Guard-value contracts and stock-clean attention control
InvarLock 0.12.1 tightens the Mistral guard-value evidence contract, promotes targeted spectral/RMT/VE probes to required detections, and replaces the attention control with a stock-cap-clean 1.05x lane.
Release: InvarLock 0.12.1 - Guard-value evidence contracts and stock-clean attention control
Highlights
- The Mistral 7B guard-value package has a stock-cap-clean attention negative control:
spectral_moderate_scale_attn_l31_o_s105, a 1.05x attentiono_projscale that passes PM, adds no new baseline-relative spectral cap, and stays below the documented stock attention cap. - Targeted guard-value probes are stricter scenario contracts:
spectral_moderate_scale_mlp_l31_up_s112,rmt_norm_noise_l31_ffn_up_b030, andve_mlp_scale_skew_l31_down_s090are required detections for the Mistral guard-value package. - The old FP8 stress lane is historical/informational context instead of a current guard-value gate, and the retired attention control report is removed from the active public evidence package.
0.12.1 is a focused patch release for evidence interpretation. The public claim is not simply that "a guard moved." The current Mistral package has to show PM acceptance plus baseline-relative guard movement for the targeted spectral, RMT, and variance/VE probes, while keeping the selected attention control clean.
The Public Evidence Walkthrough and Failure Examples now point at the selected attention control, spectral_moderate_scale_attn_l31_o_s105. The useful detail is the stock-cap boundary: the attention target has z = 2.7987064430328767 against a stock cap of 3.018, so it remains a negative control rather than another guard-value hit.
The Evidence Pack Internals reference also reflects the scenario strictness split. must_fail reports are expected direct verification failures. must_detect reports can still pass direct invarlock verify when the primary metric and hard policy gates pass; the evidence-pack verdict then checks the required sidecars or baseline-relative guard movement. That distinction matters for guard-value evidence, because the targeted Mistral spectral, RMT, and VE probes are evidence-pack detections rather than generic report-schema failures.
There is a small docs-surface cleanup in the release as well: the upstream MkDocs assets harden MathJax loading and add focus and selection styling. The site sync carries those assets forward while preserving the site-owned docs palette transforms.
Sources
Website documentation explains the maintained workflow. The changes described here belong to InvarLock v0.12.1; the tagged release record preserves that historical scope.
More in Release
Explore nearby related posts.
Release note
InvarLock 0.13.0: One Request, One Signed Decision Trail
One YAML request now binds artifacts, schedule, metric, and policy. One signed evidence pack carries that comparison through independent verification and reporting.
Release
Self-edit evidence, backend compatibility, and larger model lanes
InvarLock 0.12.0 adds knowledge/self-edit workflow metadata, widens BYOE edit-lane evidence, and reorganizes public evidence around backend compatibility and larger model findings.
Release note
InvarLock 0.14.0: Evaluator Evidence In, Recipient Policy Out
v0.14 normalizes external evaluator records, then hands a signed technical receipt to recipient-owned trust and acceptance rules.