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?repeat-event / restore-state — did ‘again’ repeat the action, or only bring the result back?2026-08-31 16:49 UTCrepeat-event / restore-state — did ‘again’ repeat the action, or only bring the result back?2026-09-12 15:28 UTC
What was measured?comprehension accuracyHow does the wording change correct answers from the declared reader panel?comprehension accuracyHow does the wording change correct answers from the declared reader panel?
What was the result?-5.2637 percentage pointsReported interval: -10.6259 to -0.1402Not yet counting in evidence decisions-4.5038 percentage pointsReported interval: -8.3333 to -1.4706Counts in current evidence decisions
Compared with what?Complete, careful EnglishReader exposure not recorded as a structured labelComplete, careful EnglishReader exposure not recorded as a structured label
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
comprehension_accuracy_delta
Second result
comprehension_accuracy_delta
English comparison declarations · Same recorded value
First result
[
    "complete-careful-english-v1"
]
Second result
[
    "complete-careful-english-v1"
]
Tested population · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Unit tested · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Named instruments (including order) · Recorded values differ
First result
[
    "deepseek/deepseek-v4-flash@provider-served"
]
Second result
[
    "deepseek-flash"
]
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 · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
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": "re:aff",
        "weight": 1
    },
    {
        "id": "re:neg",
        "weight": 1
    },
    {
        "id": "re:pq",
        "weight": 1
    },
    {
        "id": "re:dir",
        "weight": 1
    },
    {
        "id": "rs:aff",
        "weight": 1
    },
    {
        "id": "rs:neg",
        "weight": 1
    },
    {
        "id": "rs:pq",
        "weight": 1
    },
    {
        "id": "rs:dir",
        "weight": 1
    }
]
Second result
[
    {
        "id": "re:aff",
        "weight": 1
    },
    {
        "id": "re:neg",
        "weight": 1
    },
    {
        "id": "re:pq",
        "weight": 1
    },
    {
        "id": "re:dir",
        "weight": 1
    },
    {
        "id": "rs:aff",
        "weight": 1
    },
    {
        "id": "rs:neg",
        "weight": 1
    },
    {
        "id": "rs:pq",
        "weight": 1
    },
    {
        "id": "rs:dir",
        "weight": 1
    }
]
First result: full recordcomprehension accuracy · -5.2637 percentage points

First result · 2026-08-31 16:49 UTC

repeat-event / restore-state — did ‘again’ repeat the action, or only bring the result back?

Not yet counting in evidence decisions. This row remains available for assessment, but does not currently carry a counting evidence result.

What was measured
comprehension accuracy · comprehension_accuracy_delta
How does the wording change correct answers from the declared reader panel?
Reported result
-5.2637 percentage points
Reported interval: -10.6259 to -0.1402.

The value falls on the registered harmful side of this metric’s neutral point.

English comparison
Complete, careful English

Declared by the submitter; not a certification of equivalent information.

The careful-English arm states the scoped clause plus the marker's full background contribution as declared by the mapping (earlier matching event with stated participants, or earlier interval of the result state, agent unspecified). The marked arm varies only the marker prefix. Directive repeat-event cells prepend one shared context sentence to both arms and probe fit-against-context.

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
deepseek/deepseek-v4-flash@provider-served

Reader population not separately declared.

Conditions covered
Separate outcomes retained for all 8 declared conditions

re:aff, re:neg, re:pq, re:dir, rs:aff, rs:neg, rs:pq, rs:dir

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.

How often did each version lead to the right answer?

English comparison
97.92%
97.92%
Ainglish version
92.65%
92.65%

Reported real-item accuracy, not the separate calibration score. Both bars use the same 0–100% scale. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.

Reported item-bootstrap interval: -10.6259 to -0.1402 percentage points.

This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.

At least one declared condition is resolution-limited. The overall interval does not settle every condition.

Real cases: 256 · Named readers: 1. These are different units; multiple answers to one case are not new cases.

Does the overall result hide differences between conditions?

Every stored condition, without new pooling. Differences and intervals use percentage points. Condition names come from the frozen experiment.
ConditionReported differenceReported intervalEnglish accuracyAinglish accuracy
re:aff0 Not recorded 100.00%100.00%
re:neg0 Not recorded 100.00%100.00%
re:pq0 Not recorded 100.00%100.00%
re:dir-35.71 Not recorded 100.00%64.29%
rs:aff-7.69 Not recorded 100.00%92.31%
rs:neg-15.38 Not recorded 100.00%84.62%
rs:pq0 Not recorded 100.00%100.00%
rs:dir16.67 Not recorded 83.33%100.00%

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.

An external input location was declared, but it is not a safe HTTPS link this view can display. Inspect the retained specification; the missing link does not establish that there were no inputs.

No readable study input pairs are stored inline in this receipt. This does not mean the experiment used none.

Recorded input digest: 00b095dcdead7a457ef254879b16063a0109c38228f246f1a40c22117d03f1ff

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

No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.

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

{
    "english": 0.97919999999999995932142837773426435887813568115234375,
    "ainglish": 0.92649999999999999023003738329862244427204132080078125,
    "chance": 0.291700000000000014832579608992091380059719085693359375
}

Reader or tokenizer results

[
    {
        "model": "deepseek\/deepseek-v4-flash",
        "value": -5.263700000000000045474735088646411895751953125,
        "precision": "provider-served"
    }
]

Condition results

[
    {
        "id": "re:aff",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "re:neg",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "re:pq",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "re:dir",
        "weight": 1,
        "share": 0.125,
        "value": -35.71000000000000085265128291212022304534912109375,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.64290000000000002700062395888380706310272216796875,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "rs:aff",
        "weight": 1,
        "share": 0.125,
        "value": -7.69000000000000039079850466805510222911834716796875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.9231000000000000316191517413244582712650299072265625,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "rs:neg",
        "weight": 1,
        "share": 0.125,
        "value": -15.3800000000000007815970093361102044582366943359375,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.84619999999999995221600102013326250016689300537109375,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "rs:pq",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "rs:dir",
        "weight": 1,
        "share": 0.125,
        "value": 16.6700000000000017053025658242404460906982421875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.83330000000000004067857162226573564112186431884765625,
            "ainglish": 1,
            "chance": 0.291700000000000014832579608992091380059719085693359375
        },
        "resolution_bound": "resolvable"
    }
]

Exact result and immutable specificationExperiment history

Attempt 26f2f557-a8e7-417f-9cff-8afd7f385620
Content 6402298c595e40c70709bfb1aa4c16a24aed9f0effd939fad17b336a91eae05c

Second result: full recordcomprehension accuracy · -4.5038 percentage points

Second result · 2026-09-12 15:28 UTC

repeat-event / restore-state — did ‘again’ repeat the action, or only bring the result back?

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
comprehension accuracy · comprehension_accuracy_delta
How does the wording change correct answers from the declared reader panel?
Reported result
-4.5038 percentage points
Reported interval: -8.3333 to -1.4706.

The value falls on the registered harmful side of this metric’s neutral point.

English comparison
Complete, careful English

Declared by the submitter; not a certification of equivalent information.

The careful-English arm states the scoped clause plus the marker's full background contribution as declared by the mapping (earlier matching event with stated participants, or earlier interval of the result state, agent unspecified). The marked arm varies only the marker prefix. Directive repeat-event cells prepend one shared context sentence to both arms and probe fit-against-context.

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
deepseek-flash

Reader population not separately declared.

Conditions covered
Separate outcomes retained for all 8 declared conditions

re:aff, re:neg, re:pq, re:dir, rs:aff, rs:neg, rs:pq, rs:dir

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.

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?

Complete-pair freshness is not available for this receipt.

Separate-arm overlap is unavailable or has not been computed. This does not mean zero reuse.

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 identity6402298c595e40c70709bfb1aa4c16a24aed9f0effd939fad17b336a91eae05c

How often did each version lead to the right answer?

English comparison
100.00%
100.00%
Ainglish version
95.50%
95.50%

Reported real-item accuracy, not the separate calibration score. Both bars use the same 0–100% scale. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.

Reported item-bootstrap interval: -8.3333 to -1.4706 percentage points.

This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.

At least one declared condition is resolution-limited. The overall interval does not settle every condition.

Real cases: 256 · Named readers: 1. These are different units; multiple answers to one case are not new cases.

Does the overall result hide differences between conditions?

Every stored condition, without new pooling. Differences and intervals use percentage points. Condition names come from the frozen experiment.
ConditionReported differenceReported intervalEnglish accuracyAinglish accuracy
re:aff0 Not recorded 100.00%100.00%
re:neg0 Not recorded 100.00%100.00%
re:pq0 Not recorded 100.00%100.00%
re:dir-12.5 Not recorded 100.00%87.50%
rs:aff-5.88 Not recorded 100.00%94.12%
rs:neg-17.65 Not recorded 100.00%82.35%
rs:pq0 Not recorded 100.00%100.00%
rs:dir0 Not recorded 100.00%100.00%

A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.

Inspect externally stored 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.

The input material is linked externally. The number of study items and controls in that file has not been checked by this website. “External file” does not mean zero inputs.

Open the declared external input artifact. This is an unverified external link, not a hosted or inspected copy.

Declared input digest: c873562d7615bef24d73f29506c44446ac59f27130ed2a62ee4ed827f98bf80a. A recorded digest alone does not establish that the linked file matches it.

The website does not fetch the file. Verify the declared digest recipe before relying on it: SDK item digests use canonical JSON of the item array, not the raw pretty-printed file bytes.

No readable study input pairs are stored inline in this receipt. This does not mean the experiment used none.

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

No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.

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

{
    "english": 1,
    "ainglish": 0.95499999999999996003197111349436454474925994873046875,
    "chance": 0.25
}

Reader or tokenizer results

[
    {
        "model": "deepseek-flash",
        "value": -4.5038000000000000255795384873636066913604736328125
    }
]

Condition results

[
    {
        "id": "re:aff",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.25
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "re:neg",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.25
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "re:pq",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.25
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "re:dir",
        "weight": 1,
        "share": 0.125,
        "value": -12.5,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.875,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "rs:aff",
        "weight": 1,
        "share": 0.125,
        "value": -5.87999999999999989341858963598497211933135986328125,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.9412000000000000365929508916451595723628997802734375,
            "chance": 0.25
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "rs:neg",
        "weight": 1,
        "share": 0.125,
        "value": -17.64999999999999857891452847979962825775146484375,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.82350000000000000976996261670137755572795867919921875,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "rs:pq",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.25
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "rs:dir",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 1,
            "chance": 0.25
        },
        "resolution_bound": "ceiling"
    }
]

Exact result and immutable specificationExperiment history

Attempt c9d746f7-2117-4688-b4e3-47bd76982ebc
Content 3e28fafdfb6c04ab0f02b123b1be2bd8d5b540bbd4cb716f684645390cc8287e

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.