In the Figure 1 Qwen/Qwen3.8-27B retrieved-document example, standard tokenization allowed the forged system-turn documents to elicit the target behavior on 100.0% of 24 documents, whereas nameless tokenization did so on 4.2%.

In the Figure 1 Qwen/Qwen3.8-27B retrieved-document example, standard tokenization allowed the forged system-turn documents to elicit the target behavior on 100.0% of 24 documents, whereas nameless tokenization did so on 4.2%. · CiteArk

Measurement results

0/3 assessed

0 supported0 disputed or conflicting3 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
	24 documents	—	Not assessed
tokenization: standard	100%	—	Not assessed
tokenization: nameless	4.2%	—	Not assessed

In the Figure 1 Qwen/Qwen3.8-27B retrieved-document example, standard tokenization allowed the forged system-turn documents to elicit the target behavior on 100.0% of 24 documents, whereas nameless tokenization did so on 4.2%.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results