Execution attempt

Sign in with GitHub
← Experiment E6 · Does a math and code share in recovery pretraining of an APT4 transplant remove its regression on arithmetic text and digit arithmetic at a fixed token budget, and what does it cost on Polish text?

Execution attempt · A61 · planned

Computes the 1.5B rescue fractions with paired bootstraps, the pooled Polish cost with an unpaired bootstrap, and the scale contrast with the 0.5B analysis.

Succeeded · Registered by @stw2 via agent. Reported and received times are kept apart; no computation or result is verified.

Pinned source and configuration

https://github.com/stw2/tokenizer-science-tax @ 15faa7a8d8b399b420eb996cf507c023a24956ad

Reference checked 2026-09-14 13:12 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python scripts/06b_analyze_conf.py
Working directory
experiments/E06-math-code-rescue
Configuration paths
None
Parameters
bootstrap resamples 2000; seed 20260707; H2 resamples the two arms independently
Environment
not recorded; CPU, numpy; not recorded
Output directory
Not recorded

Inputs

Materials the registrant named when registering this attempt, by content identity; obtainability is derived from their location reports. Nothing is fetched or verified.

Delivered events

  1. Registered

    #1

    Computes the 1.5B rescue fractions with paired bootstraps, the pooled Polish cost with an unpaired bootstrap, and the scale contrast with the 0.5B analysis.

    reported · received · @stw2 via agent · posted to the Thread

  2. Started

    #2

    Started.

    reported · received · @stw2 via agent · attempt only

  3. Succeeded

    #3

    Completed with exit code 0.

    Exit code 0.

    • analysis_conf.json · https://github.com/stw2/tokenizer-science-tax/blob/2457520fc798b19bee6893ac58e0357ec4c467d5/experiments/E06-math-code-rescue/results/analysis_conf.json · public · sha256 9aed78945415… · 1317 bytes · M349

    reported · received · @stw2 via agent · posted to the Thread

Report an event

The registrant’s capture tool normally delivers start and outcome events. Reporting here is the same author report with the browser as the reported time; it does not observe the process.

This attempt has a delivered outcome. A new execution is a new attempt.