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.

Change the selected experimentsSearch 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

Compare the essentials

Read each question across both results. A matching description is not proof that the studies are scientifically comparable.

QuestionFirst resultSecond result
Which proposal?impact-recovered / cause-resolved — did ‘fixed’ mean the harm stopped, or the reason it broke was removed?2026-09-07 16:04 UTCimpact-recovered / cause-resolved — did ‘fixed’ mean the harm stopped, or the reason it broke was removed?2026-09-13 11:24 UTC
What was measured?token costHow does the wording change tokenizer units for the declared tokenizer population?token costHow does the wording change tokenizer units for the declared tokenizer population?
What was the result?-2 tokens per declared itemReported interval: -5 to -2Counts in current evidence decisions-2 tokens per declared itemReported interval: -4.5 to -2Counts in current evidence decisions
Compared with what?English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehensionEnglish comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension
Independently settled?Confirmed by eligible settlementEligible fresh-input replications currently give this original a settlement majority.Agrees with the named originalThis eligible row adds one agreement to the named original’s settlement tally.

Inspect first resultInspect second result

What differs in the declared methods?

These are literal recorded values, not a compatibility test. Matching declarations do not prove equivalent inputs or fair scoring. A missing structured field may be described elsewhere in the immutable specification.

What was measured · Same recorded value
First result
token_delta
Second result
token_delta
English comparison declarations · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Tested population · Same recorded value
First result
512 frozen incident complete pairs from eight authored domain frames; equal form weights; shared schemas excluded from both cost arms; repeated templates are not independent language populations
Second result
512 frozen incident complete pairs from eight authored domain frames; equal form weights; shared schemas excluded from both cost arms; repeated templates are not independent language populations
Unit tested · Same recorded value
First result
complete resolved claim sentence, with identical references and temporal spellings in both arms where applicable
Second result
complete resolved claim sentence, with identical references and temporal spellings in both arms where applicable
Named instruments (including order) · Same recorded value
First result
[
    "cl100k_base",
    "o200k_base",
    "p50k_base"
]
Second result
[
    "cl100k_base",
    "o200k_base",
    "p50k_base"
]
Reader exposure · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Exposure window · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
How results combine · Same recorded value
First result
{
    "reducer": "least_favourable",
    "rule": "mean complete-pair difference within each tokenizer, then maximum tokenizer mean; equal form strata retained separately"
}
Second result
{
    "reducer": "least_favourable",
    "rule": "mean complete-pair difference within each tokenizer, then maximum tokenizer mean; equal form strata retained separately"
}
Scoring declaration · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Conditions (including order) · Same recorded value
First result
[
    {
        "id": "impact-recovered",
        "weight": 1
    },
    {
        "id": "cause-resolved",
        "weight": 1
    }
]
Second result
[
    {
        "id": "impact-recovered",
        "weight": 1
    },
    {
        "id": "cause-resolved",
        "weight": 1
    }
]
First result: full recordtoken cost · -2 tokens per declared item

First result · 2026-09-07 16:04 UTC

impact-recovered / cause-resolved — did ‘fixed’ mean the harm stopped, or the reason it broke was removed?

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
-2 tokens per declared item
Reported interval: -5 to -2.

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

impact-recovered, cause-resolved

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?
This headline is within the allowance. The reported difference is -2 tokens; the current declaration allows at most 2 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?
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
impact-recovered-3 Not recorded
cause-resolved-1 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 512 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 · i-000-impact

English input
In I000, check C000 found its named impact absent at 06:00Z.
Ainglish input
I000 impact-recovered(C000@06:00Z).
Condition
impact-recovered

Input 2 · i-000-cause

English input
In I000, K000 was removed and the post-change test T000 passed.
Ainglish input
I000 cause-resolved(K000, checked-by=T000).
Condition
cause-resolved

Input 3 · i-001-impact

English input
In I001, check C001 found its named impact absent at 06:15Z.
Ainglish input
I001 impact-recovered(C001@06:15Z).
Condition
impact-recovered

Input 4 · i-001-cause

English input
In I001, K001 was removed and the post-change test T001 passed.
Ainglish input
I001 cause-resolved(K001, checked-by=T001).
Condition
cause-resolved

Input 5 · i-002-impact

English input
In I002, check C002 found its named impact absent at 06:30Z.
Ainglish input
I002 impact-recovered(C002@06:30Z).
Condition
impact-recovered

Input 6 · i-002-cause

English input
In I002, K002 was removed and the post-change test T002 passed.
Ainglish input
I002 cause-resolved(K002, checked-by=T002).
Condition
cause-resolved

Recorded input digest: d33f5b767e29b9f836969ef6772efb6eca481e02ce5e46bbdf704453d4887f06

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 surface versus concise semantically complete careful English; omitted inferences are not positive claims in either arm
Tested population
512 frozen incident complete pairs from eight authored domain frames; equal form weights; shared schemas excluded from both cost arms; repeated templates are not independent language populations
Unit tested
complete resolved claim sentence, with identical references and temporal spellings in both arms where applicable
How results combine
mean complete-pair difference within each tokenizer, then maximum tokenizer mean; equal form strata retained separately

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": -5
    },
    {
        "model": "o200k_base",
        "value": -5
    },
    {
        "model": "p50k_base",
        "value": -2
    }
]

Condition results

[
    {
        "id": "impact-recovered",
        "weight": 1,
        "share": 0.5,
        "value": -3,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "cause-resolved",
        "weight": 1,
        "share": 0.5,
        "value": -1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt fe45a137-24f7-488f-a11a-6d9cd0edcde1
Content d8ac746b3b44e5c3ac6135a9499d0e8fb243f091d80e1960e7bdae7ec2d9b5f5

Second result: full recordtoken cost · -2 tokens per declared item

Second result · 2026-09-13 11:24 UTC

impact-recovered / cause-resolved — did ‘fixed’ mean the harm stopped, or the reason it broke was removed?

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
-2 tokens per declared item
Reported interval: -4.5 to -2.

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

impact-recovered, cause-resolved

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 -2 tokens; the current declaration allows at most 2 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 -2 tokens; the named original reported -2.

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.

  • 0 of 512 English inputs reuse text from either side of the original.
  • 0 of 512 Ainglish inputs reuse text from either side of the original.

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 identityd8ac746b3b44e5c3ac6135a9499d0e8fb243f091d80e1960e7bdae7ec2d9b5f5

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
impact-recovered-3 Not recorded
cause-resolved-1 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 512 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 · sat-edge-routing-00-impact

English input
In J300, check Q300 found its named impact absent at 06:00Z.
Ainglish input
J300 impact-recovered(Q300@06:00Z).
Condition
impact-recovered

Input 2 · sat-edge-routing-00-cause

English input
In J300, F300 was removed and the post-change test V300 passed.
Ainglish input
J300 cause-resolved(F300, checked-by=V300).
Condition
cause-resolved

Input 3 · sat-edge-routing-01-impact

English input
In J301, check Q301 found its named impact absent at 06:15Z.
Ainglish input
J301 impact-recovered(Q301@06:15Z).
Condition
impact-recovered

Input 4 · sat-edge-routing-01-cause

English input
In J301, F301 was removed and the post-change test V301 passed.
Ainglish input
J301 cause-resolved(F301, checked-by=V301).
Condition
cause-resolved

Input 5 · sat-edge-routing-02-impact

English input
In J302, check Q302 found its named impact absent at 06:30Z.
Ainglish input
J302 impact-recovered(Q302@06:30Z).
Condition
impact-recovered

Input 6 · sat-edge-routing-02-cause

English input
In J302, F302 was removed and the post-change test V302 passed.
Ainglish input
J302 cause-resolved(F302, checked-by=V302).
Condition
cause-resolved

Recorded input digest: 95bc999b6cf4c9837ac10a0e67a8b82f5aeb79be2ee1d2d8d0f024e1c5dad3c5

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 surface versus concise semantically complete careful English; omitted inferences are not positive claims in either arm
Tested population
512 frozen incident complete pairs from eight authored domain frames; equal form weights; shared schemas excluded from both cost arms; repeated templates are not independent language populations
Unit tested
complete resolved claim sentence, with identical references and temporal spellings in both arms where applicable
How results combine
mean complete-pair difference within each tokenizer, then maximum tokenizer mean; equal form strata retained separately

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": -4.5
    },
    {
        "model": "o200k_base",
        "value": -4.5
    },
    {
        "model": "p50k_base",
        "value": -2
    }
]

Condition results

[
    {
        "id": "impact-recovered",
        "weight": 1,
        "share": 0.5,
        "value": -3,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "cause-resolved",
        "weight": 1,
        "share": 0.5,
        "value": -1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt c1430c17-7513-4b40-a36c-c99acad98e93
Content f18d62e3916baa3e439223dae6748deb6b11be792f12f6577c89a45edb4676f1

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.