First result · 2026-09-08 11:45 UTC
choose-any / draw-uniform — does ‘pick a random one’ mean any member will do, or each must have equal odds?
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
- -5.875 tokens per declared item
Reported interval: -8.125 to -5.875.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
- 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?
- This headline is within the allowance.
The reported difference is -5.875 tokens; the current declaration allows at most 0 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?
- 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 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
- Choose exactly one healthy replica; any eligible member is acceptable and no probability distribution is required.
- Ainglish input
- choose-any(healthy-replicas).
Input 2
- English input
- Draw exactly one eligible reviewer using a random procedure that gives every distinct eligible reviewer equal probability.
- Ainglish input
- draw-uniform(eligible-reviewers).
Input 3
- English input
- Please make one equal-probability draw from the frozen 2026-09-02 audit-case set.
- Ainglish input
- Please draw-uniform(audit-cases@2026-09-02).
Input 4
- English input
- Select exactly one active node; any node is acceptable and no probability distribution is required.
- Ainglish input
- choose-any(active-nodes).
Input 5
- English input
- Draw exactly one backup coordinator using a random procedure that gives every coordinator equal probability.
- Ainglish input
- draw-uniform(backup-coordinators).
Input 6
- English input
- Pick exactly one test shard; any shard is acceptable without equal odds requirement.
- Ainglish input
- choose-any(test-shards).
Recorded input digest: 09970f3e44d77d8f608e2cbbf0259d17119e5c7ea661a7fc687ceca5cde5e412
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": -8
},
{
"model": "o200k_base",
"value": -8.125
},
{
"model": "p50k_base",
"value": -5.875
}
]
Condition results
Not recorded
Exact result and immutable specificationExperiment history
Attempt 778e07cd-c2e6-4839-982f-489370c8d4c5
Content 43cd8d393fa74c455b0f64d9a63a3e04b1b04542935b996d419a876a56f76b02