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 · 0.75 tokens per declared item

First result · 2026-09-30 18:00 UTC

well-formed-under / admissible-under — did ‘valid’ mean the right shape, or allowed by the rules?

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
0.75 tokens per declared item
Reported interval: -0.640625 to 0.75.

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_base

Reader population not separately declared.

Conditions covered
Separate outcomes retained for all 2 declared conditions

well-formed-under, admissible-under

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
Disputed

Eligible replications disagree and this original does not hold a settlement majority.

Is this result within the cost allowance?
This headline is within the allowance. The reported difference is 0.75 tokens; the current declaration allows at most 4 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?
Disputed.

Eligible replications disagree and this original does not hold 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.

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
well-formed-under-0.75 Not recorded
admissible-under2.25 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 128 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 · wf-cost-001

English input
WeatherQuery-001 parses and satisfies WeatherQuery-schema-v2's structural rules.
Ainglish input
WeatherQuery-001 well-formed-under(WeatherQuery-schema-v2).
Condition
well-formed-under

Input 2 · ad-cost-001

English input
WeatherQuery-policy-v3 permits WeatherQuery-001 to proceed.
Ainglish input
WeatherQuery-001 admissible-under(WeatherQuery-policy-v3).
Condition
admissible-under

Input 3 · wf-cost-002

English input
ParcelRequest-002 parses and satisfies ParcelRequest-schema-v2's structural rules.
Ainglish input
ParcelRequest-002 well-formed-under(ParcelRequest-schema-v2).
Condition
well-formed-under

Input 4 · ad-cost-002

English input
ParcelRequest-policy-v3 permits ParcelRequest-002 to proceed.
Ainglish input
ParcelRequest-002 admissible-under(ParcelRequest-policy-v3).
Condition
admissible-under

Input 5 · wf-cost-003

English input
InvoiceRequest-003 parses and satisfies InvoiceRequest-schema-v2's structural rules.
Ainglish input
InvoiceRequest-003 well-formed-under(InvoiceRequest-schema-v2).
Condition
well-formed-under

Input 6 · ad-cost-003

English input
InvoiceRequest-policy-v3 permits InvoiceRequest-003 to proceed.
Ainglish input
InvoiceRequest-003 admissible-under(InvoiceRequest-policy-v3).
Condition
admissible-under

Recorded input digest: 71dea1a856f49c50ba16cd09854a4dcd73014b29af5bc465fc74ed77ba87e4ab

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 wording minus concise complete English: X parses and satisfies S's structural rules; P permits X to proceed. Both sides refer to the same immutable item, versioned rule and single stated gate; neither implies truth, safety, issuer authority or successful execution.
Tested population
128 authored messages: 64 structural-conformance statements and 64 policy-admission statements, eight per form in each of eight equally weighted domains (API, configuration, data import, ballots, grant applications, moderation, deployment, procurement). One fixed renderer per form; not a random natural-usage population.
Unit tested
One complete affirmative structural-conformance or policy-admission message with identical item and named rule references.
How results combine
Equal item means within each of two equally weighted predicate strata, then maximum tokenizer mean over the three declared encodings. Report both form strata and retain the complete form-by-tokenizer matrix; domain variation is diagnostic.

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": -0.640625
    },
    {
        "model": "o200k_base",
        "value": -0.21875
    },
    {
        "model": "p50k_base",
        "value": 0.75
    }
]

Condition results

[
    {
        "id": "well-formed-under",
        "weight": 1,
        "share": 0.5,
        "value": -0.75,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "admissible-under",
        "weight": 1,
        "share": 0.5,
        "value": 2.25,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 3c703c3c-20c6-4b0b-8e8e-5051ea673ff4
Content 13706318ad78f9e97a23e66157e52d4e44a153c27d60077127e70b8e53facbc5

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.