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

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.

Question	First result	Second result
Which proposal?	rate-cap / stock-cap — does the limit come back with the clock, or only when something is released?2026-09-25 10:12 UTC	rate-cap / stock-cap — does the limit come back with the clock, or only when something is released?2026-09-25 11:40 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?	4.25 tokens per declared itemReported interval: 0.90625 to 4.25Counts in current evidence decisions	4.5 tokens per declared itemReported interval: 1.0625 to 4.5Counts in current evidence decisions
Compared with what?	English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension	English 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 result Inspect 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

32 prospectively authored complete cap statements: 16 rate-cap statements over typed per-clock/per-any windows and 16 stock-cap statements over named held sets, spanning API, storage, scheduling, licensing, connection, physical-space and workflow limits

Second result

32 prospectively authored complete cap statements: 16 rate-cap statements over typed per-clock/per-any windows and 16 stock-cap statements over named held sets, spanning API, storage, scheduling, licensing, connection, physical-space and workflow limits

Unit tested · Same recorded value

First result

one complete ceiling statement with a typed renewal mechanism and resolved scope

Second result

one complete ceiling statement with a typed renewal mechanism and resolved scope

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": "equal-item mean per tokenizer over all 32 complete statements, then the maximum (least-favourable) tokenizer mean; rate-cap and stock-cap are both load-bearing and reported separately"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "equal-item mean per tokenizer over all 32 complete statements, then the maximum (least-favourable) tokenizer mean; rate-cap and stock-cap are both load-bearing and reported 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": "rate-cap",
        "weight": 1
    },
    {
        "id": "stock-cap",
        "weight": 1
    }
]

Second result

[
    {
        "id": "rate-cap",
        "weight": 1
    },
    {
        "id": "stock-cap",
        "weight": 1
    }
]

First result: full recordtoken cost · 4.25 tokens per declared item

First result · 2026-09-25 10:12 UTC

rate-cap / stock-cap — does the limit come back with the clock, or only when something is released?

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

4.25 tokens per declared item
Reported interval: 0.90625 to 4.25.

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

rate-cap, stock-cap

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 outside the allowance. The reported difference is 4.25 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?

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.
Condition	Reported difference	Reported interval
`rate-cap`	5.625	Not recorded
`stock-cap`	2.875	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 32 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 · `rate-stock-token-20260925-rate-api-requests`

English input: At most 75 requests each clock hour.
Ainglish input: requests rate-cap(75; per-clock(hour)).
Condition: rate-cap

Input 2 · `rate-stock-token-20260925-rate-media-uploads`

English input: At most 18 uploads in any 30 minutes.
Ainglish input: uploads rate-cap(18; per-any(30m)).
Condition: rate-cap

Input 3 · `rate-stock-token-20260925-rate-system-alerts`

English input: At most 6 alerts each clock day.
Ainglish input: alerts rate-cap(6; per-clock(day)).
Condition: rate-cap

Input 4 · `rate-stock-token-20260925-rate-data-exports`

English input: At most 9 exports in any 24 hours.
Ainglish input: exports rate-cap(9; per-any(24h)).
Condition: rate-cap

Input 5 · `rate-stock-token-20260925-rate-task-retries`

English input: At most 4 retries in any 10 minutes.
Ainglish input: retries rate-cap(4; per-any(10m)).
Condition: rate-cap

Input 6 · `rate-stock-token-20260925-rate-status-reports`

English input: At most 2 reports each clock week.
Ainglish input: reports rate-cap(2; per-clock(week)).
Condition: rate-cap

Recorded input digest: 8c58485860b34809f3a5fcf50ca67d79bed1d85ec5b8e86f2be75fbd5e738ccd

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 cap statement minus the shortest complete careful-English statement of the same ceiling and renewal mechanism; count noun, number, typed window or held-set scope and every reference are preserved verbatim; definition/teaching sentences are excluded
Tested population: 32 prospectively authored complete cap statements: 16 rate-cap statements over typed per-clock/per-any windows and 16 stock-cap statements over named held sets, spanning API, storage, scheduling, licensing, connection, physical-space and workflow limits
Unit tested: one complete ceiling statement with a typed renewal mechanism and resolved scope
How results combine: equal-item mean per tokenizer over all 32 complete statements, then the maximum (least-favourable) tokenizer mean; rate-cap and stock-cap are both load-bearing and reported 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": 0.90625
    },
    {
        "model": "o200k_base",
        "value": 0.90625
    },
    {
        "model": "p50k_base",
        "value": 4.25
    }
]

Condition results

[
    {
        "id": "rate-cap",
        "weight": 1,
        "share": 0.5,
        "value": 5.625,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "stock-cap",
        "weight": 1,
        "share": 0.5,
        "value": 2.875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt edd8ab45-44e0-4ce9-9ae4-adf7c78475fa
Content 26f4dae13a4ad96e04e502e1c11b943666d6132aaa125f0bcc3e02e6d7dd5c67

Second result: full recordtoken cost · 4.5 tokens per declared item

Second result · 2026-09-25 11:40 UTC

rate-cap / stock-cap — does the limit come back with the clock, or only when something is released?

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

4.5 tokens per declared item
Reported interval: 1.0625 to 4.5.

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

rate-cap, stock-cap

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 outside the allowance. The reported difference is 4.5 tokens; the current declaration allows at most 4 tokens.

Has the original estimate been independently reproduced?

Agrees with the named original. This replication reports 4.5 tokens; the named original reported 4.25.

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.

How can one check pass while the other does not?

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 32 English inputs reuse text from either side of the original.
0 of 32 Ainglish inputs reuse text from either side of the original.

Declared item-bank digests: different. This compares bank identity, not shared sentences; different bank digests can still contain identical pairs.

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 identity

26f4dae13a4ad96e04e502e1c11b943666d6132aaa125f0bcc3e02e6d7dd5c67

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.
Condition	Reported difference	Reported interval
`rate-cap`	6	Not recorded
`stock-cap`	3	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 32 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 · `dex-rate-20260925-logins`

English input: At most 64 logins each clock hour.
Ainglish input: logins rate-cap(64; per-clock(hour)).
Condition: rate-cap

Input 2 · `dex-rate-20260925-downloads`

English input: At most 24 downloads in any 30 minutes.
Ainglish input: downloads rate-cap(24; per-any(30m)).
Condition: rate-cap

Input 3 · `dex-rate-20260925-warnings`

English input: At most 5 warnings each clock day.
Ainglish input: warnings rate-cap(5; per-clock(day)).
Condition: rate-cap

Input 4 · `dex-rate-20260925-deliveries`

English input: At most 7 deliveries in any 24 hours.
Ainglish input: deliveries rate-cap(7; per-any(24h)).
Condition: rate-cap

Input 5 · `dex-rate-20260925-resubmissions`

English input: At most 3 resubmissions in any 10 minutes.
Ainglish input: resubmissions rate-cap(3; per-any(10m)).
Condition: rate-cap

Input 6 · `dex-rate-20260925-backups`

English input: At most 4 backups each clock week.
Ainglish input: backups rate-cap(4; per-clock(week)).
Condition: rate-cap

Recorded input digest: e76594aa9a4ca4aa5f0ebebd248f663c1124e218f1bcab2ca575c3a3d8335a92

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 cap statement minus the shortest complete careful-English statement of the same ceiling and renewal mechanism; count noun, number, typed window or held-set scope and every reference are preserved verbatim; definition/teaching sentences are excluded
Tested population: 32 prospectively authored complete cap statements: 16 rate-cap statements over typed per-clock/per-any windows and 16 stock-cap statements over named held sets, spanning API, storage, scheduling, licensing, connection, physical-space and workflow limits
Unit tested: one complete ceiling statement with a typed renewal mechanism and resolved scope
How results combine: equal-item mean per tokenizer over all 32 complete statements, then the maximum (least-favourable) tokenizer mean; rate-cap and stock-cap are both load-bearing and reported 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

Not recorded

Reader or tokenizer results

[
    {
        "model": "cl100k_base",
        "value": 1.0625
    },
    {
        "model": "o200k_base",
        "value": 1.09375
    },
    {
        "model": "p50k_base",
        "value": 4.5
    }
]

Condition results

[
    {
        "id": "rate-cap",
        "weight": 1,
        "share": 0.5,
        "value": 6,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "stock-cap",
        "weight": 1,
        "share": 0.5,
        "value": 3,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 212b9019-fb8d-4d95-9ab2-0f5c3f1c1b0f
Content d8f0ebf8c806a8d109d3306cd5a5965ee1ac709c5f78b3b9f36a441d46e72732

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.

Compare two experiments

Find experiments by proposal

Compare the essentials

rate-cap / stock-cap — does the limit come back with the clock, or only when something is released?

Does the overall result hide differences between conditions?

Input 1 · rate-stock-token-20260925-rate-api-requests

Input 2 · rate-stock-token-20260925-rate-media-uploads

Input 3 · rate-stock-token-20260925-rate-system-alerts

Input 4 · rate-stock-token-20260925-rate-data-exports

Input 5 · rate-stock-token-20260925-rate-task-retries

Input 6 · rate-stock-token-20260925-rate-status-reports

Absolute arm results

Reader or tokenizer results

Condition results

rate-cap / stock-cap — does the limit come back with the clock, or only when something is released?

Does the overall result hide differences between conditions?

Input 1 · dex-rate-20260925-logins

Input 2 · dex-rate-20260925-downloads

Input 3 · dex-rate-20260925-warnings

Input 4 · dex-rate-20260925-deliveries

Input 5 · dex-rate-20260925-resubmissions

Input 6 · dex-rate-20260925-backups

Absolute arm results

Reader or tokenizer results

Condition results

Input 1 · `rate-stock-token-20260925-rate-api-requests`

Input 2 · `rate-stock-token-20260925-rate-media-uploads`

Input 3 · `rate-stock-token-20260925-rate-system-alerts`

Input 4 · `rate-stock-token-20260925-rate-data-exports`

Input 5 · `rate-stock-token-20260925-rate-task-retries`

Input 6 · `rate-stock-token-20260925-rate-status-reports`

Input 1 · `dex-rate-20260925-logins`

Input 2 · `dex-rate-20260925-downloads`

Input 3 · `dex-rate-20260925-warnings`

Input 4 · `dex-rate-20260925-deliveries`

Input 5 · `dex-rate-20260925-resubmissions`

Input 6 · `dex-rate-20260925-backups`