{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005710749,0.001653844,0.00139803,0.001123853,0.0009865438,0.002853647,0.003766526,0.001558508,0.01969488],"category_scores_gemma":[0.02500749,0.0007577658,0.001438162,0.0006344102,0.0008538443,0.00477551,0.003396983,0.002923436,0.01083891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002216087,"about_ca_system_score_gemma":0.002895419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008748273,"about_ca_topic_score_gemma":0.01425245,"domain_scores_codex":[0.9950947,0.001989866,0.0003150844,0.001119696,0.001212655,0.0002680684],"domain_scores_gemma":[0.9854115,0.005586796,0.0005138179,0.005435879,0.002276829,0.0007752545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003693228,0.002298771,0.006510039,0.00249159,0.0006562234,0.0007298519,0.002318357,0.1377254,0.04734151,0.02035353,0.2410671,0.5348144],"study_design_scores_gemma":[0.0004379529,0.001105098,0.002082664,0.00009206012,0.0001372325,0.0002459935,0.0003525575,0.8597856,0.02956505,0.01337036,0.09265389,0.000171602],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08287939,0.0006579566,0.6920978,0.001625044,0.0009219128,0.002196644,0.005775156,0.1942602,0.019586],"genre_scores_gemma":[0.455949,0.0002259647,0.4699489,0.0007512431,0.0002047114,0.002254686,0.02858084,0.01250879,0.02957592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01969488,"threshold_uncertainty_score":0.06588596,"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."}}