model review and local smoke

Needle 2

A compact call-only model combines top-five tool retrieval, constrained decoding, confidence escalation, bounded context, quantization, and a small packaged Mac artifact. Catalog restriction is a latency lever, not a capability rescue. Package size and narrow call formatting do not establish grounded tool competence.

Disposition
reviewed and rejected
Study class
model review and local smoke
Reviewed
2026-09-23
Evidence
Tracked source record

What mattered

A compact call-only model combines top-five tool retrieval, constrained decoding, confidence escalation, bounded context, quantization, and a small packaged Mac artifact.

What changed locally

A 94-case local smoke reached 34.0 percent exact tool selection. Oracle catalog restriction reached 38.3 percent overall but regressed Pace and retained false actions.

Evidence limits

Catalog restriction is a latency lever, not a capability rescue. Package size and narrow call formatting do not establish grounded tool competence.

Retained disposition

Stop before integration or fine-tuning unless a new model or method changes the capability premise.

The action is retained as study context rather than an active backlog item. Any implementation, download, training run, or benchmark requires a fresh scoped question under the repository's experiment gate.

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/studies/registry.json. The links below are the tracked evidence and explanatory sources preserved with the record.