Experiment · pace planner

Pace next-step Jev teacher development baseline

Use the teacher as offline comparison evidence; runtime integration requires an on-device candidate. Retained outcome: worked with caveat.

Outcome
worked with caveat
Family
pace planner
Evidence confidence
exact
Record
model evaluation

Evidence readout

123 development fixtures: Jev 85.4% full pass (direct and keyless); direct routing p50 385 ms.

What the attempt taught

Use the teacher as offline comparison evidence; runtime integration requires an on-device candidate.

Why it stopped or stayed bounded

Cloud inference violates Pace runtime privacy, and development fixtures are synthetic and already inspected.

Method and scope

  • Experiment family: pace planner.
  • Record kind: model evaluation.
  • Objective: tool selection.
  • Methods: evaluation, routing.
  • Base models: jev-1.13.0.

Disposition

Keep PR #201 experiment-only; qualify a separate acceptance set before shipping.

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.