memory-clarity-probe

name	memory-clarity-probe
description	Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.
alwaysApply	false
category	quality-assessment
tags	["memory-quality","anchor-questions","session-management","context-clarity"]
dependencies	["memory-palace:session-palace-builder"]
scripts	[]
usage_patterns	["pre-handoff-verification","session-checkpoint","summary-quality-gate","best-of-n-selection"]
complexity	simple
model_hint	standard
estimated_tokens	600

Table of Contents

• What It Is
• The Dual-Probe Pattern
• What This Is NOT
• When to Use
• Core Workflow
• Best-of-N Mode
• Output Format
• Integration Points
• Exit Criteria

Memory Clarity Probe

Assess whether a memory, summary, or session state retains enough task information to guide future reasoning.

What It Is

A quality gate for any memory or summary, based on the dual-probe pattern from MMPO (arXiv:2605.30159, Liu et al. 2026). The probe asks two anchor questions against the current memory and evaluates whether the answers are confident and complete:

1. Progress probe: "Based on current memory, what is the current task progress?"
2. Gap probe: "Based on current memory, what information is still needed?"

A clear memory answers the progress probe with specific, verifiable state (not vague placeholders) and enumerates bounded, concrete unknowns on the gap probe. An ambiguous memory produces hedging on the progress probe and open-ended uncertainty on the gap probe.

The Dual-Probe Pattern

The two probes target different failure modes:

• Confident-wrong: the model has a wrong but confident belief about task state. The gap probe alone misses this. The model claims it has enough. The progress probe catches it: if the stated progress contradicts known facts, the memory has drifted.
• Uncertain-incomplete: the model is uncertain about where the task stands. Both probes surface this: the progress answer hedges and the gap answer lists open-ended unknowns.

The MMPO paper's ablation (Table 4) shows progress+gap outperforms gap-only across all context lengths. Use both probes.

What This Is NOT

This skill implements a qualitative clarity assessment. It does not compute the token-level predictive entropy (Belief Entropy, Eq. 5 in MMPO) that the paper uses for RL training. Night-market has no access to the model's internal log-probabilities.

The paper's Table 6 shows that qualitative probing (labeled "direct-answer entropy", r=0.54) is weaker than true entropy (r=0.68), and can encourage premature confidence. Use this probe as a necessary quality check, not a sufficient one.

When to Use