Execution attempt

Sign in with GitHub
← Experiment E9 · At a fixed 32k vocabulary, does reserving a small science slice of the tokenizer's training text remove most of the English-science fertility tax at under 5% cost to Polish fertility?

Execution attempt · A91 · planned

Writes flat headline values from the analysis, atlas, audit and tokenizer manifest, and re-checks the reference-tokenizer cells against the earlier atlas.

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 @ 7a2cffbe78cf5f6b8ee85b8ea6dd34fcb366b296

Reference checked 2026-09-14 13:15 UTC. Later commits, branches or plan changes do not retarget this attempt.

Command
python scripts/06_metrics.py
Working directory
experiments/E09-vocabulary-allocation
Configuration paths
None
Parameters
none
Environment
3.14.5; Python standard library on CPU; Apple silicon, 128 GB unified memory
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.

  • analysis.json · analysis · M449 analysis.json · raw output · Download
  • atlas.json · analysis · M447 atlas.json · raw output · Download
  • policy_audit.json · analysis · M446 policy_audit.json · raw output · Download
  • tokenizers_e9_manifest.json · analysis · M455 tokenizers_e9_manifest.json · raw output · Download
  • E01 atlas.json · reference result · M44 atlas.json · raw output · Download

Latest reported metrics

Values the registrant’s tool attached to its latest progress or outcome event. Substrate stores them; it verifies no measurement.

gate_g3_passed
1
gate_arms_total
5
h1_r_pool_e9_bal
0.2995595877508858
h1_r_pool_e9_sci
0.3996509990515416
gate_g1_arms_passed
5
gate_g2_arms_passed
5
gate_g4_arms_passed
5
gate_g5_arms_passed
5
h1_r_pool_e9_sci_ws
0.1675098874795578
h1_r_e9_bal_en_gsm8k
0.1573908586747973
h1_r_e9_sci_en_gsm8k
0.47130522774463174
h2_delta_pool_e9_bal
0.042536827598208315
h2_delta_pool_e9_sci
0.021519343325973717
preamble_en_tax_apt4
1.5465686274509804
gate_g4_lines_per_arm
10000
preamble_en_tax_e9_pl
1.482843137254902
preamble_en_tax_e9_bal
1.071078431372549
preamble_en_tax_e9_sci
1.2107843137254901
h1_r_e9_sci_ws_en_gsm8k
0.47208715536047563
h2_delta_pool_e9_pl_fix
-0.00046923044653024437
h2_delta_pool_e9_sci_ws
0.017857170602557204
h3_criterion_a_one_token
1
ws_only_pieces_e9_sci_ws
13
h1_r_pool_e9_bal_ci95_low
0.2823371015575238

and 134 more in the attempt JSON.

Delivered events

  1. Registered

    #1

    Writes flat headline values from the analysis, atlas, audit and tokenizer manifest, and re-checks the reference-tokenizer cells against the earlier atlas.

    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.

    gate_g3_passed=1 · gate_arms_total=5 · h1_r_pool_e9_bal=0.2995595877508858 · h1_r_pool_e9_sci=0.3996509990515416 · gate_g1_arms_passed=5 · gate_g2_arms_passed=5 · gate_g4_arms_passed=5 · gate_g5_arms_passed=5 · …

    • metrics.json · https://github.com/stw2/tokenizer-science-tax/blob/c5299916db7f792a209ff2944e66c673c3ebb817/experiments/E09-vocabulary-allocation/results/metrics.json · public · sha256 a5c4364c0722… · values fdd336d5e7c4… · 8559 bytes · M456

    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.