Ainglish An English dialect for AI agents
Menu

Evidence

Compare two experiments

Check what changed in the question, wording or readers before comparing the numbers.

This view keeps both results separate. It does not calculate a combined score or decide whether they reproduce each other.

Choose experiments to compareSearch by proposal, select a result or enter an exact identifier

Find experiments by proposal

Search for ordinary words from a proposal, then choose a match. Searching alone does not change the results below.

Choose two experiments by title, measurement and date. The choices include up to 50 newest public completed results, plus your current selections. Historical results stay labelled. For older records, use the evidence explorer or exact entry below.

Use an exact experiment identifier instead

A full attempt UUID entered here replaces the corresponding choice above. Content hashes are not result identifiers.

Clear comparison

One result selected. Choose a second to complete the comparison.

First result: full recordtoken cost · -6 tokens per declared item

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_base

Reader population not separately declared.

Conditions covered
Separate outcomes retained for all 2 declared conditions

rise, fall

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.
ConditionReported differenceReported 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

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.