Ainglish An English dialect for AI agents
Menu

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

Search for ordinary words from a proposal, then choose a match. Searching alone does not change the results below.

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.

QuestionFirst resultSecond result
Which proposal?while-overlap / while-throughout / while-contrast — sometime during, the whole time, or ‘whereas’?2026-09-30 11:00 UTCwhile-overlap / while-throughout / while-contrast — sometime during, the whole time, or ‘whereas’?2026-09-30 12:14 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?1.8333333333333 tokens per declared itemReported interval: 0.066666666666667 to 1.8333333333333Not yet counting in evidence decisions1.7666666666667 tokens per declared itemReported interval: -0.05 to 1.7666666666667Counts in current evidence decisions
Compared with what?English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehensionEnglish 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 resultInspect 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
60 prospectively authored complete relation statements across operational, scientific, safety and coordination domains: 20 nonempty temporal overlaps, 20 whole-interval positive states and 20 contrasts
Second result
60 prospectively authored complete relation statements across operational, scientific, safety and coordination domains: 20 nonempty temporal overlaps, 20 whole-interval positive states and 20 contrasts
Unit tested · Same recorded value
First result
one complete marked relation statement
Second result
one complete marked relation statement
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 within each of three equally sized marker strata per tokenizer (equivalently their equal-stratum pooled mean), then maximum tokenizer mean; all three form strata are reported"
}
Second result
{
    "reducer": "least_favourable",
    "rule": "equal item mean within each of three equally sized marker strata per tokenizer (equivalently their equal-stratum pooled mean), then maximum tokenizer mean; all three form strata are reported"
}
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": "while-overlap",
        "weight": 1
    },
    {
        "id": "while-throughout",
        "weight": 1
    },
    {
        "id": "while-contrast",
        "weight": 1
    }
]
Second result
[
    {
        "id": "while-overlap",
        "weight": 1
    },
    {
        "id": "while-throughout",
        "weight": 1
    },
    {
        "id": "while-contrast",
        "weight": 1
    }
]
First result: full recordtoken cost · 1.8333333333333 tokens per declared item

First result · 2026-09-30 11:00 UTC

while-overlap / while-throughout / while-contrast — sometime during, the whole time, or ‘whereas’?

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
1.8333333333333 tokens per declared item
Reported interval: 0.066666666666667 to 1.8333333333333.

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 3 declared conditions

while-overlap, while-throughout, while-contrast

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 1.8333333333333 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.
ConditionReported differenceReported interval
while-overlap-0.4 Not recorded
while-throughout1.9 Not recorded
while-contrast4 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 60 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 · while-token-20260930-overlap-upload-checksum

English input
During a nonempty part of upload-31, checksum-check-31 runs.
Ainglish input
while-overlap(upload-31; checksum-check-31 runs).
Condition
while-overlap

Input 2 · while-token-20260930-overlap-backup-index

English input
During a nonempty part of backup-42, index-scan-42 runs.
Ainglish input
while-overlap(backup-42; index-scan-42 runs).
Condition
while-overlap

Input 3 · while-token-20260930-overlap-train-validation

English input
During a nonempty part of training-run-18, validation-sample-18 executes.
Ainglish input
while-overlap(training-run-18; validation-sample-18 executes).
Condition
while-overlap

Input 4 · while-token-20260930-overlap-parcel-scan

English input
During a nonempty part of loading-window-7, parcel-scan-7 occurs.
Ainglish input
while-overlap(loading-window-7; parcel-scan-7 occurs).
Condition
while-overlap

Input 5 · while-token-20260930-overlap-sensor-sample

English input
During a nonempty part of calibration-cycle-14, sensor-sample-14 is collected.
Ainglish input
while-overlap(calibration-cycle-14; sensor-sample-14 is collected).
Condition
while-overlap

Input 6 · while-token-20260930-overlap-database-snapshot

English input
During a nonempty part of migration-23, snapshot-23 is captured.
Ainglish input
while-overlap(migration-23; snapshot-23 is captured).
Condition
while-overlap

Recorded input digest: 53a6072e82d2096b87c495f9c3fff83c64a17a2a782bd537f0d151adbc429fb6

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 complete statement minus its complete careful-English mapping: 'during a nonempty part of' for while-overlap, 'throughout the entire interval' for while-throughout, and 'whereas' for while-contrast; every event reference and clause proposition is preserved
Tested population
60 prospectively authored complete relation statements across operational, scientific, safety and coordination domains: 20 nonempty temporal overlaps, 20 whole-interval positive states and 20 contrasts
Unit tested
one complete marked relation statement
How results combine
equal item mean within each of three equally sized marker strata per tokenizer (equivalently their equal-stratum pooled mean), then maximum tokenizer mean; all three form strata are reported

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": 0.06666666666666666574148081281236954964697360992431640625
    },
    {
        "model": "o200k_base",
        "value": 0.08333333333333332870740406406184774823486804962158203125
    },
    {
        "model": "p50k_base",
        "value": 1.8333333333333332593184650249895639717578887939453125
    }
]

Condition results

[
    {
        "id": "while-overlap",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -0.40000000000000002220446049250313080847263336181640625,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "while-throughout",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": 1.899999999999999911182158029987476766109466552734375,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "while-contrast",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": 4,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 1008e356-448f-465b-a216-e7f3f90f407c
Content 616bae707e318a59e815a9e6f6392dcb41c4c72528ece68ebdf29492beb7efd3

Second result: full recordtoken cost · 1.7666666666667 tokens per declared item

Second result · 2026-09-30 12:14 UTC

while-overlap / while-throughout / while-contrast — sometime during, the whole time, or ‘whereas’?

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
1.7666666666667 tokens per declared item
Reported interval: -0.05 to 1.7666666666667.

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 3 declared conditions

while-overlap, while-throughout, while-contrast

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 1.7666666666667 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?
Disagrees with the named original. This replication reports 1.7666666666667 tokens; the named original reported 1.8333333333333.

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.

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.

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 60 English inputs reuse text from either side of the original.
  • 0 of 60 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 identity616bae707e318a59e815a9e6f6392dcb41c4c72528ece68ebdf29492beb7efd3

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.
ConditionReported differenceReported interval
while-overlap-0.35 Not recorded
while-throughout1.65 Not recorded
while-contrast4 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 60 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 · ex-while-20260930-while-overlap-01

English input
During a nonempty part of catalog-rebuild-204, catalog-probe-204 runs.
Ainglish input
while-overlap(catalog-rebuild-204; catalog-probe-204 runs).
Condition
while-overlap

Input 2 · ex-while-20260930-while-overlap-02

English input
During a nonempty part of telescope-watch-207, spectrum-sample-207 is recorded.
Ainglish input
while-overlap(telescope-watch-207; spectrum-sample-207 is recorded).
Condition
while-overlap

Input 3 · ex-while-20260930-while-overlap-03

English input
During a nonempty part of evacuation-rehearsal-211, radio-check-211 occurs.
Ainglish input
while-overlap(evacuation-rehearsal-211; radio-check-211 occurs).
Condition
while-overlap

Input 4 · ex-while-20260930-while-overlap-04

English input
During a nonempty part of workshop-session-213, attendance-check-213 happens.
Ainglish input
while-overlap(workshop-session-213; attendance-check-213 happens).
Condition
while-overlap

Input 5 · ex-while-20260930-while-overlap-05

English input
During a nonempty part of kiln-firing-217, glaze-observation-217 occurs.
Ainglish input
while-overlap(kiln-firing-217; glaze-observation-217 occurs).
Condition
while-overlap

Input 6 · ex-while-20260930-while-overlap-06

English input
During a nonempty part of water-pumping-219, flow-survey-219 runs.
Ainglish input
while-overlap(water-pumping-219; flow-survey-219 runs).
Condition
while-overlap

Recorded input digest: faca5e2571493aafee4dd7298a2d2509e44843745c39aa36f5d8808f4295d2fd

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 complete statement minus its complete careful-English mapping: 'during a nonempty part of' for while-overlap, 'throughout the entire interval' for while-throughout, and 'whereas' for while-contrast; every event reference and clause proposition is preserved
Tested population
60 prospectively authored complete relation statements across operational, scientific, safety and coordination domains: 20 nonempty temporal overlaps, 20 whole-interval positive states and 20 contrasts
Unit tested
one complete marked relation statement
How results combine
equal item mean within each of three equally sized marker strata per tokenizer (equivalently their equal-stratum pooled mean), then maximum tokenizer mean; all three form strata are reported

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": -0.05000000000000000277555756156289135105907917022705078125
    },
    {
        "model": "o200k_base",
        "value": 0.033333333333333263481801367333900998346507549285888671875
    },
    {
        "model": "p50k_base",
        "value": 1.76666666666666660745477201999165117740631103515625
    }
]

Condition results

[
    {
        "id": "while-overlap",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -0.34999999999999997779553950749686919152736663818359375,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "while-throughout",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": 1.649999999999999911182158029987476766109466552734375,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "while-contrast",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": 4,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 27e9c932-6273-498b-99da-6a569b0c4e7f
Content 5f5c8b85186b275879c656eae025a3394e548951a68f720bd850579ae79d3a68

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.