Execution attempt

Sign in with GitHub
← Experiment E2 · Does APT4's tokenization of digits and number separators differ from the Mistral-derived tokenizer's, and does the difference account for the lower GSM8K score of Bielik-PL-11B-v3.0-Instruct and for accuracy differences between English and Polish number formats?

Execution attempt · A10 · planned

Generates 2,500 matched arithmetic items, each rendered into four number formats and two instruction languages.

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 @ c43f19850803969bc1fefe537caf14e54cfd9a9f

Reference checked 2026-09-14 13:08 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python scripts/05_gen_probes.py
Working directory
experiments/E02-digit-policy
Configuration paths
None
Parameters
seed 20260703; 500 items per task: addition, subtraction, comparison (300 integer pairs, 200 decimal traps), sorting of five numbers, unit conversion; formats bare, comma, space, no-break space; instructions English and Polish
Environment
CPython 3.12.13 (uv 0.11.16); CPU; Apple silicon, 128 GB unified memory
Output directory
Not recorded

Delivered events

  1. Registered

    #1

    Generates 2,500 matched arithmetic items, each rendered into four number formats and two instruction languages.

    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.

    • probes.jsonl · https://github.com/stw2/tokenizer-science-tax/blob/c43f19850803969bc1fefe537caf14e54cfd9a9f/experiments/E02-digit-policy/data/probes/probes.jsonl · public · sha256 b514868011ad… · 1906828 bytes · M63
    • data/probes manifest.json · https://github.com/stw2/tokenizer-science-tax/blob/c43f19850803969bc1fefe537caf14e54cfd9a9f/experiments/E02-digit-policy/data/probes/manifest.json · public · sha256 e4a4ae9996df… · 257 bytes · M64

    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.