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?	only-<focus> — weld "only" to the words it excludes over: speech carried the binding as stress, writing dropped it2026-09-03 14:36 UTC	only-<focus> — weld "only" to the words it excludes over: speech carried the binding as stress, writing dropped it2026-09-04 19:47 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?	1.2083333333333 tokens per declared itemReported interval: 1.2083333333333 to 1.2083333333333Not yet counting in evidence decisions	1.1875 tokens per declared itemReported interval: 1.1875 to 1.1875Counts 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 · 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"
]

Second result

[
    "cl100k_base",
    "o200k_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": "subject",
        "weight": 1
    },
    {
        "id": "verb",
        "weight": 1
    },
    {
        "id": "object-nominal",
        "weight": 1
    },
    {
        "id": "adjunct",
        "weight": 1
    }
]

Second result

[
    {
        "id": "subject",
        "weight": 1
    },
    {
        "id": "verb",
        "weight": 1
    },
    {
        "id": "object-nominal",
        "weight": 1
    },
    {
        "id": "adjunct",
        "weight": 1
    }
]

First result: full recordtoken cost · 1.2083333333333 tokens per declared item

First result · 2026-09-03 14:36 UTC

only-<focus> — weld "only" to the words it excludes over: speech carried the binding as stress, writing dropped 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

1.2083333333333 tokens per declared item
Reported interval: 1.2083333333333 to 1.2083333333333.

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

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 4 declared conditions

subject, verb, object-nominal, adjunct

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 1.2083333333333 tokens; the current declaration allows at most 3 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.

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
`subject`	1.5	Not recorded
`verb`	1.1666666666667	Not recorded
`object-nominal`	1.1666666666667	Not recorded
`adjunct`	1	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 24 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: only Miriam authorized the shipment.
Ainglish input: only-Miriam authorized the shipment.
Condition: subject

Input 2

English input: only the compliance officer rejected the waiver.
Ainglish input: only-the-compliance-officer rejected the waiver.
Condition: subject

Input 3

English input: only three auditors verified the count.
Ainglish input: only-three-auditors verified the count.
Condition: subject

Input 4

English input: only our day supervisor confirmed the handoff.
Ainglish input: only-our-day-supervisor confirmed the handoff.
Condition: subject

Input 5

English input: only the release captain aborted the deploy.
Ainglish input: only-the-release-captain aborted the deploy.
Condition: subject

Input 6

English input: only Valen closed the incident.
Ainglish input: only-Valen closed the incident.
Condition: subject

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": 1.2083333333333332593184650249895639717578887939453125
    },
    {
        "model": "o200k_base",
        "value": 1.208333333333333481363069950020872056484222412109375
    }
]

Condition results

[
    {
        "id": "subject",
        "weight": 1,
        "share": 0.25,
        "value": 1.5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "verb",
        "weight": 1,
        "share": 0.25,
        "value": 1.1666666666666667406815349750104360282421112060546875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "object-nominal",
        "weight": 1,
        "share": 0.25,
        "value": 1.1666666666666667406815349750104360282421112060546875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "adjunct",
        "weight": 1,
        "share": 0.25,
        "value": 1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 9b5c24c4-5c31-493b-880b-8348ca14c55b
Content 4ef4767497f0c887161b25e2b12306dd5eaad4641ab1d16c0be0a239e3ef0fd1

Second result: full recordtoken cost · 1.1875 tokens per declared item

Second result · 2026-09-04 19:47 UTC

only-<focus> — weld "only" to the words it excludes over: speech carried the binding as stress, writing dropped 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

1.1875 tokens per declared item
Reported interval: 1.1875 to 1.1875.

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

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 4 declared conditions

subject, verb, object-nominal, adjunct

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 1.1875 tokens; the current declaration allows at most 3 tokens.

Has the original estimate been independently reproduced?

Disagrees with the named original. This replication reports 1.1875 tokens; the named original reported 1.2083333333333.

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

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.

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

4ef4767497f0c887161b25e2b12306dd5eaad4641ab1d16c0be0a239e3ef0fd1

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
`subject`	1.25	Not recorded
`verb`	1	Not recorded
`object-nominal`	1.75	Not recorded
`adjunct`	0.75	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

English input: only Soraya approved the exception.
Ainglish input: only-Soraya approved the exception.
Condition: subject

Input 2

English input: only the night auditor opened the archive.
Ainglish input: only-the-night-auditor opened the archive.
Condition: subject

Input 3

English input: only four reviewers signed the decision.
Ainglish input: only-four-reviewers signed the decision.
Condition: subject

Input 4

English input: only our backup operator restored the index.
Ainglish input: only-our-backup-operator restored the index.
Condition: subject

Input 5

English input: only the privacy lead viewed the export.
Ainglish input: only-the-privacy-lead viewed the export.
Condition: subject

Input 6

English input: only Kaito acknowledged the warning.
Ainglish input: only-Kaito acknowledged the warning.
Condition: subject

Recorded input digest: decc7a3541b780162bf870534826bcfd0aa8d89052dc70f46972f16e1c3620af

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

Not recorded

Reader or tokenizer results

[
    {
        "model": "cl100k_base",
        "value": 1.1875
    },
    {
        "model": "o200k_base",
        "value": 1.1875
    }
]

Condition results

[
    {
        "id": "subject",
        "weight": 1,
        "share": 0.25,
        "value": 1.25,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "verb",
        "weight": 1,
        "share": 0.25,
        "value": 1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "object-nominal",
        "weight": 1,
        "share": 0.25,
        "value": 1.75,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "adjunct",
        "weight": 1,
        "share": 0.25,
        "value": 0.75,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 44f4d9fb-3f7c-42c2-9bbb-e6cc6ae10945
Content 895f1d439bb73530527a41367c4df6e5961d1e041ea8fa87d9d624f5882b5810

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.