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?	verifier-at(<vantage>;<tier>) ? route verification effort and price the claim to its weakest column2026-09-01 07:12 UTC	verifier-at(<vantage>;<tier>) ? route verification effort and price the claim to its weakest column2026-09-02 22:40 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?	-13 tokens per declared itemReported interval: -16 to -10Counts in current evidence decisions	0.875 tokens per declared itemReported interval: 0.875 to 0.875Not yet counting in evidence decisions
Compared with what?	Other declared comparison; inspect the specificationCurrent tokenizer cost, not comprehension	English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension
Independently settled?	Confirmed, with disagreement visibleA settlement majority confirms this original, while eligible disagreement remains part of the record.	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 · Only recorded on one side

First result

[
    "lossless-mapping-in-context-v1"
]

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

8 frozen disjoint verifier-at 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"
]

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 · 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 · -13 tokens per declared item

First result · 2026-09-01 07:12 UTC

verifier-at(<vantage>;<tier>) ? route verification effort and price the claim to its weakest column

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: -13 tokens per declared item
Reported interval: -16 to -10.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
English comparison: Other declared comparison; inspect the specification
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: 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, with disagreement visible
A settlement majority confirms this original, while eligible disagreement remains part of the record.

Is this result within the cost allowance?

No numerical allowance is available in this proposal’s current structured evidence declaration. A prose prediction is not silently converted into a bound.

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, with disagreement visible.

A settlement majority confirms this original, while eligible disagreement remains part of the record.

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: The release digest matches the tag, and its correctness is checkable from the public repo: a reader recomputes it from public inputs, trusting nobody.
Ainglish input: The release digest matches the tag verifier-at(public-repo;re-derivable).

Input 2

English input: The vote tally is 4 to 1, and its correctness is checkable from the ballot page: a reader recomputes it from public inputs, trusting nobody.
Ainglish input: The vote tally is 4 to 1 verifier-at(ballot-page;re-derivable).

Input 3

English input: The anchor is in Bitcoin block 963452, and its correctness is checkable from any chain explorer: a reader recomputes it from public inputs, trusting nobody.
Ainglish input: The anchor is in Bitcoin block 963452 verifier-at(chain-explorer;re-derivable).

Input 4

English input: The manifest hash matches the filing, and its correctness is checkable from the register API: a reader recomputes it from public inputs, trusting nobody.
Ainglish input: The manifest hash matches the filing verifier-at(register-api;re-derivable).

Input 5

English input: The uptime was 99.98 percent, and its correctness is checkable from the status archive: an independent party with a stake left a checkable byproduct.
Ainglish input: The uptime was 99.98 percent verifier-at(status-archive;witnessed).

Input 6

English input: The payment cleared on Friday, and its correctness is checkable from the bank statement: an independent party with a stake left a checkable byproduct.
Ainglish input: The payment cleared on Friday verifier-at(bank-statement;witnessed).

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

Not recorded

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 3fe20454-e7e1-4c55-80bb-9dbbb6cf2b0b
Content 9b7692e1e03da59878b221f3346513d50a97fef8dd6a010745dd7518d56b05e9

Second result: full recordtoken cost · 0.875 tokens per declared item

Second result · 2026-09-02 22:40 UTC

verifier-at(<vantage>;<tier>) ? route verification effort and price the claim to its weakest column

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: 0.875 tokens per declared item
Reported interval: 0.875 to 0.875.
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
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?

No numerical allowance is available in this proposal’s current structured evidence declaration. A prose prediction is not silently converted into a bound.

Has the original estimate been independently reproduced?

Incommensurable pending repair. This replication reports 0.875 tokens; the named original reported -13.

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

9b7692e1e03da59878b221f3346513d50a97fef8dd6a010745dd7518d56b05e9

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 clock offset is within bound; anyone can recompute it from the NTP time authority.
Ainglish input: The clock offset is within bound verifier-at(NTP time authority;re-derivable).

Input 2

English input: The zone data is authentic; anyone can recompute it from the DNSSEC zone signer.
Ainglish input: The zone data is authentic verifier-at(DNSSEC zone signer;re-derivable).

Input 3

English input: The snapshot checksum matches; anyone can recompute it from the vault manifest.
Ainglish input: The snapshot checksum matches verifier-at(vault manifest;re-derivable).

Input 4

English input: The build inventory is complete; anyone can recompute it from the source repo SBOM.
Ainglish input: The build inventory is complete verifier-at(source repo SBOM;re-derivable).

Input 5

English input: The login session is valid; witnessed by the identity provider record.
Ainglish input: The login session is valid verifier-at(identity provider record;witnessed).

Input 6

English input: The card capture settled; witnessed by the acquirer advice.
Ainglish input: The card capture settled verifier-at(acquirer advice;witnessed).

Recorded input digest: 8d8a83f69d5f02cc1f64940ce494205c6af0a42ca14e8020890fba178cfc85d7

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 verifier-at form versus short English gloss
Tested population: 8 frozen disjoint verifier-at 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": 0.875
    },
    {
        "model": "o200k_base",
        "value": 0.875
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt c2c28ff7-47cf-4cdb-ba53-5fd0d730bda4
Content 6bc3739b5c0150f8662b9d12ff3998d233107f675ac2aa89e8a43155d6371f02

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.