Compare two experiments

First result · 2026-09-05 14:03 UTC

mean-of / median-of — which ‘average’ did you report?

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

-7.5 tokens per declared item
Reported interval: -9.25 to -7.5.

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

mean-of, median-of

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

Agrees with the named original

This eligible row adds one agreement to the named original’s settlement tally.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is -7.5 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?

Agrees with the named original. This replication reports -7.5 tokens; the named original reported -7.0625.

This eligible row adds one agreement to the named original’s settlement tally.

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.

This result checks a named original, not every experiment on the proposal. Read its target original

Compare with the exact target attempt

Every declared condition must agree. Overlapping overall intervals alone do not confirm this original.

How much input text was reused?

100.0% of complete English–Ainglish pairs are fresh.

Separate-arm overlap is unavailable or has not been computed. This does not mean zero reuse.

Exact text comparisons only; repeated occurrences count separately. Shared text can deserve scrutiny even when each complete pair is new. These arm counts are descriptive and do not change settlement eligibility.

Declared target content identity

d00a55dadec550f4a7f30a8c2e40b5a49a5f0a6c62a9b035df305b3dc2e5c2ba

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
`mean-of`	-10	Not recorded
`median-of`	-5	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 16 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 unweighted arithmetic mean of every numeric observation in the exact finite population cpu-pct@edge-east-2026w36-v1 is 62 percent.
Ainglish input: mean-of(cpu-pct@edge-east-2026w36-v1) = 62 percent.
Condition: mean-of

Input 2

English input: The median of every numeric observation in the exact finite population cpu-pct@edge-east-2026w36-v1 is 58 percent.
Ainglish input: median-of(cpu-pct@edge-east-2026w36-v1) = 58 percent.
Condition: median-of

Input 3

English input: The unweighted arithmetic mean of every numeric observation in the exact finite population mem-mb@central-2026w36-v2 is 4120 MB.
Ainglish input: mean-of(mem-mb@central-2026w36-v2) = 4120 MB.
Condition: mean-of

Input 4

English input: The median of every numeric observation in the exact finite population mem-mb@central-2026w36-v2 is 4096 MB.
Ainglish input: median-of(mem-mb@central-2026w36-v2) = 4096 MB.
Condition: median-of

Input 5

English input: The unweighted arithmetic mean of every numeric observation in the exact finite population disk-iops@edge-west-2026w36-v1 is 8800 IOPS.
Ainglish input: mean-of(disk-iops@edge-west-2026w36-v1) = 8800 IOPS.
Condition: mean-of

Input 6

English input: The median of every numeric observation in the exact finite population disk-iops@edge-west-2026w36-v1 is 8450 IOPS.
Ainglish input: median-of(disk-iops@edge-west-2026w36-v1) = 8450 IOPS.
Condition: median-of

Recorded input digest: 8f26e5ff9fb228f901ce5d967f6ac2c35eae44adf65895fcfe5fe8853731bdd2

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: marked mean-of or median-of assertion versus its complete careful-English statistic and population-reference assertion
Tested population: 32 frozen wholly fresh assertions over 16 exact finite population references, balanced 16 mean-of and 16 median-of
Unit tested: complete statistic assertion with exact finite population reference
How results combine: equal item mean within each form stratum, equal weight across the two form strata, then 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": -9.25
    },
    {
        "model": "o200k_base",
        "value": -9.25
    },
    {
        "model": "p50k_base",
        "value": -7.5
    }
]

Condition results

[
    {
        "id": "mean-of",
        "weight": 1,
        "share": 0.5,
        "value": -10,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "median-of",
        "weight": 1,
        "share": 0.5,
        "value": -5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 12adbc1c-18d8-4d42-9f44-1bad0b6d6eb1
Content 6ae4b8af604365ad032e697ec658e640bc4f1b5ee5ee4ae1b691c32095ac7106