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

64 prospective authored no-undo pairs, equal marker weights; fixed reference variants are not independent semantic frames

Second result

64 prospective authored no-undo pairs, equal marker weights; fixed reference variants are not independent semantic frames

Unit tested · Same recorded value

First result

one complete claim sentence with exactly shared resolved references and units

Second result

one complete claim sentence with exactly shared resolved references and units

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 complete-pair mean within each tokenizer, then maximum tokenizer mean (least-favourable) across the three; retain each marker separately"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "equal complete-pair mean within each tokenizer, then maximum tokenizer mean (least-favourable) across the three; retain each marker separately"
}

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": "no-undo",
        "weight": 1
    },
    {
        "id": "can-undo",
        "weight": 1
    }
]

Second result

[
    {
        "id": "no-undo",
        "weight": 1
    },
    {
        "id": "can-undo",
        "weight": 1
    }
]

First result · 2026-09-07 20:32 UTC

no-undo / can-undo(<how>) — can this action's effect be taken back, and by what path?

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

1.5 tokens per declared item
Reported interval: 0.75 to 1.5.

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

Separate outcomes retained for all 2 declared conditions

no-undo, can-undo

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 outside the allowance. The reported difference is 1.5 tokens; the current declaration allows at most 1 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
`no-undo`	1	Not recorded
`can-undo`	2	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 64 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 · `undo-0-0-n`

English input: Published bulletin E00 irreversibly.
Ainglish input: Published bulletin E00, no-undo.
Condition: no-undo

Input 2 · `undo-0-0-y`

English input: Published bulletin E00; restorable from snapshot S3.
Ainglish input: Published bulletin E00, can-undo(snapshot S3).
Condition: can-undo

Input 3 · `undo-0-1-n`

English input: Published bulletin E01 irreversibly.
Ainglish input: Published bulletin E01, no-undo.
Condition: no-undo

Input 4 · `undo-0-1-y`

English input: Published bulletin E01; restorable from the signed archive, within 14 days.
Ainglish input: Published bulletin E01, can-undo(the signed archive, within 14 days).
Condition: can-undo

Input 5 · `undo-0-2-n`

English input: Published bulletin E02 irreversibly.
Ainglish input: Published bulletin E02, no-undo.
Condition: no-undo

Input 6 · `undo-0-2-y`

English input: Published bulletin E02; restorable from backup B8; loses the last hour of changes.
Ainglish input: Published bulletin E02, can-undo(backup B8; loses the last hour of changes).
Condition: can-undo

Recorded input digest: bd21010e6aec6f04e7947309bac26b2ea52c8eb63f7464f96b74ea407219c285

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: registered surface versus concise meaning-complete careful English
Tested population: 64 prospective authored no-undo pairs, equal marker weights; fixed reference variants are not independent semantic frames
Unit tested: one complete claim sentence with exactly shared resolved references and units
How results combine: equal complete-pair mean within each tokenizer, then maximum tokenizer mean (least-favourable) across the three; retain each marker separately

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": 0.75
    },
    {
        "model": "o200k_base",
        "value": 0.75
    },
    {
        "model": "p50k_base",
        "value": 1.5
    }
]

Condition results

[
    {
        "id": "no-undo",
        "weight": 1,
        "share": 0.5,
        "value": 1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "can-undo",
        "weight": 1,
        "share": 0.5,
        "value": 2,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 65ddd298-5835-4de1-8ae0-cd458626d62d
Content 05054718ed806518246736d47ff7ee08bef6b4ad184011318cdf2ef2cd5bf3a5

Second result · 2026-09-08 10:19 UTC

no-undo / can-undo(<how>) — can this action's effect be taken back, and by what path?

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: 0.6875 to 1.25.

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

Separate outcomes retained for all 2 declared conditions

no-undo, can-undo

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 outside the allowance. The reported difference is 1.25 tokens; the current declaration allows at most 1 tokens.

Has the original estimate been independently reproduced?

Disagrees with the named original. This replication reports 1.25 tokens; the named original reported 1.5.

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.

Declared target content identity

05054718ed806518246736d47ff7ee08bef6b4ad184011318cdf2ef2cd5bf3a5

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
`no-undo`	1	Not recorded
`can-undo`	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 64 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: Published bulletin F00 irreversibly.
Ainglish input: Published bulletin F00, no-undo.
Condition: no-undo

Input 2

English input: Published bulletin F00; restorable from snapshot S3.
Ainglish input: Published bulletin F00, can-undo(snapshot S3).
Condition: can-undo

Input 3

English input: Published bulletin F01 irreversibly.
Ainglish input: Published bulletin F01, no-undo.
Condition: no-undo

Input 4

English input: Published bulletin F01; restorable from the signed archive, within 14 days.
Ainglish input: Published bulletin F01, can-undo(the signed archive, within 14 days).
Condition: can-undo

Input 5

English input: Published bulletin F02 irreversibly.
Ainglish input: Published bulletin F02, no-undo.
Condition: no-undo

Input 6

English input: Published bulletin F02; restorable from nightly backup, within 7 days.
Ainglish input: Published bulletin F02, can-undo(nightly backup, within 7 days).
Condition: can-undo

Recorded input digest: 60096e8524926cbbf60df20ece08f622344e427a40d14a5917ac82d6eb66e369

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: registered surface versus concise meaning-complete careful English
Tested population: 64 prospective authored no-undo pairs, equal marker weights; fixed reference variants are not independent semantic frames
Unit tested: one complete claim sentence with exactly shared resolved references and units
How results combine: equal complete-pair mean within each tokenizer, then maximum tokenizer mean (least-favourable) across the three; retain each marker separately

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": 0.6875
    },
    {
        "model": "o200k_base",
        "value": 0.75
    },
    {
        "model": "p50k_base",
        "value": 1.25
    }
]

Condition results

[
    {
        "id": "no-undo",
        "weight": 1,
        "share": 0.5,
        "value": 1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "can-undo",
        "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 607f6798-6a95-4f3b-af26-418a68cf4683
Content 4c89062ac6e235b6769dac48e961dd778d9d72a75e3df3d54085e152961c0bde

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.

Compare two experiments

Find experiments by proposal

no-undo / can-undo(<how>) — can this action's effect be taken back, and by what path?

Does the overall result hide differences between conditions?

Input 1 · undo-0-0-n

Input 2 · undo-0-0-y

Input 3 · undo-0-1-n

Input 4 · undo-0-1-y

Input 5 · undo-0-2-n

Input 6 · undo-0-2-y

Absolute arm results

Reader or tokenizer results

Condition results

no-undo / can-undo(<how>) — can this action's effect be taken back, and by what path?

Does the overall result hide differences between conditions?

Input 1

Input 2

Input 3

Input 4

Input 5

Input 6

Absolute arm results

Reader or tokenizer results

Condition results

Input 1 · `undo-0-0-n`

Input 2 · `undo-0-0-y`

Input 3 · `undo-0-1-n`

Input 4 · `undo-0-1-y`

Input 5 · `undo-0-2-n`

Input 6 · `undo-0-2-y`