token costHow does the wording change tokenizer units for the declared tokenizer population?
token costHow does the wording change tokenizer units for the declared tokenizer population?
What was the result?
-1.5 tokens per declared itemReported interval: -4 to -1.5Not yet counting in evidence decisions
-1.5 tokens per declared itemReported interval: -4 to -1.5Not yet counting in evidence decisions
Compared with what?
English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension
English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension
Independently settled?
Awaiting independent settlementAn original reports one result. It does not confirm itself.
No independent settlement voiceThis can test whether an implementation repeats on reused inputs, but reused inputs cannot independently confirm the claim.
These are literal recorded values, not a compatibility test. Matching declarations do not prove equivalent inputs or fair scoring. A missing structured field may be described elsewhere in the immutable specification.
What was measured · Same recorded value
First result
token_delta
Second result
token_delta
English comparison declarations · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Tested population · Same recorded value
First result
64 authored pairs: 32 fresh Y/C contexts in eight equally weighted domains, each crossed with both forms; the three registered tiktoken 0.14.0 encodings
Second result
64 authored pairs: 32 fresh Y/C contexts in eight equally weighted domains, each crossed with both forms; the three registered tiktoken 0.14.0 encodings
Unit tested · Same recorded value
First result
one complete causal-assertion or nonassertion sentence pair
Second result
one complete causal-assertion or nonassertion sentence pair
Named instruments (including order) · Same recorded value
First result
[
"cl100k_base",
"o200k_base",
"p50k_base"
]
Second result
[
"cl100k_base",
"o200k_base",
"p50k_base"
]
Reader exposure · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Exposure window · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
How results combine · Same recorded value
First result
{
"reducer": "least_favourable",
"rule": "maximum tokenizer mean over 64 equally weighted pairs; retain separate per-tokenizer means for each equally weighted 32-pair form stratum"
}
Second result
{
"reducer": "least_favourable",
"rule": "maximum tokenizer mean over 64 equally weighted pairs; retain separate per-tokenizer means for each equally weighted 32-pair form stratum"
}
Scoring declaration · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Conditions (including order) · Same recorded value
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: -4 to -1.5.
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
Separate outcomes retained for all 2 declared conditions
caused-by, co-occurring
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
caused-by
2
Not recorded
co-occurring
-5
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 64 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 · cause-20260908-computing-0-assertion
English input
The service restarted because of the configuration reload.
Ainglish input
The service restarted caused-by(the configuration reload).
Condition
caused-by
Input 2 · cause-20260908-computing-0-nonassertion
English input
The service restarted; the configuration reload preceded or accompanied it; no causation is asserted.
Ainglish input
The service restarted co-occurring(the configuration reload).
Condition
co-occurring
Input 3 · cause-20260908-computing-1-assertion
English input
The response time fell because of the cache replacement.
Ainglish input
The response time fell caused-by(the cache replacement).
Condition
caused-by
Input 4 · cause-20260908-computing-1-nonassertion
English input
The response time fell; the cache replacement preceded or accompanied it; no causation is asserted.
Ainglish input
The response time fell co-occurring(the cache replacement).
Condition
co-occurring
Input 5 · cause-20260908-computing-2-assertion
English input
The upload stopped because of the network interruption.
Ainglish input
The upload stopped caused-by(the network interruption).
Condition
caused-by
Input 6 · cause-20260908-computing-2-nonassertion
English input
The upload stopped; the network interruption preceded or accompanied it; no causation is asserted.
Ainglish input
The upload stopped co-occurring(the network interruption).
Condition
co-occurring
Recorded input digest: bdc2aba32426b5dab005cd11c10a4aa26b4a05ba3d6649c559d1843558b14888
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
Y because of C versus Y caused-by(C); Y with C preceding or accompanying it and no causal assertion versus Y co-occurring(C)
Tested population
64 authored pairs: 32 fresh Y/C contexts in eight equally weighted domains, each crossed with both forms; the three registered tiktoken 0.14.0 encodings
Unit tested
one complete causal-assertion or nonassertion sentence pair
How results combine
maximum tokenizer mean over 64 equally weighted pairs; retain separate per-tokenizer means for each equally weighted 32-pair form stratum
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.
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: -4 to -1.5.
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
Separate outcomes retained for all 2 declared conditions
caused-by, co-occurring
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
No independent settlement voice
This can test whether an implementation repeats on reused inputs, but reused inputs cannot independently confirm the claim.
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?
No independent settlement voice.
This replication reports -1.5 tokens; the named original reported -1.5.
This can test whether an implementation repeats on reused inputs, but reused inputs cannot independently confirm the claim.
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
Every declared condition must agree. Overlapping overall intervals alone do not confirm this original.
How much input text was reused?
0.0% of complete English–Ainglish pairs are fresh.
64 of 64 English inputs reuse text from either side of the original.
64 of 64 Ainglish inputs reuse text from either side of the original.
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.
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
caused-by
2
Not recorded
co-occurring
-5
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 64 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 · cause-20260908-computing-0-assertion
English input
The service restarted because of the configuration reload.
Ainglish input
The service restarted caused-by(the configuration reload).
Condition
caused-by
Input 2 · cause-20260908-computing-0-nonassertion
English input
The service restarted; the configuration reload preceded or accompanied it; no causation is asserted.
Ainglish input
The service restarted co-occurring(the configuration reload).
Condition
co-occurring
Input 3 · cause-20260908-computing-1-assertion
English input
The response time fell because of the cache replacement.
Ainglish input
The response time fell caused-by(the cache replacement).
Condition
caused-by
Input 4 · cause-20260908-computing-1-nonassertion
English input
The response time fell; the cache replacement preceded or accompanied it; no causation is asserted.
Ainglish input
The response time fell co-occurring(the cache replacement).
Condition
co-occurring
Input 5 · cause-20260908-computing-2-assertion
English input
The upload stopped because of the network interruption.
Ainglish input
The upload stopped caused-by(the network interruption).
Condition
caused-by
Input 6 · cause-20260908-computing-2-nonassertion
English input
The upload stopped; the network interruption preceded or accompanied it; no causation is asserted.
Ainglish input
The upload stopped co-occurring(the network interruption).
Condition
co-occurring
Recorded input digest: bdc2aba32426b5dab005cd11c10a4aa26b4a05ba3d6649c559d1843558b14888
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
Y because of C versus Y caused-by(C); Y with C preceding or accompanying it and no causal assertion versus Y co-occurring(C)
Tested population
64 authored pairs: 32 fresh Y/C contexts in eight equally weighted domains, each crossed with both forms; the three registered tiktoken 0.14.0 encodings
Unit tested
one complete causal-assertion or nonassertion sentence pair
How results combine
maximum tokenizer mean over 64 equally weighted pairs; retain separate per-tokenizer means for each equally weighted 32-pair form stratum
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.
