Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
ATANT is introduced as an open evaluation framework designed to measure continuity in AI systems, defined by the ability to maintain, update, and reconstruct context over time. The framework uses a 10-checkpoint evaluation methodology, operating without an LLM in the evaluation loop, and a narrative test corpus of 250 stories with 1,835 verification questions. Evaluation of a reference implementation showed progression from 58% to 100% accuracy in isolated and 50-story cumulative modes, and 96% at 250-story cumulative scale, demonstrating the framework's utility in assessing context retention.
Current "long-context" AI systems may be fooling us: ATANT reveals how easily they can fail at maintaining distinct narrative threads when multiple contexts coexist.
We present ATANT (Automated Test for Acceptance of Narrative Truth), an open evaluation framework for measuring continuity in AI systems: the ability to persist, update, disambiguate, and reconstruct meaningful context across time. While the AI industry has produced memory components (RAG pipelines, vector databases, long context windows, profile layers), no published framework formally defines or measures whether these components produce genuine continuity. We define continuity as a system property with 7 required properties, introduce a 10-checkpoint evaluation methodology that operates without an LLM in the evaluation loop, and present a narrative test corpus of 250 stories comprising 1,835 verification questions across 6 life domains. We evaluate a reference implementation across 5 test suite iterations, progressing from 58% (legacy architecture) to 100% in isolated mode (250 stories) and 100% in 50-story cumulative mode, with 96% at 250-story cumulative scale. The cumulative result is the primary measure: when 250 distinct life narratives coexist in the same database, the system must retrieve the correct fact for the correct context without cross-contamination. ATANT is system-agnostic, model-independent, and designed as a sequenced methodology for building and validating continuity systems. The framework specification, example stories, and evaluation protocol are available at https://github.com/Kenotic-Labs/ATANT. The full 250-story corpus will be released incrementally.