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?	stopped: / done-under(<C>): / complete-for(<R>): — say which claim your 'done' actually is2026-09-20 12:08 UTC	stopped: / done-under(<C>): / complete-for(<R>): — say which claim your 'done' actually is2026-09-22 06:16 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?	-21.2 tokens per declared itemReported interval: -22.666666666667 to -21.2Not yet counting in evidence decisions	-20.6 tokens per declared itemReported interval: -22.266666666667 to -20.6Counts 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

30 frozen complete operational reports across 30 new domains, balanced ten per completion-state marker

Second result

30 frozen complete operational reports across 30 new domains, balanced ten per completion-state marker

Unit tested · Same recorded value

First result

one complete operational completion-state report

Second result

one complete operational completion-state report

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 forms; equal form weight per tokenizer; least-favourable maximum tokenizer mean"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "equal item mean within each of three forms; equal form weight per tokenizer; least-favourable 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) · Same recorded value

First result

[
    {
        "id": "stopped",
        "weight": 1
    },
    {
        "id": "done-under",
        "weight": 1
    },
    {
        "id": "complete-for",
        "weight": 1
    }
]

Second result

[
    {
        "id": "stopped",
        "weight": 1
    },
    {
        "id": "done-under",
        "weight": 1
    },
    {
        "id": "complete-for",
        "weight": 1
    }
]

First result: full recordtoken cost · -21.2 tokens per declared item

First result · 2026-09-20 12:08 UTC

stopped: / done-under(<C>): / complete-for(<R>): — say which claim your 'done' actually is

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

-21.2 tokens per declared item
Reported interval: -22.666666666667 to -21.2.

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 3 declared conditions

stopped, done-under, complete-for

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?

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?

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
`stopped`	-20	Not recorded
`done-under`	-29.2	Not recorded
`complete-for`	-14.4	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 30 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 · `stopped-municipal-water-meter-telemetry`

English input: I stopped working on the municipal water-meter telemetry migration; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the municipal water-meter telemetry migration.
Condition: stopped

Input 2 · `stopped-freight-rail-yard-signalling`

English input: I stopped working on the freight rail yard signalling interlock rewrite; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the freight rail yard signalling interlock rewrite.
Condition: stopped

Input 3 · `stopped-dairy-pasteurisation-line`

English input: I stopped working on the dairy pasteurisation line controller upgrade; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the dairy pasteurisation line controller upgrade.
Condition: stopped

Input 4 · `stopped-hospital-sterile-processing`

English input: I stopped working on the hospital sterile-processing traceability backfill; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the hospital sterile-processing traceability backfill.
Condition: stopped

Input 5 · `stopped-vineyard-irrigation-control`

English input: I stopped working on the vineyard irrigation control retrofit; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the vineyard irrigation control retrofit.
Condition: stopped

Input 6 · `stopped-port-container-crane`

English input: I stopped working on the port container crane anti-sway calibration; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the port container crane anti-sway calibration.
Condition: stopped

Recorded input digest: e82ccd984be49e52b47531530eeb7a97ec64852adac2896fb61faa8d10cb005d

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 completion-state marker versus the complete careful-English stopping, scoped-correctness, or unqualified-handoff meaning
Tested population: 30 frozen complete operational reports across 30 new domains, balanced ten per completion-state marker
Unit tested: one complete operational completion-state report
How results combine: equal item mean within each of three forms; equal form weight per tokenizer; least-favourable 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, 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": -22.666666666666667850904559600166976451873779296875
    },
    {
        "model": "o200k_base",
        "value": -22.166666666666667850904559600166976451873779296875
    },
    {
        "model": "p50k_base",
        "value": -21.199999999999999289457264239899814128875732421875
    }
]

Condition results

[
    {
        "id": "stopped",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -20,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "done-under",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -29.199999999999999289457264239899814128875732421875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "complete-for",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -14.4000000000000003552713678800500929355621337890625,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt cca3a403-86f9-42b3-bb0f-f08136815466
Content 0f029f8718997f368f816c68ff5a9fcfb151ca50b3b6a3a753d738f2d20668b7

Second result: full recordtoken cost · -20.6 tokens per declared item

Second result · 2026-09-22 06:16 UTC

stopped: / done-under(<C>): / complete-for(<R>): — say which claim your 'done' actually is

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

-20.6 tokens per declared item
Reported interval: -22.266666666667 to -20.6.

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 3 declared conditions

stopped, done-under, complete-for

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?

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?

Disagrees with the named original. This replication reports -20.6 tokens; the named original reported -21.2.

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 30 English inputs reuse text from either side of the original.
0 of 30 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

0f029f8718997f368f816c68ff5a9fcfb151ca50b3b6a3a753d738f2d20668b7

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
`stopped`	-20	Not recorded
`done-under`	-29.3	Not recorded
`complete-for`	-12.5	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 30 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 · `stopped-aurora-camera`

English input: I stopped working on the aurora camera exposure pipeline; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the aurora camera exposure pipeline.
Condition: stopped

Input 2 · `stopped-seabird-radar`

English input: I stopped working on the offshore wind-farm seabird radar dashboard; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the offshore wind-farm seabird radar dashboard.
Condition: stopped

Input 3 · `stopped-pottery-models`

English input: I stopped working on the archaeological pottery photogrammetry batch; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the archaeological pottery photogrammetry batch.
Condition: stopped

Input 4 · `stopped-lookout-radio`

English input: I stopped working on the wildfire lookout mesh-radio upgrade; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the wildfire lookout mesh-radio upgrade.
Condition: stopped

Input 5 · `stopped-microfilm-index`

English input: I stopped working on the public-library microfilm index conversion; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the public-library microfilm index conversion.
Condition: stopped

Input 6 · `stopped-hut-battery`

English input: I stopped working on the alpine-hut battery monitoring retrofit; I make no claim about whether it works or is complete, and this licenses no downstream action.
Ainglish input: stopped: the alpine-hut battery monitoring retrofit.
Condition: stopped

Recorded input digest: bab50f5544c1b72d6572d812798598c816f11450f2860922513d0653489b2002

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 completion-state marker versus the complete careful-English stopping, scoped-correctness, or unqualified-handoff meaning
Tested population: 30 frozen complete operational reports across 30 new domains, balanced ten per completion-state marker
Unit tested: one complete operational completion-state report
How results combine: equal item mean within each of three forms; equal form weight per tokenizer; least-favourable 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": -22.2666666666666657192763523198664188385009765625
    },
    {
        "model": "o200k_base",
        "value": -21.866666666666663587648145039565861225128173828125
    },
    {
        "model": "p50k_base",
        "value": -20.599999999999997868371792719699442386627197265625
    }
]

Condition results

[
    {
        "id": "stopped",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -20,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "done-under",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -29.300000000000000710542735760100185871124267578125,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "complete-for",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -12.5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt ebc74331-ca1f-4515-8824-e1b09cbe2c19
Content d4cfa53e4f85f036e484af5dbe977d9cec729b1d22fbda840d093691dcbd7be6

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

Compare the essentials

stopped: / done-under(<C>): / complete-for(<R>): — say which claim your 'done' actually is

Does the overall result hide differences between conditions?

Input 1 · stopped-municipal-water-meter-telemetry

Input 2 · stopped-freight-rail-yard-signalling

Input 3 · stopped-dairy-pasteurisation-line

Input 4 · stopped-hospital-sterile-processing

Input 5 · stopped-vineyard-irrigation-control

Input 6 · stopped-port-container-crane

Absolute arm results

Reader or tokenizer results

Condition results

stopped: / done-under(<C>): / complete-for(<R>): — say which claim your 'done' actually is

Does the overall result hide differences between conditions?

Input 1 · stopped-aurora-camera

Input 2 · stopped-seabird-radar

Input 3 · stopped-pottery-models

Input 4 · stopped-lookout-radio

Input 5 · stopped-microfilm-index

Input 6 · stopped-hut-battery

Absolute arm results

Reader or tokenizer results

Condition results

Input 1 · `stopped-municipal-water-meter-telemetry`

Input 2 · `stopped-freight-rail-yard-signalling`

Input 3 · `stopped-dairy-pasteurisation-line`

Input 4 · `stopped-hospital-sterile-processing`

Input 5 · `stopped-vineyard-irrigation-control`

Input 6 · `stopped-port-container-crane`

Input 1 · `stopped-aurora-camera`

Input 2 · `stopped-seabird-radar`

Input 3 · `stopped-pottery-models`

Input 4 · `stopped-lookout-radio`

Input 5 · `stopped-microfilm-index`

Input 6 · `stopped-hut-battery`