File-ops hard gate
100% held from the distilled depth anchorQwen3-4B ReST Fused
This is the factory's first narrow ship decision from an existing measured candidate: the public weights, frozen fixtures, package, and routing boundary are preserved, while missing historical performance and trace evidence stays visible.
Headline Numbers
Breadth after ReST
65% up from 59.6% stock 4BBreadth delta
+5.4pp 52 held-out non-file-ops tasksPaid API cost
$0 teacher-free local ReST iterationCompetitive Context
| System | Metric | Score | Size / Class | Comparable? | Readout |
|---|---|---|---|---|---|
| posttrainllm Qwen3-4B ReST | out-of-domain breadth | 65% | 4B, 8.06GB stored | Direct | Recorded on the same 52-task breadth fixture and prompt family as stock. |
| Stock Qwen3-4B | same out-of-domain breadth fixture | 59.6% | 4B | Direct | The ReST iteration recovers breadth without giving up the file-ops depth gate. |
| File-ops-only distilled 4B | same out-of-domain breadth fixture | 42.3% | 4B | Direct | Shows the negative transfer that the ReST iteration was designed to recover. |
Direct rows share this artifact's eval setup. Directional rows are useful market context but should not be read as leaderboard claims.
Recorded result
| Gate | Stock | ReST candidate | Readout |
|---|---|---|---|
| File-ops hard gate | 0.58 | 1.00 | Depth preserved |
| Out-of-domain breadth | 0.596 | 0.65 | +5.4 points over stock |
| Latency / RAM / tok-s | not preserved | not preserved | No estimated values |
Release Blockers
Historical performance evidence missing
The original run did not preserve latency, RAM, tok-s, elapsed time, or raw predictions.
Unblock: Run a fresh product-specific gate only when a downstream integration justifies the heavy model work.
Not a Pace planner
Pace uses a different intent envelope and its own six-dimension ship gate.
Unblock: Re-distill on Pace's action surface and clear the Pace gate before runtime wiring.
Fine-Tune Report Card
The portable before/after proof for this artifact: baseline, candidate, deltas, regressions, slices, performance, eval validity, and the ship/retry/reject decision — with every value labeled measured, derived, historical, skipped, or not recorded. Compiled offline from the recorded factory evidence; no model was run to produce it.