{"id":"W6950076615","doi":"10.5281/zenodo.16691211","title":"FedIRT: An R package and Shiny app for estimating federated item response theory models","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Item response theory; Measure (data warehouse); Feature (linguistics); Field (mathematics); Key (lock)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006370841,0.003666998,0.002388865,0.003718913,0.0006543682,0.00234101,0.002815028,0.001236495,0.1628287],"category_scores_gemma":[0.05179394,0.002271049,0.003510836,0.003146824,0.0004960702,0.001905249,0.0028623,0.002032105,0.138382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009590348,"about_ca_system_score_gemma":0.002306658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006393638,"about_ca_topic_score_gemma":0.01013148,"domain_scores_codex":[0.9966463,0.001676802,0.0003790098,0.0005383229,0.0005681804,0.0001913324],"domain_scores_gemma":[0.977479,0.01625479,0.001059836,0.003323317,0.001623223,0.0002598162],"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":[0.0003854234,0.0001299679,0.00442566,0.001561697,0.0008474493,0.0001733021,0.0002468371,0.006670955,0.001080834,0.008450158,0.8020816,0.173946],"study_design_scores_gemma":[0.001364487,0.0003269963,0.01756965,0.00119754,0.001328577,0.0008747492,0.0001760632,0.1133296,0.00864688,0.08794414,0.7667963,0.0004449591],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.00388655,0.0005156386,0.4214724,0.0004146625,0.0002581464,0.0007692135,0.2540885,0.3081809,0.01041393],"genre_scores_gemma":[0.02597323,0.0004013226,0.6037076,0.0005886997,0.0001379897,0.006403028,0.18703,0.1482603,0.02749788],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1628287,"threshold_uncertainty_score":0.5447162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2855873603340278,"score_gpt":0.4031943907775357,"score_spread":0.1176070304435079,"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."}}