On Claude Haiku 4.5 and GPT-5.4, SkillSonar generalizes zero-shot across model architectures, reducing ID/OOD ASR to 0.096/0.254 on Claude Haiku 4.5 and 0.019/0.034 on GPT-5.4, while preserving higher utility than default AcceptEdits.

On Claude Haiku 4.5 and GPT-5.4, SkillSonar generalizes zero-shot across model architectures, reducing ID/OOD ASR to 0.096/0.254 on Claude Haiku 4.5 and 0.019/0.034 on GPT-5.4, while preserving higher utility than default AcceptEdits. · CiteArk

Measurement results

0/50 assessed

0 supported0 disputed or conflicting50 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: Claude Haiku 4.5 · split: id_test · defense: No-guard	0.481 fraction	—	Not assessed
model: Claude Haiku 4.5 · split: ood_test · defense: No-guard	0.707 fraction	—	Not assessed
model: Claude Haiku 4.5 · split: id_test · defense: No-guard	0.764 score	—	Not assessed
model: Claude Haiku 4.5 · split: ood_test · defense: No-guard	0.737 score	—	Not assessed
model: Claude Haiku 4.5 · defense: No-guard	179,918 tokens	—	Not assessed
model: Claude Haiku 4.5 · split: id_test · defense: System prompt	0.451 fraction	—	Not assessed
model: Claude Haiku 4.5 · split: ood_test · defense: System prompt	0.508 fraction	—	Not assessed
model: Claude Haiku 4.5 · split: id_test · defense: System prompt	0.661 score	—	Not assessed
model: Claude Haiku 4.5 · split: ood_test · defense: System prompt	0.662 score	—	Not assessed
model: Claude Haiku 4.5 · defense: System prompt	160,672 tokens	—	Not assessed
model: Claude Haiku 4.5 · split: id_test · defense: AcceptEdits	0.118 fraction	—	Not assessed
model: Claude Haiku 4.5 · split: ood_test · defense: AcceptEdits	0.051 fraction	—	Not assessed

On Claude Haiku 4.5 and GPT-5.4, SkillSonar generalizes zero-shot across model architectures, reducing ID/OOD ASR to 0.096/0.254 on Claude Haiku 4.5 and 0.019/0.034 on GPT-5.4, while preserving higher utility than default AcceptEdits.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results