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 · -6.9583333333333 tokens per declared item

First result · 2026-09-28 11:17 UTC

tested-against(<revision>) — pin a test claim to the exact revision it ran on

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
-6.9583333333333 tokens per declared item
Reported interval: -7.9583333333333 to -6.9583333333333.

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 1 declared conditions

tested-against

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
tested-against-6.9583333333333 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 · ledger-suite

English input
The ledger reconciliation suite passes as of commit 9ac41e7; it may not hold on other revisions.
Ainglish input
The ledger reconciliation suite passes tested-against(9ac41e7).
Condition
tested-against

Input 2 · schema-upgrade

English input
The schema upgrade preserves every account row as of version 6.4.2; it may not hold on other revisions.
Ainglish input
The schema upgrade preserves every account row tested-against(6.4.2).
Condition
tested-against

Input 3 · tls-handshake

English input
The mutual TLS handshake succeeds as of build 2741; it may not hold on other revisions.
Ainglish input
The mutual TLS handshake succeeds tested-against(2741).
Condition
tested-against

Input 4 · fixture-validator

English input
The fixture validator rejects malformed records as of hash 71bd09f; it may not hold on other revisions.
Ainglish input
The fixture validator rejects malformed records tested-against(71bd09f).
Condition
tested-against

Input 5 · resolver-order

English input
The dependency resolver returns a stable order as of tag v3.11.0; it may not hold on other revisions.
Ainglish input
The dependency resolver returns a stable order tested-against(v3.11.0).
Condition
tested-against

Input 6 · heap-profile

English input
The overnight heap profile stays flat as of commit 2de88b4; it may not hold on other revisions.
Ainglish input
The overnight heap profile stays flat tested-against(2de88b4).
Condition
tested-against

Recorded input digest: 885141e1fc389228b4efa97064c02f42e2a52a1e8f9c6164795e8e73e0b7d7c5

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
tested-against(<revision>) versus the shortest natural careful-English statement carrying the same claim, named revision and explicit warning that it may not hold on other revisions
Tested population
24 frozen complete revision-pinned test claims across 24 fresh operational domains
Unit tested
one complete revision-pinned test claim
How results combine
equal-pair mean per tokenizer, then the 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": -7.95833333333333303727386009995825588703155517578125
    },
    {
        "model": "o200k_base",
        "value": -6.95833333333333303727386009995825588703155517578125
    },
    {
        "model": "p50k_base",
        "value": -6.95833333333333303727386009995825588703155517578125
    }
]

Condition results

[
    {
        "id": "tested-against",
        "weight": 1,
        "share": 1,
        "value": -6.95833333333333303727386009995825588703155517578125,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 9d211a25-8968-4a25-b34a-45b62494c1b3
Content 2c12114f1f7bcd9e0ce98acb06e45c44811387ae449e922393a2d5e03a4510fd

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.