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

First result · 2026-09-05 19:31 UTC

prob / odds-for / odds-against — is a risk a share or a ratio, and which side comes first?

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

-3 tokens per declared item
Reported interval: -3.25 to -3.

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

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 3 declared conditions

prob, odds-for, odds-against

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

Confirmed, with disagreement visible

A settlement majority confirms this original, while eligible disagreement remains part of the record.

Reported token direction. Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.

Current declared cost bound: at most 4 tokens. This bound applies to the Ainglish-minus-English difference. The reported point value is within that bound. This uses the current declaration, not necessarily the one in force when the result was filed.

A numerical match is not a completed prerequisite. Current evidence status, independent settlement and the other declared results still determine readiness.

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
`prob`	-3	Not recorded
`odds-for`	-5	Not recorded
`odds-against`	-1	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.

Showing the first 3 of 32 readable, inline non-control items, in stored order—not a selection of successes. 0 control items omitted.

Input 1

English input: In forecast-0, E-00 means rain occurs before noon; its complement is that this event does not occur. The probability of E-00 is 0%.
Ainglish input: In forecast-0, E-00 means rain occurs before noon; its complement is that this event does not occur. prob(E-00)=0%.
Condition: prob

Input 2

English input: In forecast-0, E-01 means rain occurs before noon; its complement is that this event does not occur. The probability of E-01 is 100%.
Ainglish input: In forecast-0, E-01 means rain occurs before noon; its complement is that this event does not occur. prob(E-01)=100%.
Condition: prob

Input 3

English input: In forecast-0, E-00 means rain occurs before noon; its complement is that this event does not occur. The probability odds in favour of E-00 are 0:1.
Ainglish input: In forecast-0, E-00 means rain occurs before noon; its complement is that this event does not occur. odds-for(E-00)=0:1.
Condition: odds-for

Recorded input digest: 28fdbdb4cbf99c8d0b13c8b92319b8245c06236a3e0ff5969e54ee67714ef0e6

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: Current registered forms minus concise complete English carrying the same event, direction, scope, force and known quantities; no unqualified ambiguous substitute
Tested population: 32 prospective authored probability claims across all eight declared domains. Sixteen probability claims and eight of each odds form; eight rational edge/interior cases, including zero and certainty. Fixed 2:1:1 form mixture. Not random natural prose.
Unit tested: one complete scoped claim or operation, including identical surrounding context
How results combine: Declared weighted condition means within each tokenizer; maximum tokenizer mean (least-favourable) across cl100k_base and o200k_base. Bounds are tokenizer member span, not a population confidence interval.

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": -3.25
    },
    {
        "model": "o200k_base",
        "value": -3
    }
]

Condition results

[
    {
        "id": "prob",
        "weight": 2,
        "share": 0.5,
        "value": -3,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "odds-for",
        "weight": 1,
        "share": 0.25,
        "value": -5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "odds-against",
        "weight": 1,
        "share": 0.25,
        "value": -1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 3dc6b4c5-0fea-49ef-90a6-b74acb7a8697
Content dea6509b1747c9d9c37b904d0a02e31d1ac0441277cca79c61e5f431a5c8665d

Second result · 2026-09-06 08:56 UTC

prob / odds-for / odds-against — is a risk a share or a ratio, and which side comes first?

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: -3.09375 to -2.875.

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

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 3 declared conditions

prob, odds-for, odds-against

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.

Reported token direction. Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.

A numerical match is not a completed prerequisite. Current evidence status, independent settlement and the other declared results still determine readiness.

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

dea6509b1747c9d9c37b904d0a02e31d1ac0441277cca79c61e5f431a5c8665d

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
`prob`	-1.25	Not recorded
`odds-for`	-6	Not recorded
`odds-against`	-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.

Showing the first 3 of 32 readable, inline non-control items, in stored order—not a selection of successes. 0 control items omitted.

Input 1

English input: Bristol forecast desk, issued 05:40. Let rain mean measurable rainfall at Filton between 09:00 and 15:00 today; its complement is no measurable rainfall in that window. The probability of rain is 0.1.
Ainglish input: Bristol forecast desk, issued 05:40. Let rain mean measurable rainfall at Filton between 09:00 and 15:00 today; its complement is no measurable rainfall in that window. prob(rain)=0.1.
Condition: prob

Input 2

English input: Bristol forecast desk, issued 05:40. Let gust mean a gust above 40 kn at Avonmouth before midnight; its complement is no such gust. The probability of gust is 60%.
Ainglish input: Bristol forecast desk, issued 05:40. Let gust mean a gust above 40 kn at Avonmouth before midnight; its complement is no such gust. prob(gust)=60%.
Condition: prob

Input 3

English input: Bristol forecast desk, issued 05:40. Let frost mean a ground frost at Filton overnight; its complement is no ground frost. The probability odds in favour of frost are 3:7.
Ainglish input: Bristol forecast desk, issued 05:40. Let frost mean a ground frost at Filton overnight; its complement is no ground frost. odds-for(frost)=3:7.
Condition: odds-for

Recorded input digest: 7fcd9cdf4cb815936720edc609c3a24d3b96aabb83746cfb229c4ee226bd3b72

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: Current registered forms minus concise complete English carrying the same event, direction, scope, force and known quantities; no unqualified ambiguous substitute
Tested population: 32 prospective authored probability claims across all eight declared domains. Sixteen probability claims and eight of each odds form; eight rational edge/interior cases, including zero and certainty. Fixed 2:1:1 form mixture. Not random natural prose.
Unit tested: one complete scoped claim or operation, including identical surrounding context
How results combine: Declared weighted condition means within each tokenizer; maximum tokenizer mean (least-favourable) across cl100k_base and o200k_base. Bounds are tokenizer member span, not a population confidence interval.

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": -3.09375
    },
    {
        "model": "o200k_base",
        "value": -2.875
    }
]

Condition results

[
    {
        "id": "prob",
        "weight": 2,
        "share": 0.5,
        "value": -1.25,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "odds-for",
        "weight": 1,
        "share": 0.25,
        "value": -6,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "odds-against",
        "weight": 1,
        "share": 0.25,
        "value": -3,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 622beb84-3958-43f3-80d3-214899221c3d
Content 8ec887ed87f9c1f8fbc03f762ffa00ebd0aa1aa7436a9e90d9320a679a88d36f

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.