Skip to content

spec(ship-two-models): v2.90.0 — §45 apr-cpu-vs-gpu-output-parity-v1 5/5 LIVE DISCHARGE milestone#1447

Merged
noahgift merged 2 commits into
mainfrom
spec/v2-90-cpu-gpu-parity-5-of-5-discharge
May 4, 2026
Merged

spec(ship-two-models): v2.90.0 — §45 apr-cpu-vs-gpu-output-parity-v1 5/5 LIVE DISCHARGE milestone#1447
noahgift merged 2 commits into
mainfrom
spec/v2-90-cpu-gpu-parity-5-of-5-discharge

Conversation

@noahgift

@noahgift noahgift commented May 4, 2026

Copy link
Copy Markdown
Contributor

Summary

Spec v2.89.0 → v2.90.0 records today's terminal-discharge milestone: `apr-cpu-vs-gpu-output-parity-v1` reaches 5/5 DISCHARGED — first contract in the SHIP-TWO program to achieve complete-evidence terminal state.

Milestone significance

What §45 records

Subsection Content
45.1 PR table (#1445 + #1446)
45.2 Complete observed jidoka chain (verbatim from smoke log)
45.3 Coverage flip table (5/5 → DISCHARGED)
45.4 Why this matters (audit + MODEL-1 + cadence)
45.5 Five Whys
45.6 Net effects
45.7 Next-session pickup (multi-PR research tracks)

Net effects

  • Contract `apr-cpu-vs-gpu-output-parity-v1` v1.3.0 → v1.5.0 ACTIVE, 5/5 DISCHARGED
  • MODEL-1 ship %: 89% → 91%
  • Coverage tally: 15+37 → 20+32 (+5 in one cycle)

Test plan

  • CI green on required gates

🤖 Generated with Claude Code

…5/5 LIVE DISCHARGE milestone

Canonical record of today's terminal-discharge milestone. The
apr-cpu-vs-gpu-output-parity-v1 contract reaches its complete state:
all 5/5 falsifiers DISCHARGED with live empirical evidence on the
canonical Qwen2.5-Coder-7B teacher.

Milestone significance:
- First contract in the SHIP-TWO program to reach 5/5 DISCHARGED
  (complete-evidence terminal state).
- Largest single-cycle coverage flip of the SHIP-TWO program: +5
  falsifiers DISCHARGED in one 2-PR cycle (#1445 + #1446).
- The §41 → §43 → §44 → §45 jidoka chain is contract-complete:
  silent-GPU-gibberish on canonical broken-GPU is no longer possible.
  Both impl closure AND end-to-end live verification delivered.

Coverage tally: 15+37 → 20+32.
Contract: v1.3.0 → v1.5.0 ACTIVE.
MODEL-1 ship %: 89% → 91%.

§45 documents:
- 45.1 What landed (PR table)
- 45.2 The complete observed jidoka chain (verbatim from smoke log)
- 45.3 Coverage flip (5/5 status table)
- 45.4 Why this milestone matters (audit + MODEL-1 + cadence)
- 45.5 Five Whys
- 45.6 Net effects
- 45.7 Next-session pickup (SHIP-007 GPU kernel fix, MODEL-2 §35
  real-training, cross-contract sweep — all multi-PR research tracks)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
@noahgift noahgift enabled auto-merge (squash) May 4, 2026 00:28
@noahgift noahgift merged commit be33cf8 into main May 4, 2026
10 checks passed
@noahgift noahgift deleted the spec/v2-90-cpu-gpu-parity-5-of-5-discharge branch May 4, 2026 01:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant