Restoring Evidence Routing Does Not Restore Exact Matching in Compressed KV Caches

Exact lookup requires both access to a record and discrimination of its complete address. We test record recovery, targeted restoration, and source-specific matching under query-agnostic KV-cache compression. Phase 1 reveals a recovery–decision gap in 45 of 144 positive queries under prefix-only attention selection. Both complete source records are independently recoverable from the same cache in these cases, yet the existence readout denies a match. Phase 2 uses independently coded records and equal-byte substitutions of evicted primary-record versus matched nonprimary positions. Primary restoration reduces false absence from 64/96 to 7/96 relative to sham, but also increases near-miss errors. Phase 3 separates the two sources factorially. Restoring A predominantly changes A-queries, and restoring B changes B-queries, yielding a predeclared crossover of $79.17$ percentage points with a conservative lower bound of $14.13$ points. Joint restoration reduces false absence by $76.04$ points while increasing one-field false alarms by $47.92$ points. Full and joint restoration both reject all 48 far negatives, yet accept 61 and 55 of 96 near negatives, respectively. This source-selective overmatching separates reinstated source influence from exact Boolean comparison. The resulting diagnostics separately measure record recovery, behavioral fidelity, and query discrimination.