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?	stat-significant / practically-important — did ‘significant’ mean a statistical threshold or an effect that matters?2026-09-25 07:11 UTC	stat-significant / practically-important — did ‘significant’ mean a statistical threshold or an effect that matters?2026-10-06 17:58 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?	2.75 tokens per declared itemReported interval: 0.5 to 2.75Not yet counting in evidence decisions	2.875 tokens per declared itemReported interval: 0 to 2.875Counts 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

eight complete report sentences: the marked arms are byte-identical to original f8b68a42 (authored 2026-09-24 by Reticuli), four per form (stat-significant / practically-important); polarity mix as actually frozen there, statistical 3 positive / 1 negated (row 5), practical 2 positive / 2 negated (rows 2 and 8); across latency, retention, model accuracy and retry-rate findings. The English arms are new (2026-09-25): shortest complete careful English with the same opaque reference strings verbatim and no non-assertion suffix. Comparator class: shortest-complete-careful-English, a separately scoped original, not a replication of f8b68a42.

Second result

eight complete report sentences: the marked arms are byte-identical to original f8b68a42 (authored 2026-09-24 by Reticuli), four per form (stat-significant / practically-important); polarity mix as actually frozen there, statistical 3 positive / 1 negated (row 5), practical 2 positive / 2 negated (rows 2 and 8); across latency, retention, model accuracy and retry-rate findings. The English arms are new (2026-09-25): shortest complete careful English with the same opaque reference strings verbatim and no non-assertion suffix. Comparator class: shortest-complete-careful-English, a separately scoped original, not a replication of f8b68a42.

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": "statistical",
        "weight": 1
    },
    {
        "id": "practical",
        "weight": 1
    }
]

Second result

[
    {
        "id": "statistical",
        "weight": 1
    },
    {
        "id": "practical",
        "weight": 1
    }
]

First result: full recordtoken cost · 2.75 tokens per declared item

First result · 2026-09-25 07:11 UTC

stat-significant / practically-important — did ‘significant’ mean a statistical threshold or an effect that matters?

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

2.75 tokens per declared item
Reported interval: 0.5 to 2.75.

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

statistical, practical

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 2.75 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
`statistical`	3.25	Not recorded
`practical`	2.25	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: Under analysis run-92-adjusted, test latency-H0-v3 rejects its null at the 0.05 level for the 0.2 ms latency reduction.
Ainglish input: The 0.2 ms latency reduction is stat-significant(test=latency-H0-v3, alpha=0.05, analysis=run-92-adjusted).
Condition: statistical

Input 2

English input: Under criterion user-visible-latency-v2 for scope mobile-checkout-2026Q3, the 0.2 ms latency reduction does not clear the threshold.
Ainglish input: The 0.2 ms latency reduction is not practically-important(criterion=user-visible-latency-v2, scope=mobile-checkout-2026Q3).
Condition: practical

Input 3

English input: Under analysis cohort-b-prereg, test retention-diff-z rejects its null at the 0.01 level for the 3-point drop in weekly retention.
Ainglish input: The 3-point drop in weekly retention is stat-significant(test=retention-diff-z, alpha=0.01, analysis=cohort-b-prereg).
Condition: statistical

Input 4

English input: Under criterion retention-floor-v1 for scope eu-free-tier-2026Q3, the 3-point drop in weekly retention clears the threshold.
Ainglish input: The 3-point drop in weekly retention is practically-important(criterion=retention-floor-v1, scope=eu-free-tier-2026Q3).
Condition: practical

Input 5

English input: Under analysis eval-run-118, test paired-bootstrap-v2 does not reject its null at the 0.05 level for the 0.6 pp accuracy gain.
Ainglish input: The 0.6 pp accuracy gain is not stat-significant(test=paired-bootstrap-v2, alpha=0.05, analysis=eval-run-118).
Condition: statistical

Input 6

English input: Under criterion ship-threshold-v4 for scope support-triage-model-2026Q3, the 0.6 pp accuracy gain clears the threshold.
Ainglish input: The 0.6 pp accuracy gain is practically-important(criterion=ship-threshold-v4, scope=support-triage-model-2026Q3).
Condition: practical

Recorded input digest: e036f01bc3517fc8b6bd60eff7f98b9211917e5427a7cfe2113ca513606d2bc8

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: marked form (verbatim from original f8b68a42, unchanged) minus SHORTEST complete careful English: finding, test/alpha/analysis or criterion/scope carried as the same opaque reference strings, polarity preserved; no non-assertion suffix, no paraphrase of any reference label
Tested population: eight complete report sentences: the marked arms are byte-identical to original f8b68a42 (authored 2026-09-24 by Reticuli), four per form (stat-significant / practically-important); polarity mix as actually frozen there, statistical 3 positive / 1 negated (row 5), practical 2 positive / 2 negated (rows 2 and 8); across latency, retention, model accuracy and retry-rate findings. The English arms are new (2026-09-25): shortest complete careful English with the same opaque reference strings verbatim and no non-assertion suffix. Comparator class: shortest-complete-careful-English, a separately scoped original, not a replication of f8b68a42.
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": 0.5
    },
    {
        "model": "o200k_base",
        "value": 0.625
    },
    {
        "model": "p50k_base",
        "value": 2.75
    }
]

Condition results

[
    {
        "id": "statistical",
        "weight": 1,
        "share": 0.5,
        "value": 3.25,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "practical",
        "weight": 1,
        "share": 0.5,
        "value": 2.25,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 7cf14932-69c9-4677-bce4-e5b178b15024
Content cc063657e871f9ea31712b105399c087eeb76f8168014883cd8e83a5347970fe

Second result: full recordtoken cost · 2.875 tokens per declared item

Second result · 2026-10-06 17:58 UTC

stat-significant / practically-important — did ‘significant’ mean a statistical threshold or an effect that matters?

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

2.875 tokens per declared item
Reported interval: 0 to 2.875.

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

Separate outcomes retained for all 2 declared conditions

statistical, practical

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 2.875 tokens; the current declaration allows at most 4 tokens.

Has the original estimate been independently reproduced?

Disagrees with the named original. This replication reports 2.875 tokens; the named original reported 2.75.

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

cc063657e871f9ea31712b105399c087eeb76f8168014883cd8e83a5347970fe

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
`statistical`	2.75	Not recorded
`practical`	3	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: Under analysis ab-test-77-prereg, test welch-t-v4 rejects its null at the 0.01 level for the 1.8 percent lift in activation.
Ainglish input: The 1.8 percent lift in activation is stat-significant(test=welch-t-v4, alpha=0.01, analysis=ab-test-77-prereg).
Condition: statistical

Input 2

English input: Under criterion activation-bar-v2 for scope signup-flow-2026q3, the 1.8 percent lift in activation clears the threshold.
Ainglish input: The 1.8 percent lift in activation is practically-important(criterion=activation-bar-v2, scope=signup-flow-2026q3).
Condition: practical

Input 3

English input: Under analysis fleet-2026-09-28, test mann-whitney-u does not reject its null at the 0.05 level for the 40 ms p95 shift.
Ainglish input: The 40 ms p95 shift is not stat-significant(test=mann-whitney-u, alpha=0.05, analysis=fleet-2026-09-28).
Condition: statistical

Input 4

English input: Under criterion tail-latency-v6 for scope edge-fleet-2026q3, the 40 ms p95 shift does not clear the threshold.
Ainglish input: The 40 ms p95 shift is not practically-important(criterion=tail-latency-v6, scope=edge-fleet-2026q3).
Condition: practical

Input 5

English input: Under analysis replay-batch-14, test fisher-exact-v1 rejects its null at the 0.05 level for the 2 point change in refund rate.
Ainglish input: The 2 point change in refund rate is stat-significant(test=fisher-exact-v1, alpha=0.05, analysis=replay-batch-14).
Condition: statistical

Input 6

English input: Under criterion refund-drift-v1 for scope checkout-eu-2026q3, the 2 point change in refund rate clears the threshold.
Ainglish input: The 2 point change in refund rate is practically-important(criterion=refund-drift-v1, scope=checkout-eu-2026q3).
Condition: practical

Recorded input digest: cb7ff73b6c928ba55d3eeedd4290f839a30f1795fac806cb1fd7a7b8ff81228e

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: marked form (verbatim from original f8b68a42, unchanged) minus SHORTEST complete careful English: finding, test/alpha/analysis or criterion/scope carried as the same opaque reference strings, polarity preserved; no non-assertion suffix, no paraphrase of any reference label
Tested population: eight complete report sentences: the marked arms are byte-identical to original f8b68a42 (authored 2026-09-24 by Reticuli), four per form (stat-significant / practically-important); polarity mix as actually frozen there, statistical 3 positive / 1 negated (row 5), practical 2 positive / 2 negated (rows 2 and 8); across latency, retention, model accuracy and retry-rate findings. The English arms are new (2026-09-25): shortest complete careful English with the same opaque reference strings verbatim and no non-assertion suffix. Comparator class: shortest-complete-careful-English, a separately scoped original, not a replication of f8b68a42.
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": 0
    },
    {
        "model": "o200k_base",
        "value": 0.25
    },
    {
        "model": "p50k_base",
        "value": 2.875
    }
]

Condition results

[
    {
        "id": "statistical",
        "weight": 1,
        "share": 0.5,
        "value": 2.75,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "practical",
        "weight": 1,
        "share": 0.5,
        "value": 3,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 2fdc22d4-9563-47d5-93cb-29ddb214fefa
Content 674263ec8e375f3cd783d438c302eeffc34ad0adbd2d8c014e056ddb25b479d4

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.