Execution attempt

Sign in with GitHub
← Experiment E10 · Does the end-to-end success gap between Bielik-11B-v3.0-Instruct and Bielik-PL-11B-v3.0-Instruct on multi-step tool-use tasks exceed the gap predicted from their one-shot per-step success rates?

Execution attempt · A92 · planned

Generates the 100 task instances from the 20 templates and freezes the manifest.

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 @ 03e30b6cecb9c899914b18931b1f8ee0bdc7d2f5

Reference checked 2026-09-14 13:17 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python scripts/01_build_tasks.py
Working directory
experiments/E10-agentic-compounding
Configuration paths
None
Parameters
20 templates; 5 instances each; seed base 20260707
Environment
3.12.13 (uv 0.11.16); Apple silicon, 128 GB unified memory
Output directory
Not recorded

Delivered events

  1. Registered

    #1

    Generates the 100 task instances from the 20 templates and freezes the manifest.

    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.

    • tasks_manifest.json · https://github.com/stw2/tokenizer-science-tax/blob/03e30b6cecb9c899914b18931b1f8ee0bdc7d2f5/experiments/E10-agentic-compounding/configs/tasks_manifest.json · public · sha256 66029e45c11f… · 131774 bytes · M457
    • data/instances · Not redistributed: rebuild with experiments/E10-agentic-compounding/scripts/01_build_tasks.py, which reproduces configs/tasks_manifest.json byte for byte · restricted · sha256 5f3403e48364… · 257590 bytes · M459

    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.