{"id":"W7103104071","doi":"","title":"The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Persona Design and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Narrative; Context (archaeology); Identity (music); Coherence (philosophical gambling strategy); Conceptual framework; Situated; Generative grammar","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002651012,0.0003463248,0.0004674967,0.0001047123,0.001924196,0.0008973816,0.002125686,0.0002541867,0.000008672735],"category_scores_gemma":[0.004259004,0.0003008729,0.0002303719,0.001723037,0.0008276112,0.0008668989,0.0004539801,0.0007484151,0.000057696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003395495,"about_ca_system_score_gemma":0.0008529016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001606846,"about_ca_topic_score_gemma":0.0002120973,"domain_scores_codex":[0.996371,0.0004892668,0.0008339464,0.001029752,0.0004979388,0.00077814],"domain_scores_gemma":[0.99272,0.004915659,0.000408945,0.001100748,0.0007199301,0.0001347126],"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":[0.00006729462,0.0003667017,0.1891846,0.0001378716,0.0001286306,0.000005515024,0.04736024,0.0002427786,0.003228861,0.75121,0.001250022,0.006817504],"study_design_scores_gemma":[0.002147898,0.000696003,0.2462287,0.002185953,0.0001602179,0.000009494899,0.06610097,0.6459317,0.0006570244,0.03025247,0.004638419,0.0009911467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4178342,0.003688061,0.5683389,0.006351947,0.001173298,0.002120107,0.00002774689,0.00007047135,0.0003953279],"genre_scores_gemma":[0.9926888,0.00007715698,0.002962529,0.001077173,0.0001570109,0.0009937993,0.000002411181,0.00001315479,0.002027993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7209575,"threshold_uncertainty_score":0.9999443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059554235835739,"score_gpt":0.37466355025563,"score_spread":0.2687081266720561,"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."}}