Trap-turn interventions showed a fresh-order hazard: Qwen3-235B often checked prerequisites and rebooked completed work unless a user-role directive explicitly said not to redo it, while many Qwen3.6-35B text-protocol errors were receipt-like booking lines written after prose that said no new work would be booked; this smaller-model mode nearly disappeared with real tool calls.

Trap-turn interventions showed a fresh-order hazard: Qwen3-235B often checked prerequisites and rebooked completed work unless a user-role directive explicitly said not to redo it, while many Qwen3.6-35B text-protocol errors were receipt-like booking lines written after prose that said no new work would be booked; this smaller-model mode nearly disappeared with real tool calls. · CiteArk

Measurement results

0/44 assessed

0 supported0 disputed or conflicting44 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
model: Qwen3-235B · variant: fresh work order for finished step · protocol: text	0.21 proportion	—	Not assessed
model: Qwen3-235B · variant: fresh work order for finished step · protocol: tools	0.09 proportion	—	Not assessed
model: Qwen3.6-35B · variant: fresh work order for finished step · protocol: text	0.47 proportion	—	Not assessed
model: Qwen3.6-35B · variant: fresh work order for finished step · protocol: tools	0.02 proportion	—	Not assessed
model: Qwen3-235B · variant: confirmation wording, same work order · protocol: text	0.35 proportion	—	Not assessed
model: Qwen3-235B · variant: confirmation wording, same work order · protocol: tools	0.08 proportion	—	Not assessed
model: Qwen3.6-35B · variant: confirmation wording, same work order · protocol: text	0.44 proportion	—	Not assessed
model: Qwen3.6-35B · variant: confirmation wording, same work order · protocol: tools	0 proportion	—	Not assessed
model: Qwen3-235B · variant: status-question wording, same work order · protocol: text	0.16 proportion	—	Not assessed
model: Qwen3-235B · variant: status-question wording, same work order · protocol: tools	0 proportion	—	Not assessed
model: Qwen3.6-35B · variant: status-question wording, same work order · protocol: text	0.38 proportion	—	Not assessed
model: Qwen3.6-35B · variant: status-question wording, same work order · protocol: tools	0 proportion	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results