attested-exposure-gate

Task gallery / Security / cyber / Version 1

Reference solution (oracle): Pass
No-op resistance check: Pass
QA verdict: snorkel review: needs-revision x1, accept x1
Aggregate eligibility: Eligible version

The task

An instruction excerpt is not available in the public snapshot.

Excerpt only; not a complete executable task specification. Task ID review-db431123502e492e · version 1. Selection status: not fully recorded.

repo ↗

Results by model and effort

This exact task version only. Every rate is passes / valid runs with a Wilson 95% interval; n≤2 remains counts only. Macro aggregation does not apply within a single task. Baselines are summarized in the quality gates, not ranked. A passed no-op resistance check means that doing nothing did not solve the task.

Current evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes

Legacy evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes
Claude Opus 4.8 · default (unverified)	4/5 · 80.0% [37.6%, 96.4%]	0 / 5	0	GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0
GPT-5.5 · default (unverified)	0/5 · 0.0% [0.0%, 43.4%]	0 / 5	0	GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0

Every recorded run

14 recorded trials, including controls. Diagnostic labels do not replace verifier reward. Labels and quality checks are source declarations, not independently attested here. Internal evidence remains private; a missing public URL is shown explicitly. Records with invalid or absent rewards are not scored.

Run / model	Date / source	Reward / eligibility	Diagnostic class / source	Resources	Evidence
`tbench-task__rQzfkVP` oracle@@	Not recorded repo	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`tbench-task__N9QgEZb` oracle@@	Not recorded repo	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`tbench-task__DaJa7W9` oracle@@	Not recorded repo	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`tbench-task__rpsp7d4` nop@@	Not recorded repo	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`tbench-task__NLphQtN` Claude Opus 4.8 · default (unverified)	Not recorded repo	0 · valid	No diagnostic label derived	Tokens: 42,965 Turns: — Cost: $4.4037	Not publicly available
`tbench-task__TfuZZ6q` Claude Opus 4.8 · default (unverified)	Not recorded repo	1 · valid	No diagnostic label derived	Tokens: 53,093 Turns: — Cost: $6.0947	Not publicly available
`tbench-task__Qswfb7b` Claude Opus 4.8 · default (unverified)	Not recorded repo	1 · valid	No diagnostic label derived	Tokens: 39,121 Turns: — Cost: $3.7046	Not publicly available
`tbench-task__oEw9VvU` Claude Opus 4.8 · default (unverified)	Not recorded repo	1 · valid	No diagnostic label derived	Tokens: 34,821 Turns: — Cost: $3.6309	Not publicly available
`tbench-task__hRFvikH` Claude Opus 4.8 · default (unverified)	Not recorded repo	1 · valid	No diagnostic label derived	Tokens: 47,796 Turns: — Cost: $4.6357	Not publicly available
`tbench-task__Sxq6Tr4` GPT-5.5 · default (unverified)	Not recorded repo	0 · valid	No diagnostic label derived	Tokens: 27,332 Turns: — Cost: $4.9412	Not publicly available
`tbench-task__g7EqJqJ` GPT-5.5 · default (unverified)	Not recorded repo	0 · valid	No diagnostic label derived	Tokens: 31,074 Turns: — Cost: $6.0164	Not publicly available
`tbench-task__ou3Hkg8` GPT-5.5 · default (unverified)	Not recorded repo	0 · valid	No diagnostic label derived	Tokens: 26,386 Turns: — Cost: $5.2746	Not publicly available
`tbench-task__2F4w4qN` GPT-5.5 · default (unverified)	Not recorded repo	0 · valid	No diagnostic label derived	Tokens: 21,186 Turns: — Cost: $3.8243	Not publicly available
`tbench-task__c34jDAd` GPT-5.5 · default (unverified)	Not recorded repo	0 · valid	No diagnostic label derived	Tokens: 24,796 Turns: — Cost: $5.2070	Not publicly available