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?	dispatched(<transport>) / delivered(<witness>) — say which transit event you witnessed, and who witnessed it2026-09-10 13:57 UTC	dispatched(<transport>) / delivered(<witness>) — say which transit event you witnessed, and who witnessed it2026-10-07 13:26 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?	5.25 tokens per declared itemReported interval: 3.125 to 5.25Not yet counting in evidence decisions	3.875 tokens per declared itemReported interval: 2.5 to 3.875Counts 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?	DisputedEligible replications disagree and this original does not hold a settlement majority.	Disagrees with the named originalThis eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

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

8 prospective authored pairs crossing transit phase (dispatched vs delivered) and actor role (sender/courier/system vs recipient/customer/subscriber)

Second result

8 prospective authored pairs crossing transit phase (dispatched vs delivered) and actor role (sender/courier/system vs recipient/customer/subscriber)

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: full recordtoken cost · 5.25 tokens per declared item

First result · 2026-09-10 13:57 UTC

dispatched(<transport>) / delivered(<witness>) — say which transit event you witnessed, and who witnessed it

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: 5.25 tokens per declared item
Reported interval: 3.125 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: Disputed
Eligible replications disagree and this original does not hold a settlement majority.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is 5.25 tokens; the current declaration allows at most 6 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?

Disputed.

Eligible replications disagree and this original does not hold 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 package was dispatched by the courier at 10:00 AM.
Ainglish input: The package dispatched(courier@2026-09-10T10:00).

Input 2

English input: The package was delivered to the recipient at 2:00 PM.
Ainglish input: The package delivered(recipient@2026-09-10T14:00).

Input 3

English input: We dispatched the shipment via air freight yesterday.
Ainglish input: We dispatched(shipment, via=air-freight@2026-09-09).

Input 4

English input: The shipment was delivered to the warehouse this morning.
Ainglish input: The shipment delivered(warehouse@2026-09-10T08:00).

Input 5

English input: The driver dispatched the order from the depot at dawn.
Ainglish input: The order dispatched(driver, from=depot@dawn).

Input 6

English input: The customer confirmed the order was delivered to their door.
Ainglish input: The order delivered(customer, to=door).

Recorded input digest: 460b72ce88e59636896f9a85ec9475d01c070a600cbe8f80bda5d009ed992038

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 dispatched/delivered marker versus full English paraphrase
Tested population: 8 prospective authored pairs crossing transit phase (dispatched vs delivered) and actor role (sender/courier/system vs recipient/customer/subscriber)
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": 3.125
    },
    {
        "model": "o200k_base",
        "value": 3.625
    },
    {
        "model": "p50k_base",
        "value": 5.25
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 8608ae86-49d9-431d-a8ca-c4acec35b7dc
Content 64045bdff4e3d8522d64989efaa0928fc11d9a261d9c5dad06b0509835616727

Second result: full recordtoken cost · 3.875 tokens per declared item

Second result · 2026-10-07 13:26 UTC

dispatched(<transport>) / delivered(<witness>) — say which transit event you witnessed, and who witnessed 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: 3.875 tokens per declared item
Reported interval: 2.5 to 3.875.
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: Disagrees with the named original
This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is 3.875 tokens; the current declaration allows at most 6 tokens.

Has the original estimate been independently reproduced?

Disagrees with the named original. This replication reports 3.875 tokens; the named original reported 5.25.

This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

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.

0 of 8 English inputs reuse text from either side of the original.
0 of 8 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

64045bdff4e3d8522d64989efaa0928fc11d9a261d9c5dad06b0509835616727

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 parcel was dispatched by the courier at 9:15 AM.
Ainglish input: The parcel dispatched(courier@2026-10-07T09:15).

Input 2

English input: The parcel was delivered to the recipient at 5:45 PM.
Ainglish input: The parcel delivered(recipient@2026-10-07T17:45).

Input 3

English input: We dispatched the crate via rail yesterday.
Ainglish input: We dispatched(crate, via=rail@2026-10-06).

Input 4

English input: The crate was delivered to the port this morning.
Ainglish input: The crate delivered(port@2026-10-07T06:30).

Input 5

English input: The clerk dispatched the invoice from the office at noon.
Ainglish input: The invoice dispatched(clerk, from=office@noon).

Input 6

English input: The client confirmed the invoice was delivered to their portal.
Ainglish input: The invoice delivered(client, to=portal).

Recorded input digest: 3e144393a65ca4f311659c7be0cd7cdca216040d029075e8f6ddcdc31d00ebc6

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 dispatched/delivered marker versus full English paraphrase
Tested population: 8 prospective authored pairs crossing transit phase (dispatched vs delivered) and actor role (sender/courier/system vs recipient/customer/subscriber)
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": 2.5
    },
    {
        "model": "o200k_base",
        "value": 2.625
    },
    {
        "model": "p50k_base",
        "value": 3.875
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt e77fcdda-bd58-46ab-982c-f783a0b46d22
Content 4ce973255f68942c0b3c6c07e15f01922cbe067e2326df300b91469d29f1963b

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.