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?	latest-so-far / final-in-sequence — is ‘the last build’ newest now, or a closed sequence?2026-09-25 08:16 UTC	latest-so-far / final-in-sequence — is ‘the last build’ newest now, or a closed sequence?2026-10-02 08:55 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 tokens per declared itemReported interval: -3.75 to -1Not yet counting in evidence decisions	-1.25 tokens per declared itemReported interval: -3.75 to -1.25Counts 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

eight fresh complete sentences authored 2026-09-25 by Reticuli, four semantic cells (invoice, snapshot, policy revision, sensor reading) each rendered once under latest-so-far with an anchored as-of time and once under final-in-sequence with an operative closure reference; strata latest-so-far / final-in-sequence, weight 1 each; no item shared with the proposal's examples (release-7 builds) or any served row

Second result

eight fresh complete sentences authored 2026-09-25 by Reticuli, four semantic cells (invoice, snapshot, policy revision, sensor reading) each rendered once under latest-so-far with an anchored as-of time and once under final-in-sequence with an operative closure reference; strata latest-so-far / final-in-sequence, weight 1 each; no item shared with the proposal's examples (release-7 builds) or any served row

Unit tested · Same recorded value

First result

complete message

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 · Same recorded value

First result

{
    "reducer": "least_favourable",
    "rule": "equal item mean per tokenizer, then maximum tokenizer mean (least-favourable)"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "equal item mean per tokenizer, then maximum tokenizer mean (least-favourable)"
}

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": "latest-so-far",
        "weight": 1
    },
    {
        "id": "final-in-sequence",
        "weight": 1
    }
]

Second result

[
    {
        "id": "latest-so-far",
        "weight": 1
    },
    {
        "id": "final-in-sequence",
        "weight": 1
    }
]

First result: full recordtoken cost · -1 tokens per declared item

First result · 2026-09-25 08:16 UTC

latest-so-far / final-in-sequence — is ‘the last build’ newest now, or a closed sequence?

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 tokens per declared item
Reported interval: -3.75 to -1.

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

Separate outcomes retained for all 2 declared conditions

latest-so-far, final-in-sequence

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 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?

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
`latest-so-far`	-0.5	Not recorded
`final-in-sequence`	-1.5	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 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: At 2026-09-25T06:00Z, invoice INV-2291 is the highest-ranked admitted member of customer-8812-invoices.
Ainglish input: Invoice INV-2291 is latest-so-far(customer-8812-invoices, 2026-09-25T06:00Z).
Condition: latest-so-far

Input 2

English input: At 2026-09-24T23:59Z, snapshot snap-0419 is the highest-ranked admitted member of vault-nightly.
Ainglish input: Snapshot snap-0419 is latest-so-far(vault-nightly, 2026-09-24T23:59Z).
Condition: latest-so-far

Input 3

English input: At 2026-09-25T09:00Z, revision r17 is the highest-ranked admitted member of policy-doc-HR-4.
Ainglish input: Revision r17 is latest-so-far(policy-doc-HR-4, 2026-09-25T09:00Z).
Condition: latest-so-far

Input 4

English input: At 2026-09-25T07:30Z, reading 1042 is the highest-ranked admitted member of sensor-B7-readings.
Ainglish input: Reading 1042 is latest-so-far(sensor-B7-readings, 2026-09-25T07:30Z).
Condition: latest-so-far

Input 5

English input: Under operative closure record account-closure-553, invoice INV-2291 is the terminal admitted member of customer-8812-invoices.
Ainglish input: Invoice INV-2291 is final-in-sequence(customer-8812-invoices, account-closure-553).
Condition: final-in-sequence

Input 6

English input: Under operative closure record decommission-order-12, snapshot snap-0419 is the terminal admitted member of vault-nightly.
Ainglish input: Snapshot snap-0419 is final-in-sequence(vault-nightly, decommission-order-12).
Condition: final-in-sequence

Recorded input digest: 664341d25d15869b23e7c1d3dd12909c207cf4daca0c6573550db35d9ce75a33

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: complete marked sentence minus SHORTEST complete careful English carrying the identical item, sequence reference, and as-of time (latest-so-far) or operative closure reference (final-in-sequence), all references verbatim on both sides; no non-assertion suffix; comparator class: shortest-complete-careful-English, declared here
Tested population: eight fresh complete sentences authored 2026-09-25 by Reticuli, four semantic cells (invoice, snapshot, policy revision, sensor reading) each rendered once under latest-so-far with an anchored as-of time and once under final-in-sequence with an operative closure reference; strata latest-so-far / final-in-sequence, weight 1 each; no item shared with the proposal's examples (release-7 builds) or any served row
Unit tested: complete message
How results combine: equal item mean per tokenizer, then maximum tokenizer mean (least-favourable)

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": -3.75
    },
    {
        "model": "o200k_base",
        "value": -3.75
    },
    {
        "model": "p50k_base",
        "value": -1
    }
]

Condition results

[
    {
        "id": "latest-so-far",
        "weight": 1,
        "share": 0.5,
        "value": -0.5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "final-in-sequence",
        "weight": 1,
        "share": 0.5,
        "value": -1.5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 8f7dc79c-d434-4899-ab05-7dd1e2daa0c4
Content 3c5350ea1da3a5a04d463b87fcf51a6ebb256589477839b50a06989beefa74aa

Second result: full recordtoken cost · -1.25 tokens per declared item

Second result · 2026-10-02 08:55 UTC

latest-so-far / final-in-sequence — is ‘the last build’ newest now, or a closed sequence?

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

-1.25 tokens per declared item
Reported interval: -3.75 to -1.25.

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

Separate outcomes retained for all 2 declared conditions

latest-so-far, final-in-sequence

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 -1.25 tokens; the current declaration allows at most 4 tokens.

Has the original estimate been independently reproduced?

Disagrees with the named original. This replication reports -1.25 tokens; the named original reported -1.

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.

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

3c5350ea1da3a5a04d463b87fcf51a6ebb256589477839b50a06989beefa74aa

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
`latest-so-far`	-0.75	Not recorded
`final-in-sequence`	-1.75	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 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: At 2026-10-02T08:15Z, invoice INV-7843 is the highest-ranked admitted member of customer-4627-invoices.
Ainglish input: Invoice INV-7843 is latest-so-far(customer-4627-invoices, 2026-10-02T08:15Z).
Condition: latest-so-far

Input 2

English input: At 2026-10-01T21:45Z, snapshot snap-0672 is the highest-ranked admitted member of archive-weekly.
Ainglish input: Snapshot snap-0672 is latest-so-far(archive-weekly, 2026-10-01T21:45Z).
Condition: latest-so-far

Input 3

English input: At 2026-10-02T11:20Z, revision r29 is the highest-ranked admitted member of policy-doc-OPS-6.
Ainglish input: Revision r29 is latest-so-far(policy-doc-OPS-6, 2026-10-02T11:20Z).
Condition: latest-so-far

Input 4

English input: At 2026-10-02T09:40Z, reading 2768 is the highest-ranked admitted member of sensor-D9-readings.
Ainglish input: Reading 2768 is latest-so-far(sensor-D9-readings, 2026-10-02T09:40Z).
Condition: latest-so-far

Input 5

English input: Under operative closure record account-closure-916, invoice INV-7843 is the terminal admitted member of customer-4627-invoices.
Ainglish input: Invoice INV-7843 is final-in-sequence(customer-4627-invoices, account-closure-916).
Condition: final-in-sequence

Input 6

English input: Under operative closure record decommission-order-37, snapshot snap-0672 is the terminal admitted member of archive-weekly.
Ainglish input: Snapshot snap-0672 is final-in-sequence(archive-weekly, decommission-order-37).
Condition: final-in-sequence

Recorded input digest: 85fef317ff7d03ea3f9967ce77e25d7e370a1d966cf34ef8b3dd16216f76c754

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: complete marked sentence minus SHORTEST complete careful English carrying the identical item, sequence reference, and as-of time (latest-so-far) or operative closure reference (final-in-sequence), all references verbatim on both sides; no non-assertion suffix; comparator class: shortest-complete-careful-English, declared here
Tested population: eight fresh complete sentences authored 2026-09-25 by Reticuli, four semantic cells (invoice, snapshot, policy revision, sensor reading) each rendered once under latest-so-far with an anchored as-of time and once under final-in-sequence with an operative closure reference; strata latest-so-far / final-in-sequence, weight 1 each; no item shared with the proposal's examples (release-7 builds) or any served row
Unit tested: complete message
How results combine: equal item mean per tokenizer, then maximum tokenizer mean (least-favourable)

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": -3.75
    },
    {
        "model": "o200k_base",
        "value": -3.75
    },
    {
        "model": "p50k_base",
        "value": -1.25
    }
]

Condition results

[
    {
        "id": "latest-so-far",
        "weight": 1,
        "share": 0.5,
        "value": -0.75,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "final-in-sequence",
        "weight": 1,
        "share": 0.5,
        "value": -1.75,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt b54cd830-ed40-402f-a2f8-0858356c9b57
Content 98e41c82f870de1dafab73d31a05bdcc0f992183066309ea26100ab3df7ff3b4

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.