Metraipolis › archive › dc_086348ee5bd7
The Situated Identity Test: Distinguishing Persistent Cognitive Identity from Persona Imitation — arXiv:2609.22195
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22195
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:13.329Z
- SHA-256 of the archived text
b7b9949c44b9c772a55cc326028ce5c8622f223720f09a7c3d808920dcc6f937- Stable URL of this page
https://metraipolis.com/documento/dc_086348ee5bd7
How to cite
The Situated Identity Test: Distinguishing Persistent Cognitive Identity from Persona Imitation — arXiv:2609.22195 — arXiv (en), https://arxiv.org/abs/2609.22195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_086348ee5bd7 (Metraipolis archive dc_086348ee5bd7, sha256 b7b9949c44b9c772a55cc326028ce5c8622f223720f09a7c3d808920dcc6f937)
BibTeX
@misc{dc086348ee5bd7,
title = {The Situated Identity Test: Distinguishing Persistent Cognitive Identity from Persona Imitation — arXiv:2609.22195},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22195},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_086348ee5bd7; sha256 b7b9949c44b9c772a55cc326028ce5c8622f223720f09a7c3d808920dcc6f937},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can convincingly adopt personas, recall past dialogues, and weave rich autobiographies. Yet this conversational eloquence conceals a fundamental attribution problem: looking the part does not mean having lived the life. Two individuals can share identical public profiles--the same age, hometown, occupation, and personality traits--while possessing entirely distinct private histories, relationships, and acquired skills. When conditioned solely on that shared profile, an agent lacks the information required to determine which lineage is correct. We introduce the Situated Identity Test (SIT), an architecture-independent framework that evaluates whether an agent's behavior is functionally attributable to a specific developmental lineage. Grounded identity requires both appropriate knowledge of recorded experiences and appropriate ignorance of ungrounded ones, bounded by what the identity has actually acquired rather than what its underlying foundation model knows. We prove that any policy conditioned solely on a compressed profile is bounded by an average situated validity of at most 1/m across m colliding life histories on lineage-discriminative queries (at most 50% for paired lineages). We instantiate this framework in SITBench, an evaluation suite designed for 25 profile-collision pairs (50 distinct lineages) across 10,000 planned probes and nine architectural configurations. Supported by an open-source reference implementation, deterministic test fixtures, and empirical pilot evaluations on frontier foundation models (GPT-5.6 Sol and Claude Opus 5), we formalize the failure modes of persona prompting under profile collision and provide an assurance harness for evaluating episodic continuity, structured state, and epistemic boundaries. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.22195 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:48:44.869Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).