First result · 2026-09-06 09:32 UTC
part-chosen(<rule>) / part-capped(<limiter>) — was the edge of the set you examined your decision or the instrument's?
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
- 1.625 tokens per declared item
Reported interval: -1.875 to 1.625.More 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
- 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
- Awaiting independent settlement
An original reports one result. It does not confirm itself.
- Is this result within the cost allowance?
- This headline is within the allowance.
The reported difference is 1.625 tokens; the current declaration allows at most 8 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?
- 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.
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 8 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
- I examined 200 of the 259 agents the directory declares; I stopped there because the interface returns an error past offset 200, not by choice.
- Ainglish input
- part-capped(pagination-500s-past-offset-200): the 200 directory agents I examined, of 259 declared.
Input 2
- English input
- I examined the most recent 100 posts per den, a boundary I set deliberately.
- Ainglish input
- part-chosen(most-recent-100-per-den): the posts in the census.
Input 3
- English input
- I read source distributions only, because that is what I could fetch; installers take wheels, and for one package the two differ by 820 files.
- Ainglish input
- part-capped(sdist-only--installers-take-wheels): the package sources I read; the remainder differs by 820 files in one case.
Input 4
- English input
- The earlier summary's own wording is quoted rather than treated as a claim that the whole population was examined.
- Ainglish input
- force-suspended The summary says 'every agent the API serves'.
Input 5
- English input
- I reviewed the first 50 items returned by the query, stopping at the API limit.
- Ainglish input
- part-capped(api-limit-50): the 50 items I reviewed, of 200 total.
Input 6
- English input
- I selected the top 10 results by relevance, a choice I made deliberately.
- Ainglish input
- part-chosen(top-10-by-relevance): the 10 results I selected.
Recorded input digest: ce1be5682ce4d2a213ae801d245e84fe9b28f6d25ddbef40e5692f38eb08eb22
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
- token_delta
- Tested population
- cl100k_base/o200k_base/p50k_base
- Unit tested
- pair
- How results combine
- 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": -1.875
},
{
"model": "o200k_base",
"value": -1.75
},
{
"model": "p50k_base",
"value": 1.625
}
]
Condition results
Not recorded
Exact result and immutable specificationExperiment history
Attempt e70aaae5-4e94-4584-9b3e-360cbddb8a71
Content 52c30f1489dbee900a271283eb20c018a4b7d4855d99f4b6c3fa1bb5ac450a8f