Counts in current evidence decisions. This row currently contributes to evidence decisions. Its direction is separate from whether the proposal is ready for adoption.
What was measured
token cost · token_delta How does the wording change tokenizer units for the declared tokenizer population?
Reported result
-25.916666666667 tokens per declared item Reported interval: -28.166666666667 to -25.916666666667.
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
Confirmed by eligible settlement
Eligible fresh-input replications currently give this original a settlement majority.
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?
Confirmed by eligible settlement.
Eligible fresh-input replications currently give this original a settlement majority.
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.
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 24 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
The choice whether to release the disputed vendor refund requires a human decision because the fraud and fulfilment records conflict; an agent must not resolve it, and release the disputed vendor refund without that decision is out of scope.
Ainglish input
release the disputed vendor refund human_needed(the fraud and fulfilment records conflict).
Input 2
English input
The choice whether to delete the archived customer export requires a human decision because an unresolved legal hold may cover it; an agent must not resolve it, and delete the archived customer export without that decision is out of scope.
Ainglish input
delete the archived customer export human_needed(an unresolved legal hold may cover it).
Input 3
English input
The choice whether to grant the emergency production role requires a human decision because the two named service owners disagree; an agent must not resolve it, and grant the emergency production role without that decision is out of scope.
Ainglish input
grant the emergency production role human_needed(the two named service owners disagree).
Input 4
English input
The choice whether to publish the incident attribution requires a human decision because the investigation has two incompatible findings; an agent must not resolve it, and publish the incident attribution without that decision is out of scope.
Ainglish input
publish the incident attribution human_needed(the investigation has two incompatible findings).
Input 5
English input
The choice whether to accept the damaged medical shipment requires a human decision because the safety exception has no delegated owner; an agent must not resolve it, and accept the damaged medical shipment without that decision is out of scope.
Ainglish input
accept the damaged medical shipment human_needed(the safety exception has no delegated owner).
Input 6
English input
The choice whether to waive the missed accessibility review requires a human decision because the policy names no automated waiver authority; an agent must not resolve it, and waive the missed accessibility review without that decision is out of scope.
Ainglish input
waive the missed accessibility review human_needed(the policy names no automated waiver authority).
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.
