When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory

Abstract. An agent that inherits a consolidated memory may inherit a constraint that was true when written and has since been withdrawn by a newer authoritative record. Under a scarce verification budget, does the agent recover the withdrawal, and if not, is the error avoidable without spending more? We model supersession explicitly — historical provenance is immutable; what changes is which record is current — and assign by design the memory’s form, the world’s state (source current or superseded), and the verification policy at a fixed budget of two records: the agent’s own allocation, or the same budget with one slot re-assigned to the critical provenance path or to a random record. With a constraint stated, agents inspected its provenance path in about one episode in five; when that constraint had been superseded, native allocation produced stale-consistent decisions in 77.3%, 74.7% and 74.7% of episodes across a primary run, a fresh-wording replication and a held-out domain. Re-assigning one slot to the critical path raised current-record-consistent decisions by +74.0, +72.7 and +61.3 points, positive in six of six models in each of those runs, and changed nothing when the record agreed with the memory. The held-out scenario was later found to contain a temporal inconsistency; a robustness replication with one sentence corrected, deposited externally before execution, gave +73.3 points and is reported alongside the original. The intervention uses knowledge of the critical path and is not a scheduler; it identifies that the share of stale-memory error attributable to verification allocation is close to its structural ceiling. Memory systems may need freshness or supersession signals separate from relevance. Version notes (v1). First public version. The scientific content is the author's frozen canonical version 1.1 (2026-08-26): experiments, data, estimands, numbers, figures, tables, limitations and conclusions are unchanged. This public text (manuscript revision 1.2) adds related-work citations to recent work on stale, superseded and temporally valid agent memory, qualifies two sentences of the Discussion's positioning, adds PDF metadata and an AI-assistance statement. Every number in the paper is generated from the raw episode files by the included generator and verified by the included audit script. Data and code availability. All 5,400 confirmatory episode files (exact prompts, raw responses, parsed objects, deterministic scores) and the 48 labelled pilot episodes, the frozen specification packages with SHA256 manifests and OpenTimestamps proofs (Bitcoin blocks 964062 and 964064), the registration records, the frozen analysis scripts with their committed outputs, independent recomputation scripts with outputs, the runners, and the generator and audit scripts are in paper2-data-and-code-v1.zip (README inside). Re-running every analysis and rebuilding the paper requires only Python 3.12 and a TeX distribution; re-running the experiments requires provider API keys, which are not included. Evidence / prospective-specification statement. For the primary run, the fresh-wording replication and the original held-out run, the complete specification was frozen, hashed, committed and cryptographically timestamped (OpenTimestamps, 2026-08-25 23:05:06 UTC) before the first confirmatory model call (23:06:42 UTC); the package was deposited to OSF after the runs (project axsnm, files 75kaw and 8wes5) and verified against the pre-run manifest hash-for-hash. This deposit is an archival record, not a preregistration. For the corrected held-out robustness replication, the complete specification was deposited to OSF (file hdm75) and verified byte-for-byte before execution; its success criteria were fixed in advance and could have failed. Zero amendments were made to any package. Two self-found defects are disclosed with their size in the paper (a temporal inconsistency in the original held-out scenario; a design limitation of the forced-noncritical control). AI assistance. See the statement in the paper's back matter: the author used Anthropic's Claude (principally through Claude Code) for design critique, planning, implementation and execution of the runners, analysis and audit tooling, drafting, editing, simulated adversarial review and release engineering, and OpenAI's ChatGPT for design critique, interpretation discussion, manuscript critique, simulated adversarial review, and publication and release planning. The author is responsible for the research question, the decision to run each experiment, interpretation, claims, publication decisions and correctness. No model is an author; the six models studied are experimental subjects. Suggested citation. Nakayashiki, K. (2026). When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory (v1). Zenodo. https://doi.org/10.5281/zenodo.22108558 Relation to prior work. This paper tests the case that the author's earlier paper, Verification Allocation in Inherited Agent Memory: Provenance Availability Is Not Provenance Use (doi:10.5281/zenodo.22084498), explicitly left untested; it reuses that paper's instrument with a different randomised variable, different data and a different outcome.