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 17:10 UTC

set-to / adjust-by — is the number the new value, or the size of the change?

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

3.9433 percentage points
Reported interval: -5.4759 to 13.8449.

The value is neutral or does not resolve the registered direction.

English comparison

Complete, careful English

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

Complete concise registered English, identical consequence context and common constraints; no bare ambiguous primary.

Reader exposure

Reader exposure not recorded as a structured label

Named instruments

mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m, gemma3-12b-opaque-choice-q4_k_m@q4_k_m

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 6 declared conditions

set-to:known, adjust-by:known, set-to:unknown, adjust-by:unknown, set-to:ordered, adjust-by:ordered

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

Awaiting independent settlement

An original reports one result. It does not confirm itself.

How often did each version lead to the right answer?

English comparison: 62.34%; 62.34%
Ainglish version: 66.28%; 66.28%

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: -5.4759 to 13.8449 percentage points.

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

Item-selection sensitivity warning. At least one reported reduced-item check changed direction or fell outside the full-item interval. Keep this warning with the score: the headline interval alone does not resolve sensitivity to which cases were included.

Real cases: 192 · Named readers: 2. 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.
Condition	Reported difference	Reported interval	English accuracy	Ainglish accuracy
`set-to:known`	-19.6	Not recorded	88.57%	68.97%
`adjust-by:known`	12.94	Not recorded	47.06%	60.00%
`set-to:unknown`	-1.37	Not recorded	78.79%	77.42%
`adjust-by:unknown`	-1.96	Not recorded	69.70%	67.74%
`set-to:ordered`	9.11	Not recorded	44.74%	53.85%
`adjust-by:ordered`	24.54	Not recorded	45.16%	69.70%

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.

No readable non-control input pairs are stored inline in this receipt. This does not mean the experiment used no inputs.

Open the declared external input artifact. The website has not fetched or verified it. Verify the declared digest recipe before relying on it: SDK item digests use canonical JSON, not the raw pretty-printed file bytes.

Recorded input digest: d287a544d2e07094333d8866669368ae7db4669f574bbbc580c3a38a8bc03648

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": 0.6233999999999999541699935434735380113124847412109375,
    "ainglish": 0.66279999999999994475530229465221054852008819580078125,
    "chance": 0.25
}

Reader or tokenizer results

[
    {
        "model": "mistral-small3.2-24b-opaque-choice-q4_k_m",
        "value": 8.82000000000000028421709430404007434844970703125,
        "precision": "q4_k_m"
    },
    {
        "model": "gemma3-12b-opaque-choice-q4_k_m",
        "value": -0.2316999999999999892974500426134909503161907196044921875,
        "precision": "q4_k_m"
    }
]

Condition results

[
    {
        "id": "set-to:known",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": -19.60000000000000142108547152020037174224853515625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.88570000000000004281019982954603619873523712158203125,
            "ainglish": 0.6896999999999999797495320308371447026729583740234375,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "adjust-by:known",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": 12.9399999999999995026200849679298698902130126953125,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.47060000000000001829647544582257978618144989013671875,
            "ainglish": 0.59999999999999997779553950749686919152736663818359375,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "set-to:unknown",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": -1.37000000000000010658141036401502788066864013671875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.787900000000000044764192352886311709880828857421875,
            "ainglish": 0.774199999999999999289457264239899814128875732421875,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "adjust-by:unknown",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": -1.95999999999999996447286321199499070644378662109375,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.69699999999999995292654375589336268603801727294921875,
            "ainglish": 0.677400000000000002131628207280300557613372802734375,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "set-to:ordered",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": 9.1099999999999994315658113919198513031005859375,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.4474000000000000198951966012828052043914794921875,
            "ainglish": 0.53849999999999997868371792719699442386627197265625,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "adjust-by:ordered",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": 24.53999999999999914734871708787977695465087890625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.45160000000000000142108547152020037174224853515625,
            "ainglish": 0.69699999999999995292654375589336268603801727294921875,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    }
]

Exact result and immutable specification Experiment history

Attempt c709a96c-4e12-472c-b017-8d410b4996d4
Content c9d8d897817d90b0072f1e84384422260838db189775d51844f65927fd06bdc3

Second result · 2026-09-07 07:03 UTC

set-to / adjust-by — is the number the new value, or the size of the change?

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

-4.7 percentage points
Reported interval: -11.3285 to 2.0699.

The value is neutral or does not resolve the registered direction.

English comparison

Complete, careful English

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

Complete concise registered English, identical consequence context and common constraints; no bare ambiguous primary.

Reader exposure

Reader exposure not recorded as a structured label

Named instruments

deepseek-v4-flash-nous@provider-served, llama-3.3-70b-nous@provider-served

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 6 declared conditions

set-to:known, adjust-by:known, set-to:unknown, adjust-by:unknown, set-to:ordered, adjust-by:ordered

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

No independent settlement voice

This can test whether an implementation repeats on reused inputs, but reused inputs cannot independently confirm the claim.

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

c9d8d897817d90b0072f1e84384422260838db189775d51844f65927fd06bdc3

How often did each version lead to the right answer?

English comparison: 87.48%; 87.48%
Ainglish version: 82.78%; 82.78%

Reported item-bootstrap interval: -11.3285 to 2.0699 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: 192 · Named readers: 2. 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.
Condition	Reported difference	Reported interval	English accuracy	Ainglish accuracy
`set-to:known`	-8.73	Not recorded	94.44%	85.71%
`adjust-by:known`	-13.69	Not recorded	87.88%	74.19%
`set-to:unknown`	-8.43	Not recorded	96.67%	88.24%
`adjust-by:unknown`	-5.56	Not recorded	75.00%	69.44%
`set-to:ordered`	5.86	Not recorded	90.91%	96.77%
`adjust-by:ordered`	2.35	Not recorded	80.00%	82.35%

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.

No readable non-control input pairs are stored inline in this receipt. This does not mean the experiment used no inputs.

Recorded input digest: d287a544d2e07094333d8866669368ae7db4669f574bbbc580c3a38a8bc03648

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

{
    "english": 0.874800000000000022026824808563105762004852294921875,
    "ainglish": 0.82779999999999998028243908265721984207630157470703125,
    "chance": 0.25
}

Reader or tokenizer results

[
    {
        "model": "deepseek-v4-flash-nous",
        "value": 0.52329999999999998738786644025822170078754425048828125,
        "precision": "provider-served"
    },
    {
        "model": "llama-3.3-70b-nous",
        "value": -10.31830000000000069348971010185778141021728515625,
        "precision": "provider-served"
    }
]

Condition results

[
    {
        "id": "set-to:known",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": -8.730000000000000426325641456060111522674560546875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.94440000000000001723066134218242950737476348876953125,
            "ainglish": 0.85709999999999997299937604111619293689727783203125,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "adjust-by:known",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": -13.6899999999999995026200849679298698902130126953125,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.8788000000000000255795384873636066913604736328125,
            "ainglish": 0.7419000000000000039079850466805510222911834716796875,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "set-to:unknown",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": -8.42999999999999971578290569595992565155029296875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.96670000000000000373034936274052597582340240478515625,
            "ainglish": 0.88239999999999996216359932077466510236263275146484375,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "adjust-by:unknown",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": -5.55999999999999960920149533194489777088165283203125,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.75,
            "ainglish": 0.69440000000000001723066134218242950737476348876953125,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "set-to:ordered",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": 5.86000000000000031974423109204508364200592041015625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.909100000000000019184653865522705018520355224609375,
            "ainglish": 0.9677000000000000046185277824406512081623077392578125,
            "chance": 0.25
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "adjust-by:ordered",
        "weight": 1,
        "share": 0.1666666666666666574148081281236954964697360992431640625,
        "value": 2.350000000000000088817841970012523233890533447265625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.8000000000000000444089209850062616169452667236328125,
            "ainglish": 0.82350000000000000976996261670137755572795867919921875,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    }
]

Exact result and immutable specification Experiment history

Attempt ea1a856a-cd67-44a2-9fb2-cbd4bfe8929a
Content 2421c651d3beda762841c10b0bfc486e5bc43393172ef4472cd374f234ce20c7

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.