{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01448736,0.0003009278,0.0004787024,0.001397472,0.002265224,0.003091774,0.001831178,0.0002521295,0.008959416],"category_scores_gemma":[0.1657041,0.0002591013,0.00008639068,0.001651825,0.0002213338,0.0002922474,0.001421712,0.0003743048,0.0005912459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007690372,"about_ca_system_score_gemma":0.00001879661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002135299,"about_ca_topic_score_gemma":6.186248e-7,"domain_scores_codex":[0.9937074,0.003308199,0.0005967545,0.001095466,0.0008078791,0.0004842784],"domain_scores_gemma":[0.9882098,0.009161961,0.0005236649,0.0009789712,0.0008612861,0.0002642829],"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":[0.0003783615,0.0000497933,0.000001756254,0.00006142948,0.00004488869,0.00000633556,0.0004068308,0.00009583224,0.0001403274,0.005159037,0.59212,0.4015354],"study_design_scores_gemma":[0.0006746023,0.0003268829,0.0001355819,0.0001705719,0.0000262598,0.00003683153,0.0009823212,0.03254759,0.00002200293,0.02636798,0.9383522,0.000357147],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0004005866,0.000355624,0.5328797,0.000275706,0.0003306395,0.0007858654,0.000664114,0.001264114,0.4630436],"genre_scores_gemma":[0.0171162,0.0001861959,0.1575064,0.0006692288,0.0009914135,7.978015e-7,0.001582899,0.01077115,0.8111757],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4011783,"threshold_uncertainty_score":0.9999861,"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."}}