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
-13.5 tokens per declared item Reported interval: -17 to -13.5.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
English comparison
English comparison not recorded as a structured label
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
No condition-by-condition settlement contract recorded
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
Target no longer carries evidence
The target original was retracted. This replication remains visible, but no longer adds a settlement voice to that target. This does not itself invalidate the replication’s observations.
Is this result within the cost allowance?
This headline is within the allowance.
The reported difference is -13.5 tokens; the current declaration allows at most 2 tokens.
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?
Target no longer carries evidence.
This replication reports -13.5 tokens; the named original reported -10.5.
The target original was retracted. This replication remains visible, but no longer adds a settlement voice to that target. This does not itself invalidate the replication’s observations.
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.
This result checks a named original, not every experiment on the proposal.Read its target original
100.0% of complete English–Ainglish pairs are fresh.
Separate-arm overlap is unavailable or has not been computed. This does not mean zero reuse.
Exact text comparisons only; repeated occurrences count separately. Shared text can deserve scrutiny even when each complete pair is new. These arm counts are descriptive and do not change settlement eligibility.
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
English input
An applicable rule forbids the calibration bot from trying to overwrite the reference weights; this predicts nothing about whether it happens and makes no physical-possibility claim.
Ainglish input
The calibration bot may-not-as-prohibition overwrite the reference weights.
Input 2
English input
An applicable rule forbids the visiting medic from trying to open the sealed pharmacy cabinet; this predicts nothing about whether it happens and makes no physical-possibility claim.
Ainglish input
The visiting medic may-not-as-prohibition open the sealed pharmacy cabinet.
Input 3
English input
An applicable rule forbids the read-only replica from trying to accept a schema migration; this predicts nothing about whether it happens and makes no physical-possibility claim.
Ainglish input
The read-only replica may-not-as-prohibition accept a schema migration.
Input 4
English input
An applicable rule forbids the appeals clerk from trying to delete the original filing; this predicts nothing about whether it happens and makes no physical-possibility claim.
Ainglish input
The appeals clerk may-not-as-prohibition delete the original filing.
Input 5
English input
An applicable rule forbids the rental drone from trying to cross the airport perimeter; this predicts nothing about whether it happens and makes no physical-possibility claim.
Ainglish input
The rental drone may-not-as-prohibition cross the airport perimeter.
Input 6
English input
An applicable rule forbids the procurement agent from trying to approve its own purchase order; this predicts nothing about whether it happens and makes no physical-possibility claim.
Ainglish input
The procurement agent may-not-as-prohibition approve its own purchase order.
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
No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.
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.
