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 · 1.5 tokens per declared item

First result · 2026-10-01 14:11 UTC

twice-weekly / every-two-weeks — split “biweekly” into its two incompatible schedules

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
1.5 tokens per declared item
Reported interval: 0.5 to 1.5.

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

twice-weekly, every-two-weeks

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?
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?
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.

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
twice-weekly0 Not recorded
every-two-weeks3 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 64 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 · audits-1-twice-weekly

English input
Schedule the permission inventory twice per week. Each week runs from Monday 00:00Z to the next Monday 00:00Z.
Ainglish input
Schedule the permission inventory twice-weekly. Each week runs from Monday 00:00Z to the next Monday 00:00Z.
Condition
twice-weekly

Input 2 · audits-1-every-two-weeks

English input
Schedule the permission inventory every two weeks. The recurrence anchor is 2026-10-05T09:00Z.
Ainglish input
Schedule the permission inventory every-two-weeks. The recurrence anchor is 2026-10-05T09:00Z.
Condition
every-two-weeks

Input 3 · audits-2-twice-weekly

English input
Schedule the dependency ledger twice per week. Each week runs from Monday 00:00Z to the next Monday 00:00Z.
Ainglish input
Schedule the dependency ledger twice-weekly. Each week runs from Monday 00:00Z to the next Monday 00:00Z.
Condition
twice-weekly

Input 4 · audits-2-every-two-weeks

English input
Schedule the dependency ledger every two weeks. The recurrence anchor is 2026-10-12T11:00Z.
Ainglish input
Schedule the dependency ledger every-two-weeks. The recurrence anchor is 2026-10-12T11:00Z.
Condition
every-two-weeks

Input 5 · audits-3-twice-weekly

English input
Schedule the change archive twice per week. Each week runs from Monday 00:00Z to the next Monday 00:00Z.
Ainglish input
Schedule the change archive twice-weekly. Each week runs from Monday 00:00Z to the next Monday 00:00Z.
Condition
twice-weekly

Input 6 · audits-3-every-two-weeks

English input
Schedule the change archive every two weeks. The recurrence anchor is 2026-10-19T13:00Z.
Ainglish input
Schedule the change archive every-two-weeks. The recurrence anchor is 2026-10-19T13:00Z.
Condition
every-two-weeks

Recorded input digest: 7fc014b189147a34185964b344bad5c78ec05bc0878f8ca5cb7a776c63e7c5cd

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
Registered twice-weekly/every-two-weeks minus concise complete careful English twice per week/every two weeks. No bare biweekly arm and no padded explanatory comparator.
Tested population
64 prospectively authored scheduling instructions: 32 per form, four per form in each of eight domains (audits, reports, backups, reviews, polls, maintenance, meetings, jobs). Fixed imperative renderer and reference schedule conventions; template-expanded comparison, not a random natural-use corpus.
Unit tested
One complete scheduling instruction with the same action and explicit schedule-week definition or recurrence anchor in both arms.
How results combine
Equal item mean in each equally weighted form stratum, then maximum tokenizer mean. Report every form/tokenizer mean separately; pooled value alone does not establish both forms are economical.

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": 0.5
    },
    {
        "model": "o200k_base",
        "value": 0.5
    },
    {
        "model": "p50k_base",
        "value": 1.5
    }
]

Condition results

[
    {
        "id": "twice-weekly",
        "weight": 1,
        "share": 0.5,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "every-two-weeks",
        "weight": 1,
        "share": 0.5,
        "value": 3,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 7223b8f4-a80e-49b9-a6bc-2618bdd789fd
Content ef0c432e6706629fe295d46d31955b59f07ad5e7a62964e460fef599886947c4

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.