{"id":"W4416033663","doi":"10.18653/v1/2025.tsar-1.9","title":"OneNRC@TSAR2025 Shared Task Small Models for Readability Controlled Text Simplification","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Readability; Task (project management); Text simplification; Feature (linguistics); Task analysis","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003580238,0.0008004676,0.001525768,0.0004753265,0.001000572,0.001311643,0.002737227,0.0007178953,0.0001451653],"category_scores_gemma":[0.001678249,0.0007612279,0.0008993056,0.001627523,0.0003654344,0.001528167,0.0005488161,0.0004772738,0.00009703203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000685497,"about_ca_system_score_gemma":0.001611486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005030589,"about_ca_topic_score_gemma":0.0003994198,"domain_scores_codex":[0.9922532,0.0006616234,0.002537572,0.002814192,0.0005777588,0.001155608],"domain_scores_gemma":[0.9899042,0.003090708,0.0006880235,0.00411718,0.001856334,0.0003435522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001468798,0.001658156,0.0002082238,0.0006198707,0.0003013512,6.178519e-7,0.001465852,0.00349719,0.004750369,0.7207454,0.004607094,0.2606771],"study_design_scores_gemma":[0.004440794,0.0002133783,0.002587185,0.0001091771,0.000212928,0.000001580191,0.0001571887,0.7878187,0.002652653,0.1919025,0.009279326,0.0006245751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004659443,0.0007855684,0.9459392,0.02360591,0.001150302,0.008203058,0.0002086451,0.0004706885,0.01497715],"genre_scores_gemma":[0.9405285,0.0001022087,0.03833154,0.001625173,0.0001331814,0.001695809,0.0001632581,0.00003145112,0.01738894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.935869,"threshold_uncertainty_score":0.9997251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.042788311038452,"score_gpt":0.2835559253019534,"score_spread":0.2407676142635015,"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."}}