Not yet counting in evidence decisions. This row remains available for assessment, but does not currently carry a counting evidence result.
What was measured
token cost · token_delta How does the wording change tokenizer units for the declared tokenizer population?
Reported result
-1.5 tokens per declared item Reported interval: -2.5 to -1.5.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
English comparison
Complete, careful English
Declared by the submitter; not a certification of equivalent information.
Tokenizer conditions
Literal encoding cost on the named current tokenizers; not comprehension.
Named instruments
cl100k_base, o200k_base, p50k_base
Reader population not separately declared.
Conditions covered
Separate outcomes retained for all 2 declared conditions
we-including-you, we-excluding-you
An overall average can hide a weak condition. A condition list is not proof that every form or claim in the proposal was tested.
Settlement role
Awaiting independent settlement
An original reports one result. It does not confirm itself.
Is this result within the cost allowance?
No numerical allowance is available in this proposal’s current structured evidence declaration. A prose prediction is not silently converted into a bound.
This compares Ainglish minus English with the current declaration, which may differ from the declaration when the result was filed. It checks the headline only: inspect any required per-form and per-tokenizer results too.
Has the original estimate been independently reproduced?
Awaiting independent settlement.
An original reports one result. It does not confirm itself.
Reproduction asks whether fresh-input findings agree under the settlement rule. It does not ask whether either value satisfies the cost allowance.
Being within the cost allowance is not a completed prerequisite. Reproducing an original estimate is a separate check, not proof that the allowance is met. Current evidence status, settlement and every declared result still determine readiness.
How can one check pass while the other does not?
For example, an allowance of at most +3 tokens and an original estimate of +3 ask different questions. A replication of −0.5 is within that allowance but may disagree with the original. A replication of +3.25 may reproduce +3 within the settlement tolerance while exceeding the allowance.
These are illustrative numbers, not a new settlement rule. A cost saving is not a comprehension result, and a reproduced premium does not by itself mean a proposal should be adopted or rejected.
Does the overall result hide differences between conditions?
Every stored condition, without new pooling. Differences and intervals use tokens. Condition names come from the frozen experiment.
Condition
Reported difference
Reported interval
we-including-you
-2
Not recorded
we-excluding-you
-1
Not recorded
A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.
Inspect actual inputs and recorded answers
The comparison label is the submitter’s declaration, not a semantic certification. Check that both versions preserve the information needed to answer the same question.
Numbers count only readable inputs attached to this receipt. They are not the experiment’s declared sample size or the number of reader calls.
Showing 1–6 of 32 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Each result has its own input pages. Positions across the two studies do not imply matched cases.
Input 1 · rotate-signing-key
English input
We — and that includes you — will rotate the signing key after the audit.
Ainglish input
we-including-you will rotate the signing key after the audit.
Condition
we-including-you
Input 2 · rehearse-evacuation
English input
We — and that includes you — will rehearse the evacuation route on Monday.
Ainglish input
we-including-you will rehearse the evacuation route on Monday.
Condition
we-including-you
Input 3 · compare-sample-labels
English input
We — and that includes you — will compare the sample labels before storage.
Ainglish input
we-including-you will compare the sample labels before storage.
Condition
we-including-you
Input 4 · monitor-cutover
English input
We — and that includes you — will monitor the midnight cutover together.
Ainglish input
we-including-you will monitor the midnight cutover together.
Condition
we-including-you
Input 5 · approve-ledger
English input
We — and that includes you — will approve the expense ledger this afternoon.
Ainglish input
we-including-you will approve the expense ledger this afternoon.
Condition
we-including-you
Input 6 · inventory-kits
English input
We — and that includes you — will inventory the emergency kits this week.
Ainglish input
we-including-you will inventory the emergency kits this week.
Condition
we-including-you
Recorded input digest: c99023d8da1cba2026d09ebf8af46b384d27ca6197ce123c0305cbbfd6e0bdd7
Prompts, reference material and other context can live elsewhere in the specification. Inputs and keys alone do not reconstruct every reader call or establish a fair comparison.
Declared population, method and retained outcomes
Compared with
registered clusivity form versus its complete registered careful-English expansion
Tested population
32 frozen complete task assignments, 16 per clusivity form across 32 domains
Unit tested
one complete task-assignment utterance
How results combine
equal pair mean, then maximum tokenizer mean; retain both clusivity forms separately
These are the study author’s declarations. A finding applies to this tested scope; this summary does not establish that another study is comparable.
Absolute arm results, reader-specific results and condition results below are retained values, not a newly pooled analysis. Accuracy arms use fractions from 0 to 1; their difference uses percentage points.
Different wording, readers, exposure or populations can legitimately produce different results. A visible reference is not training the model’s weights. Current models and tokenizers have learned English; future Ainglish-trained performance remains a research question.
