File-ops depth
100% saturated narrow gateQwen3-4B Multibackend Distilled
Adding multibackend teacher data did not create a broader agent. It preserved the saturated file-ops score while producing the worst breadth result in the recorded Qwen3-4B lineage. The public weights are useful as a reproducible warning: breadth gates must be frozen before specialist distillation.
Headline Numbers
Breadth
31% down from 59.6% stockBreadth delta
-28.6pp recorded stock-to-candidate changeDecision
Reject failed negative-transfer artifactCompetitive Context
| System | Metric | Score | Size / Class | Comparable? | Readout |
|---|---|---|---|---|---|
| Multibackend-distilled 4B | recorded depth / breadth | 100% / 31% | 4B | Direct | The target gate stayed saturated while breadth collapsed. |
| Stock Qwen3-4B | same recorded depth / breadth family | 58% / 59.6% | 4B | Direct | The candidate gained depth but lost 28.6 breadth points. |
| File-ops-distilled 4B | same recorded depth / breadth family | 100% / 42.3% | 4B | Direct | Already showed negative transfer; multibackend distillation made breadth worse. |
| ReST-fused 4B | same recorded depth / breadth family | 100% / 65% | 4B | Direct | The later teacher-free ReST attempt is the breadth-preserving research candidate. |
Direct rows share this artifact's eval setup. Directional rows are useful market context but should not be read as leaderboard claims.
Attempts and decisions
| Attempt | Method | Depth | Breadth | Decision |
|---|---|---|---|---|
| A0 | Stock Qwen3-4B | 58% | 59.6% | Baseline |
| A1 | File-ops distillation | 100% | 42.3% | Route only |
| A2 | Multibackend distillation | 100% | 31% | Reject |
| A3 | Teacher-free ReST | 100% | 65% | Research-only routed ship |
Release Blockers
Breadth collapsed
The recorded 31% breadth result is 28.6 points below stock and 11.3 points below the narrower file-ops distillation.
Unblock: Do not promote this checkpoint. Start from a breadth-preserving recipe with a frozen regression gate.
No committed machine-readable eval package
The exact historical result is preserved in the attempt ledger and session record, but raw predictions and a package-level eval report were not committed.
Unblock: Retain the result as historical evidence; only rerun if a new recipe needs the same checkpoint as a controlled baseline.