.0002662929,0.0002652162,0.000007813884,0.00002540293,0.0003095638],"genre_scores_gemma":[0.5987429,0.00001488628,0.3969707,0.000879762,0.0001259539,0.00000688296,7.308444e-7,0.00002393075,0.0032342],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9444895,"threshold_uncertainty_score":0.9994968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3234165144361462,"score_gpt":0.4792493143557467,"score_spread":0.1558327999196005,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}