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?	simulate-only(<world-ref>): — make consequences inspectable without making them real2026-09-02 16:52 UTC	simulate-only(<world-ref>): — make consequences inspectable without making them real2026-09-02 22:28 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?	-9 tokens per declared itemReported interval: -12.917 to -9Counts in current evidence decisions	-6.3125 tokens per declared itemReported interval: -10.8125 to -6.3125Not yet counting in 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.	Incommensurable pending repairA comparison key does not match, so the row cannot presently vote on settlement.

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 · Only recorded on one side

First result

Not recorded in this structured field

Second result

16 frozen disjoint simulate-only pairs, Spark replication

Unit tested · Only recorded on one side

First result

Not recorded in this structured field

Second result

complete message

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 · Only recorded on one side

First result

Not recorded in this structured field

Second result

{
    "reducer": "least_favourable",
    "rule": "equal item mean, then maximum tokenizer mean"
}

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) · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

First result: full recordtoken cost · -9 tokens per declared item

First result · 2026-09-02 16:52 UTC

simulate-only(<world-ref>): — make consequences inspectable without making them real

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: -9 tokens per declared item
Reported interval: -12.917 to -9.
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: No condition-by-condition settlement contract recorded
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 -9 tokens; the current declaration allows at most 0 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.

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 12 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: Using only isolated production snapshot revision 42, simulate deleting the inactive accounts and report the simulated outcome; do not delete live accounts.
Ainglish input: simulate-only(prod-snapshot@r42): delete accounts inactive for 90 days.

Input 2

English input: In isolated mail fixture version 3, simulate sending the renewal notices to overdue customers and report the simulated outcome; send no real message.
Ainglish input: simulate-only(mail-fixture@v3): send renewal notices to overdue customers.

Input 3

English input: In the isolated authorization copy identified by sha256-7f3a, simulate revoking contractor access and report the simulated outcome; alter no live permission.
Ainglish input: simulate-only(auth-copy@sha256-7f3a): revoke contractor access.

Input 4

English input: Using only the isolated staging database snapshot, simulate running the schema migration and report the simulated outcome; do not migrate the live database.
Ainglish input: simulate-only(staging-snapshot): run the schema migration.

Input 5

English input: In the isolated payment sandbox, simulate charging the overdue invoices and report the simulated outcome; send no real charge.
Ainglish input: simulate-only(payment-sandbox): charge overdue invoices.

Input 6

English input: Using only the isolated deployment twin, simulate rolling out the new service version and report the simulated outcome; do not deploy to the live cluster.
Ainglish input: simulate-only(deploy-twin): roll out the new service version.

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": -12.9169999999999998152588887023739516735076904296875
    },
    {
        "model": "o200k_base",
        "value": -12.9169999999999998152588887023739516735076904296875
    },
    {
        "model": "p50k_base",
        "value": -9
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt ef156503-e669-4ca0-8d46-93f85d7137b4
Content 05cd46d9b0032f7fd3253669e215a3990e282252ca3c2a9da190d47a92f017e5

Second result: full recordtoken cost · -6.3125 tokens per declared item

Second result · 2026-09-02 22:28 UTC

simulate-only(<world-ref>): — make consequences inspectable without making them real

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: -6.3125 tokens per declared item
Reported interval: -10.8125 to -6.3125.
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: No condition-by-condition settlement contract recorded
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: Incommensurable pending repair
A comparison key does not match, so the row cannot presently vote on settlement.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is -6.3125 tokens; the current declaration allows at most 0 tokens.

Has the original estimate been independently reproduced?

Incommensurable pending repair. This replication reports -6.3125 tokens; the named original reported -9.

A comparison key does not match, so the row cannot presently vote on settlement.

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

How much input text was reused?

100.0% of complete English–Ainglish pairs are fresh.

Separate-arm overlap is unavailable or has not been computed. This does not mean zero reuse.

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

05cd46d9b0032f7fd3253669e215a3990e282252ca3c2a9da190d47a92f017e5

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 16 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 isolated checkout sandbox 2026-09-02, simulate voiding the expired coupons and report the simulated outcome; void no live coupon.
Ainglish input: simulate-only(checkout-sandbox@2026-09-02): void expired coupons.

Input 2

English input: Using only isolated ledger clone w11, simulate reversing the duplicate journal postings and report the simulated outcome; alter no live ledger.
Ainglish input: simulate-only(ledger-clone@w11): reverse duplicate journal postings.

Input 3

English input: In isolated edge replica h3, simulate evicting the stale edge objects and report the simulated outcome; evict no live object.
Ainglish input: simulate-only(edge-replica@h3): evict stale edge objects.

Input 4

English input: Using only isolated vault mirror k9, simulate rotating the service secrets and report the simulated outcome; rotate no live secret.
Ainglish input: simulate-only(vault-mirror@k9): rotate service secrets.

Input 5

English input: In isolated queue shadow s4, simulate draining the poison messages and report the simulated outcome; drop no live message.
Ainglish input: simulate-only(queue-shadow@s4): drain poison messages.

Input 6

English input: Using only isolated search index copy t6, simulate rebuilding the product index and report the simulated outcome; touch no live index.
Ainglish input: simulate-only(search-index-copy@t6): rebuild the product index.

Recorded input digest: 4179c60bf6d5ad109da8718a542fa38211df6b279c0af3c12ba0c8e7f3962943

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: Ainglish simulate-only form versus complete careful English
Tested population: 16 frozen disjoint simulate-only pairs, Spark replication
Unit tested: complete message
How results combine: equal item mean, then 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

Not recorded

Reader or tokenizer results

[
    {
        "model": "cl100k_base",
        "value": -10.8125
    },
    {
        "model": "o200k_base",
        "value": -10.625
    },
    {
        "model": "p50k_base",
        "value": -6.3125
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt fb3b0184-35f6-49a9-b41c-128a7f5ad1ea
Content 2050ed1084b70fda9bba78e27085ca938400b844d22d3afc5023ffd965dba3cb

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.