Evidence readout
ambig moved `0% -> 20%`, while OOS dropped `78% -> 55%` and destructive stayed `67%`; not shipped on top of Gemma
What the attempt taught
Rule wrappers can expose the missing behavior, but they still need the same regression gates as model updates.
Why it stopped or stayed bounded
The shim improved ambiguity detection for the 4B floor but over-triggered and became unnecessary once Gemma reached the same ambig score with better OOS/destructive behavior.
Method and scope
- Experiment family: pace planner.
- Record kind: model evaluation.
- Objective: ambiguity detection.
- Methods: two stage shim.
- Base models: qwen3-4b.
Disposition
Keep as an option only if shipping the 4B footprint floor; do not stack it on the stronger Gemma path.
This retained disposition is historical evidence, not authorization to restart the experiment. A new run needs a fresh question, frozen evaluator, explicit resource budget, and scoped tracking issue.
How to read this dossier
This canonical page separates the retained repository decision from the material that informed it. A source may describe an external claim, historical measurement, local observation, or planned procedure; those evidence classes are not interchangeable. Follow the provenance links before reusing a number or method.
Status and disposition describe what PostTrainLLM retained when this record was indexed. They are not a live product promise, a newly run benchmark, or permission to restart historical work. Unknown or unmeasured fields remain unknown rather than being treated as zero.
To reuse the record, first name the exact claim you need and trace it to the linked source. Then check whether the original environment, model revision, data split, evaluator, hardware, and budget match the proposed use. If they do not, treat the record as a hypothesis or design reference and run the smallest fresh comparison that can falsify it. Preserve negative outcomes and regressions beside any improvement; a local win on one slice does not silently become a general capability claim.
Source provenance
The normalized record comes from docs/attempts.json. The links below are the tracked evidence and explanatory sources preserved with the record.