PAT-0350
Persistence Instability
A structural condition where persisted state cannot be stored and restored into an equivalent structure without alteration.
Primary Lenses
Reference Stability Lens
Evaluates whether structural references, identifiers, nodes, and edges remain consistent across execution cycles or comparable states.
Lens Application
The Reference Stability Lens is a primary inspection mechanism for Persistence Instability because it focuses on whether persisted structures return with stable references and equivalent relationships. It can surface altered identifiers, reordered links, broken edges, or reference drift introduced during save, load, serialization, or migration paths.
Inspect For
- Identifier changes after restore
- Broken or remapped references
- Node and edge drift across cycles
- Equivalent state with altered structure
Avoid
Treat reference changes as inspection signals that may indicate Persistence Instability, not as standalone proof that it has been established.
Secondary Lenses
Determinism Lens
Evaluates whether identical structural inputs produce equivalent structural outputs across repeated executions.
Lens Application
As a secondary lens, the Determinism Lens supports inspection of Persistence Instability by surfacing inconsistent restoration outcomes across repeated persistence cycles. If identical persisted structures restore into varying or altered forms, determinism checks may help locate where persistence behavior contributes to structural instability.
Inspect For
- Different restored structures from identical persisted inputs
- Repeated save/load cycles producing drift
- Non-deterministic ordering, defaults, or identifiers after restore
- Environment-dependent restoration behavior
Avoid
Treat inconsistent restoration as a supporting inspection signal, not as standalone confirmation that Persistence Instability is present.
Primary Issue Matches
AI Forgets Earlier Constraints
A constraint, instruction, preference, or decision that should persist through the task stops affecting later output.
Saved Memory Not Used
A saved memory, preference, instruction, or durable context item exists but does not affect the AI output when it should.
Task Progress Is Lost Midway
The AI loses track of completed work, prior decisions, current position, or remaining steps before the task is finished.
Supporting Issue Matches
AI Memory Has No Governance
Saved or persistent AI memory affects output without clear rules for ownership, scope, review, update, expiry, or removal.
AI Memory Updated Without Asking
AI memory, saved context, preference, or durable state is updated without the user clearly asking for or approving that update.
Context Changes After Restore
Restoring, reopening, resuming, or reloading a task changes the context that the AI uses to continue the work.
Context Leaks Between Tasks
Context, assumptions, constraints, examples, files, or decisions from one task affect another task where they should not apply.
Old Output Expectations Survive Migration
Expectations from a prior model, prompt, schema, tool, or workflow survive a migration and continue shaping review or downstream handling after they should be replaced.
Policy Update Not Reflected in Output
A policy, rule, standard, or instruction has been updated, but the AI output still follows the older version.
Revoked Approval Still Treated as Active
An approval, permission, exception, or authorization that was revoked continues to affect AI behavior or workflow decisions as if it were still active.
Rubric Changed but Results Did Not
A review rubric, scoring rule, evaluation standard, or classification criterion changes, but AI results continue to reflect the old rubric.
Stale Context Affects Output
Old context, prior instructions, outdated references, or earlier task state continue to affect output after they should no longer apply.