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.

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

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

cl100k_base/o200k_base/p50k_base

Second result

cl100k_base/o200k_base/p50k_base

Unit tested · Same recorded value

First result

pair

Second result

pair

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": "maximum tokenizer mean"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "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 · 2026-09-07 18:15 UTC

sanction-allow / sanction-penalize — did the authority permit it or punish it?

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: 5.25 tokens per declared item
Reported interval: 2.75 to 5.25.
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: 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 outside the allowance. The reported difference is 5.25 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.

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 8 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: The financial regulator formally permitted bank 7 to acquire branch 2.
Ainglish input: sanction-allow(financial-regulator): bank-7 may acquire branch-2.

Input 2

English input: The financial regulator formally imposed a restrictive penalty on bank 7: transfers are suspended for 30 days.
Ainglish input: sanction-penalize(financial-regulator): bank-7, transfers suspended for 30 days.

Input 3

English input: The data authority formally permitted the startup to process user data.
Ainglish input: sanction-allow(data-authority): startup-3 may process user-data.

Input 4

English input: The data authority formally imposed a restrictive penalty on the startup: data collection suspended for 60 days.
Ainglish input: sanction-penalize(data-authority): startup-3, collection suspended for 60 days.

Input 5

English input: The aviation board formally permitted the airline to operate the new route.
Ainglish input: sanction-allow(aviation-board): airline-4 may operate route-7.

Input 6

English input: The aviation board formally imposed a restrictive penalty on the airline: route suspended for 90 days.
Ainglish input: sanction-penalize(aviation-board): airline-4, route suspended for 90 days.

Recorded input digest: f7d6805dde676ea8c6f932e232b61de5f754b2504506c3631afa191c29e2e399

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: token_delta
Tested population: cl100k_base/o200k_base/p50k_base
Unit tested: pair
How results combine: 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, 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": 2.75
    },
    {
        "model": "o200k_base",
        "value": 3.25
    },
    {
        "model": "p50k_base",
        "value": 5.25
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 51255879-e43b-4102-9f2d-06ab49a6ba33
Content c0fed3e5fd9316100def0cfec4e31d2e58ff630d995f2972424141d276821a08

Second result · 2026-09-08 15:49 UTC

sanction-allow / sanction-penalize — did the authority permit it or punish it?

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: 5.25 tokens per declared item
Reported interval: 3.25 to 5.25.
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: 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: 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 5.25 tokens; the current declaration allows at most 4 tokens.

Has the original estimate been independently reproduced?

Agrees with the named original. This replication reports 5.25 tokens; the named original reported 5.25.

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

Declared target content identity

c0fed3e5fd9316100def0cfec4e31d2e58ff630d995f2972424141d276821a08

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 8 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: The food-standards inspector formally permitted the bakery to resume production after the audit.
Ainglish input: sanction-allow(food-standards-inspector): the bakery may resume production after the audit.

Input 2

English input: The energy commission formally approved the utility beginning the battery-grid pilot in May.
Ainglish input: sanction-allow(energy-commission): the utility may begin the battery-grid pilot in May.

Input 3

English input: The heritage council formally permitted the museum to move the sculpture to the annex.
Ainglish input: sanction-allow(heritage-council): the museum may move the sculpture to the annex.

Input 4

English input: The space agency formally approved the company launching the cubesat in November.
Ainglish input: sanction-allow(space-agency): the company may launch the cubesat in November.

Input 5

English input: The tax authority formally imposed a fine of 45000 pounds on the retailer for undeclared sales.
Ainglish input: sanction-penalize(tax-authority): the retailer, fined 45000 pounds for undeclared sales.

Input 6

English input: The gaming commission formally imposed a penalty on the casino by suspending its online licence for 21 days.
Ainglish input: sanction-penalize(gaming-commission): the casino, online licence suspended for 21 days.

Recorded input digest: 3ea451b6a173a80c9530c0269cf65ffac43da93c4e82f7e4a001b1e3245a213a

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: token_delta
Tested population: cl100k_base/o200k_base/p50k_base
Unit tested: pair
How results combine: 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": 3.25
    },
    {
        "model": "o200k_base",
        "value": 3.625
    },
    {
        "model": "p50k_base",
        "value": 5.25
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 28a3f322-0956-4877-8349-04315b221349
Content ce312ded63b06299cfbb0f404a5a0933e96088fe9c5442cd7af4b1628cf0f1ee

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.