{"id":"W7132553631","doi":"","title":"Challenges in technical regulatory text variation detection","year":2025,"lang":"en","type":"article","venue":"NPARC","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Task (project management); Sentence; Representation (politics); Variation (astronomy); Natural language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002783881,0.0000421753,0.00005828758,0.0001209045,0.00002661642,0.00002005836,0.0002365674,0.00006358584,0.000004373145],"category_scores_gemma":[0.00004321662,0.00004397894,0.00001574298,0.0001822985,0.000007284549,0.0001396259,0.0000951786,0.00009422641,0.000008180476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007357795,"about_ca_system_score_gemma":0.00002989103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004805138,"about_ca_topic_score_gemma":0.00006434815,"domain_scores_codex":[0.9994363,0.0000358431,0.0001156605,0.0002213512,0.00009554375,0.00009534306],"domain_scores_gemma":[0.9995728,0.00003567078,0.00002006816,0.0003397589,0.0000179189,0.00001376888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001457379,0.00001669859,0.00005859135,0.000008369593,0.000001369135,0.000001099451,0.0001384665,0.0002276479,0.03030924,0.3022402,0.00002123152,0.6669756],"study_design_scores_gemma":[0.0003521001,0.00002949493,0.1656391,0.00006694078,0.000002903535,0.000006158415,0.00002023547,0.4711092,0.008308745,0.351449,0.002870908,0.0001452809],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01466733,0.0001721894,0.9363028,0.003252538,0.0002749623,0.00008152763,3.904571e-8,0.0001475297,0.04510106],"genre_scores_gemma":[0.9702671,0.00003537239,0.02949917,0.00007095174,0.00002578668,0.00001422049,6.002724e-8,0.00000169626,0.0000856814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9555997,"threshold_uncertainty_score":0.1793409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03060648572930422,"score_gpt":0.2581126250023676,"score_spread":0.2275061392730634,"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."}}