EXP-080VALIDATED
Canonical GPU engineering / SHA-256d

Independent replication of observable P8

The per-launch observable P8 candidate replicates on eight unseen headers while retaining the throughput of P8-S0.

Claim statusNO END-TO-END MINING ADVANTAGE DEMONSTRATED

Diagnostic work, exact algebra and local capabilities are not treated as end-to-end mining advantage.

Date2026-08-16
HardwareNVIDIA GeForce RTX 5080 · exact CUDA SHA-256d verifier
Run scopePreregistered paired campaign with sealed validation and audit
ReproducibilityUse the three sealed binaries, eight unseen headers, balanced order and separate P1 and P8-S0 comparisons.
01 / Question & hypothesis

What was tested?

The per-launch observable P8 candidate replicates on eight unseen headers while retaining the throughput of P8-S0.

02 / Scientific basis

Why the test is meaningful

A sub-percent orchestration effect requires binaries frozen before data, unseen headers, balanced order and separate comparisons against both the baseline and retained default.

R_1=wall(P8-S1)/wall(P1-S0)R_0=wall(P8-S1)/wall(P8-S0)replicate iff R_1 CI95_low>1 and retention is neutral
Independent replication of observable P8Visual reading of the published metrics and gates for EXP-080; it summarizes the registered result, not a mining advantage.EXP-080 / INDEPENDENT REPLICATION OF OBSERVABLE P8VERSUS P11.002459×P8 RETENTION1.000053HOST OBSERVATION0.020325 s
FIGURE / RESULT READINGVisual reading of the published metrics and gates for EXP-080; it summarizes the registered result, not a mining advantage.
03 / Method

How it was tested

Freeze P1-S0, P8-S0 and P8-S1, then run 64 measurements on eight new headers, alternating ABBA and BAAB without recompilation or reselection.

04 / Observed result

What happened

Versus P11.002459×
P8 retention1.000053
Host observation0.020325 s

S1 beat P1 on 8/8 headers at 1.002459×, CI95 1.001985–1.002933. It retained 1.000053 of P8-S0, CI95 0.999046–1.001060, with 0.020325 s observation.

05 / Validation

Exactness and statistical controls

All binaries recovered B32 and exact compiled factors with zero discrepancies; the candidate was frozen before replication.

06 / Interpretation

What the result means

Per-launch observability is independently reproducible and throughput-neutral versus P8-S0. Paired energy and thermal testing remains required before changing the default.

Limitations

  • Energy noninferiority is not established here.
  • The finding is local to the tested CUDA stack.
  • Lower latency does not increase per-hash success probability.
07 / Reproduction

Evidence trail

Use the three sealed binaries, eight unseen headers, balanced order and separate P1 and P8-S0 comparisons.

Canonical variants

CANONICAL-EXP-156PREREGISTERED-CAMPAIGNSEALED-AUDIT

Source: internally audited canonical reports. Local filesystem structure, private headers and operational identifiers are excluded from publication.