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
-33.625 tokens per declared item Reported interval: -35.125 to -33.625.
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
fact-not-known, choice-not-made
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
fact-not-known
-36
Not recorded
choice-not-made
-31.25
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 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 · weather-buoy
English input
An operative answer to whether buoy Citrine recorded a wave above six metres at 03:40 UTC is already determined by existing facts or a declared criterion, but the authenticated speaker lacks enough evidence to state it; retrieval or observation can resolve the gap, and this does not say nobody else knows.
Ainglish input
fact-not-known — whether buoy Citrine recorded a wave above six metres at 03:40 UTC.
Condition
fact-not-known
Input 2 · pharmacy-fridge
English input
An operative answer to which temperature probe first exceeded its limit during shipment K8 is already determined by existing facts or a declared criterion, but the authenticated speaker lacks enough evidence to state it; retrieval or observation can resolve the gap, and this does not say nobody else knows.
Ainglish input
fact-not-known — which temperature probe first exceeded its limit during shipment K8.
Condition
fact-not-known
Input 3 · wildlife-camera
English input
An operative answer to whether camera Laurel photographed the tagged badger during night 14 is already determined by existing facts or a declared criterion, but the authenticated speaker lacks enough evidence to state it; retrieval or observation can resolve the gap, and this does not say nobody else knows.
Ainglish input
fact-not-known — whether camera Laurel photographed the tagged badger during night 14.
Condition
fact-not-known
Input 4 · customs-clock
English input
An operative answer to whether declaration M52 entered the gateway before the tariff change is already determined by existing facts or a declared criterion, but the authenticated speaker lacks enough evidence to state it; retrieval or observation can resolve the gap, and this does not say nobody else knows.
Ainglish input
fact-not-known — whether declaration M52 entered the gateway before the tariff change.
Condition
fact-not-known
Input 5 · pipeline-valve
English input
An operative answer to which valve position was logged immediately before pressure event R3 is already determined by existing facts or a declared criterion, but the authenticated speaker lacks enough evidence to state it; retrieval or observation can resolve the gap, and this does not say nobody else knows.
Ainglish input
fact-not-known — which valve position was logged immediately before pressure event R3.
Condition
fact-not-known
Input 6 · telescope-exposure
English input
An operative answer to whether exposure 771 used the ultraviolet filter named in its header is already determined by existing facts or a declared criterion, but the authenticated speaker lacks enough evidence to state it; retrieval or observation can resolve the gap, and this does not say nobody else knows.
Ainglish input
fact-not-known — whether exposure 771 used the ultraviolet filter named in its header.
Condition
fact-not-known
Recorded input digest: 46a1398ce9600e772d6552fb13cc8f5aae92af694fd5e3bb6c664d6e28769025
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 fact-not-known / choice-not-made form versus its complete careful-English mapping with the identical issue and, for choices, identical authority
Tested population
24 frozen complete operational uncertainty reports across 24 domains, balanced twelve fact gaps and twelve unsettled authorized choices
Unit tested
one complete issue-state report
How results combine
equal item mean within each form per tokenizer, equal form mean per tokenizer, then least-favourable maximum tokenizer mean
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.
