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?finish-started / interrupt-started — when you say stop, should running work finish?2026-09-14 21:19 UTCfinish-started / interrupt-started — when you say stop, should running work finish?2026-09-19 14:06 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?-5.5 tokens per declared itemReported interval: -5.5 to -5.5Counts in current evidence decisions-5.5 tokens per declared itemReported interval: -5.5 to -5.5Counts 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 · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Unit tested · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
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 · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
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": "finish-started",
        "weight": 1
    },
    {
        "id": "interrupt-started",
        "weight": 1
    }
]
Second result
[
    {
        "id": "finish-started",
        "weight": 1
    },
    {
        "id": "interrupt-started",
        "weight": 1
    }
]
First result: full recordtoken cost · -5.5 tokens per declared item

First result · 2026-09-14 21:19 UTC

finish-started / interrupt-started — when you say stop, should running work finish?

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
-5.5 tokens per declared item
Reported interval: -5.5 to -5.5.

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

finish-started, interrupt-started

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
finish-started-6 Not recorded
interrupt-started-5 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

English input
In downloads D1-D4, start no new tasks; let running tasks finish.
Ainglish input
Stop downloads D1-D4, finish-started.
Condition
finish-started

Input 2

English input
In downloads D1-D4, start no new tasks; interrupt running tasks.
Ainglish input
Stop downloads D1-D4, interrupt-started.
Condition
interrupt-started

Input 3

English input
In downloads D5-D8, start no new tasks; let running tasks finish.
Ainglish input
Stop downloads D5-D8, finish-started.
Condition
finish-started

Input 4

English input
In downloads D5-D8, start no new tasks; interrupt running tasks.
Ainglish input
Stop downloads D5-D8, interrupt-started.
Condition
interrupt-started

Input 5

English input
In downloads A1-A4, start no new tasks; let running tasks finish.
Ainglish input
Stop downloads A1-A4, finish-started.
Condition
finish-started

Input 6

English input
In downloads A1-A4, start no new tasks; interrupt running tasks.
Ainglish input
Stop downloads A1-A4, interrupt-started.
Condition
interrupt-started

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

No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.

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": -5.5
    },
    {
        "model": "o200k_base",
        "value": -5.5
    },
    {
        "model": "p50k_base",
        "value": -5.5
    }
]

Condition results

[
    {
        "id": "finish-started",
        "weight": 1,
        "share": 0.5,
        "value": -6,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "interrupt-started",
        "weight": 1,
        "share": 0.5,
        "value": -5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 23a64d1e-1b63-43eb-aef9-d77537af8cbf
Content f3d0ae2b2ee22cdac21ba43210113bb171822e934c5ffbb48341d5581c6a8348

Second result: full recordtoken cost · -5.5 tokens per declared item

Second result · 2026-09-19 14:06 UTC

finish-started / interrupt-started — when you say stop, should running work finish?

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
-5.5 tokens per declared item
Reported interval: -5.5 to -5.5.

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

finish-started, interrupt-started

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?
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?
Agrees with the named original. This replication reports -5.5 tokens; the named original reported -5.5.

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 64 English inputs reuse text from either side of the original.
  • 0 of 64 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 identityf3d0ae2b2ee22cdac21ba43210113bb171822e934c5ffbb48341d5581c6a8348

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
finish-started-6 Not recorded
interrupt-started-5 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

English input
In downloads Aurora11-Aurora14, start no new tasks; let running tasks finish.
Ainglish input
Stop downloads Aurora11-Aurora14, finish-started.
Condition
finish-started

Input 2

English input
In downloads Aurora11-Aurora14, start no new tasks; interrupt running tasks.
Ainglish input
Stop downloads Aurora11-Aurora14, interrupt-started.
Condition
interrupt-started

Input 3

English input
In downloads Birch11-Birch14, start no new tasks; let running tasks finish.
Ainglish input
Stop downloads Birch11-Birch14, finish-started.
Condition
finish-started

Input 4

English input
In downloads Birch11-Birch14, start no new tasks; interrupt running tasks.
Ainglish input
Stop downloads Birch11-Birch14, interrupt-started.
Condition
interrupt-started

Input 5

English input
In downloads Cedar11-Cedar14, start no new tasks; let running tasks finish.
Ainglish input
Stop downloads Cedar11-Cedar14, finish-started.
Condition
finish-started

Input 6

English input
In downloads Cedar11-Cedar14, start no new tasks; interrupt running tasks.
Ainglish input
Stop downloads Cedar11-Cedar14, interrupt-started.
Condition
interrupt-started

Recorded input digest: 45335c20d0db8464a579d3d2ea68fdf8c366f20b4749f27d3d19318a976c1221

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

No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.

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": -5.5
    },
    {
        "model": "o200k_base",
        "value": -5.5
    },
    {
        "model": "p50k_base",
        "value": -5.5
    }
]

Condition results

[
    {
        "id": "finish-started",
        "weight": 1,
        "share": 0.5,
        "value": -6,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "interrupt-started",
        "weight": 1,
        "share": 0.5,
        "value": -5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 30627a5e-ac98-48c2-a3c4-1768f9436767
Content 1fcbe642fe31168a4594b6a20cbebf0c6fd7d9a5e5a77552e32a5a247e286dbd

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.