First result · 2026-09-19 20:38 UTC
percentage points, not bare percent — a change to a percentage is stated in points, endpoints attached when known
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
- -6 tokens per declared item
Reported interval: -7 to -6.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_baseReader population not separately declared.
- Conditions covered
- Separate outcomes retained for all 2 declared conditions
rise,fallAn 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?
| Condition | Reported difference | Reported interval |
|---|---|---|
rise | -6 | Not recorded |
fall | -6 | 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 · rise-rescue-drone
- English input
- Alpine rescue drone availability increased additively by 8 units on the percentage scale, from 23% to 31%.
- Ainglish input
- Alpine rescue drone availability rose 8 percentage points, from 23% to 31%.
- Condition
- rise
Input 2 · rise-tidal-sensor
- English input
- Tidal sensor reporting coverage increased additively by 6 units on the percentage scale, from 41% to 47%.
- Ainglish input
- Tidal sensor reporting coverage rose 6 percentage points, from 41% to 47%.
- Condition
- rise
Input 3 · rise-rare-book
- English input
- Rare-book metadata completion increased additively by 9 units on the percentage scale, from 52% to 61%.
- Ainglish input
- Rare-book metadata completion rose 9 percentage points, from 52% to 61%.
- Condition
- rise
Input 4 · rise-kiln-recovery
- English input
- Kiln heat recovery rate increased additively by 5 units on the percentage scale, from 34% to 39%.
- Ainglish input
- Kiln heat recovery rate rose 5 percentage points, from 34% to 39%.
- Condition
- rise
Input 5 · rise-wetland-seed
- English input
- Wetland seed germination increased additively by 11 units on the percentage scale, from 18% to 29%.
- Ainglish input
- Wetland seed germination rose 11 percentage points, from 18% to 29%.
- Condition
- rise
Input 6 · rise-tram-ramp
- English input
- Low-floor tram ramp availability increased additively by 7 units on the percentage scale, from 63% to 70%.
- Ainglish input
- Low-floor tram ramp availability rose 7 percentage points, from 63% to 70%.
- Condition
- rise
Recorded input digest: 0617692da509569539eed0f74554ad1e5a2feeb176fa98685aa9afe71f0b54e1
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
- standard percentage-points wording versus its complete unambiguous additive-scale English expansion, with identical metric, direction, change and endpoints
- Tested population
- 24 frozen endpoint-attached percentage changes across 24 new domains, balanced twelve rises and twelve falls
- Unit tested
- one complete percentage-change report with both endpoints attached
- How results combine
- equal item mean within rise and fall; equal stratum weight per tokenizer; 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.
Absolute arm results
Not recorded
Reader or tokenizer results
[
{
"model": "cl100k_base",
"value": -7
},
{
"model": "o200k_base",
"value": -7
},
{
"model": "p50k_base",
"value": -6
}
]
Condition results
[
{
"id": "rise",
"weight": 1,
"share": 0.5,
"value": -6,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
},
{
"id": "fall",
"weight": 1,
"share": 0.5,
"value": -6,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
}
]
Exact result and immutable specificationExperiment history
Attempt f7605112-e875-4c25-b223-ad039e13e8f6
Content 43981c1706df75a78daf08896d82669144f7a5e2e03a31fcbdbc67630f313f72