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.

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

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) · Same recorded value
First result
[
    "mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m",
    "gemma3-12b-opaque-choice-q4_k_m@q4_k_m"
]
Second result
[
    "mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m",
    "gemma3-12b-opaque-choice-q4_k_m@q4_k_m"
]
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": "utc",
        "weight": 1
    },
    {
        "id": "civil",
        "weight": 1
    },
    {
        "id": "missing-date-utc",
        "weight": 1
    },
    {
        "id": "missing-date-civil",
        "weight": 1
    },
    {
        "id": "fold",
        "weight": 1
    },
    {
        "id": "gap",
        "weight": 1
    },
    {
        "id": "recurring-civil",
        "weight": 1
    },
    {
        "id": "recurring-utc",
        "weight": 1
    }
]
Second result
[
    {
        "id": "utc",
        "weight": 1
    },
    {
        "id": "civil",
        "weight": 1
    },
    {
        "id": "missing-date-utc",
        "weight": 1
    },
    {
        "id": "missing-date-civil",
        "weight": 1
    },
    {
        "id": "fold",
        "weight": 1
    },
    {
        "id": "gap",
        "weight": 1
    },
    {
        "id": "recurring-civil",
        "weight": 1
    },
    {
        "id": "recurring-utc",
        "weight": 1
    }
]

First result · 2026-09-05 22:03 UTC

14:00Z / 09:00@Europe/London — which instant does a bare clock time name?

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
10.7225 percentage points
Reported interval: 0.6638 to 20.6696.

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

English comparison
Complete, careful English

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

Identical contextual facts in both arms; direct complete English for the question asked. Scope and omitted dimensions are explicit in DESIGN.md.

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 8 declared conditions

utc, civil, missing-date-utc, missing-date-civil, fold, gap, recurring-civil, recurring-utc

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
54.73%
54.73%
Ainglish version
65.45%
65.45%

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: 0.6638 to 20.6696 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: 128 · 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.
ConditionReported differenceReported intervalEnglish accuracyAinglish accuracy
utc0 Not recorded 100.00%100.00%
civil58.04 Not recorded 35.29%93.33%
missing-date-utc6.93 Not recorded 45.45%52.38%
missing-date-civil-6.27 Not recorded 52.94%46.67%
fold8.33 Not recorded 41.67%50.00%
gap18.75 Not recorded 0.00%18.75%
recurring-civil0 Not recorded 62.50%62.50%
recurring-utc0 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: f0a6b2c703ead4d9ba2a9c93106a2c9ddec6ee558964877c5084784808aadf4c. 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": 0.54730000000000000870414851306122727692127227783203125,
    "ainglish": 0.65449999999999997069011214989586733281612396240234375,
    "chance": 0.25
}

Reader or tokenizer results

[
    {
        "model": "mistral-small3.2-24b-opaque-choice-q4_k_m",
        "value": 10.208800000000000096633812063373625278472900390625,
        "precision": "q4_k_m"
    },
    {
        "model": "gemma3-12b-opaque-choice-q4_k_m",
        "value": 13.8388000000000008782308213994838297367095947265625,
        "precision": "q4_k_m"
    }
]

Condition results

[
    {
        "id": "utc",
        "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": "civil",
        "weight": 1,
        "share": 0.125,
        "value": 58.03999999999999914734871708787977695465087890625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.3528999999999999914734871708787977695465087890625,
            "ainglish": 0.93330000000000001847411112976260483264923095703125,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "missing-date-utc",
        "weight": 1,
        "share": 0.125,
        "value": 6.92999999999999971578290569595992565155029296875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.45450000000000001509903313490212894976139068603515625,
            "ainglish": 0.523800000000000043343106881366111338138580322265625,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "missing-date-civil",
        "weight": 1,
        "share": 0.125,
        "value": -6.269999999999999573674358543939888477325439453125,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.52939999999999998170352455417742021381855010986328125,
            "ainglish": 0.46670000000000000373034936274052597582340240478515625,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "fold",
        "weight": 1,
        "share": 0.125,
        "value": 8.3300000000000000710542735760100185871124267578125,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.416700000000000014832579608992091380059719085693359375,
            "ainglish": 0.5,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "gap",
        "weight": 1,
        "share": 0.125,
        "value": 18.75,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0,
            "ainglish": 0.1875,
            "chance": 0.25
        },
        "resolution_bound": "floor"
    },
    {
        "id": "recurring-civil",
        "weight": 1,
        "share": 0.125,
        "value": 0,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.625,
            "ainglish": 0.625,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "recurring-utc",
        "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 40abfceb-7ae6-4fc7-b70f-90b2be7a80b1
Content 3940048334a3bd6861c7cbc1ec1bb7372f2a3de1d556db89a1ebfe9ec9f7b758

Second result · 2026-09-08 10:07 UTC

14:00Z / 09:00@Europe/London — which instant does a bare clock time name?

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
19.4013 percentage points
Reported interval: 10.6111 to 28.838.

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

English comparison
Complete, careful English

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

Identical contextual facts in both arms; direct complete English for the question asked. Scope and omitted dimensions are explicit in DESIGN.md.

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 8 declared conditions

utc, civil, missing-date-utc, missing-date-civil, fold, gap, recurring-civil, recurring-utc

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.

Declared target content identity3940048334a3bd6861c7cbc1ec1bb7372f2a3de1d556db89a1ebfe9ec9f7b758

How often did each version lead to the right answer?

English comparison
54.20%
54.20%
Ainglish version
73.60%
73.60%

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: 10.6111 to 28.838 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: 128 · 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.
ConditionReported differenceReported intervalEnglish accuracyAinglish accuracy
utc0 Not recorded 100.00%100.00%
civil57.89 Not recorded 42.11%100.00%
missing-date-utc18.25 Not recorded 42.86%61.11%
missing-date-civil6.93 Not recorded 45.45%52.38%
fold1.58 Not recorded 55.56%57.14%
gap13.42 Not recorded 4.76%18.18%
recurring-civil57.14 Not recorded 42.86%100.00%
recurring-utc0 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: 4067713e1c99f75b78e769530787f3f8314485aa63a9d39cb9b72de4d7e26974. 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": 0.5420000000000000373034936274052597582340240478515625,
    "ainglish": 0.7359999999999999875655021241982467472553253173828125,
    "chance": 0.25
}

Reader or tokenizer results

[
    {
        "model": "mistral-small3.2-24b-opaque-choice-q4_k_m",
        "value": 16.747499999999998721023075631819665431976318359375,
        "precision": "q4_k_m"
    },
    {
        "model": "gemma3-12b-opaque-choice-q4_k_m",
        "value": 5.19629999999999991899812812334857881069183349609375,
        "precision": "q4_k_m"
    }
]

Condition results

[
    {
        "id": "utc",
        "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": "civil",
        "weight": 1,
        "share": 0.125,
        "value": 57.8900000000000005684341886080801486968994140625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.421099999999999974331643670666380785405635833740234375,
            "ainglish": 1,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "missing-date-utc",
        "weight": 1,
        "share": 0.125,
        "value": 18.25,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.42859999999999998099298181841732002794742584228515625,
            "ainglish": 0.611099999999999976552089719916693866252899169921875,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "missing-date-civil",
        "weight": 1,
        "share": 0.125,
        "value": 6.92999999999999971578290569595992565155029296875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.45450000000000001509903313490212894976139068603515625,
            "ainglish": 0.523800000000000043343106881366111338138580322265625,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "fold",
        "weight": 1,
        "share": 0.125,
        "value": 1.5800000000000000710542735760100185871124267578125,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.55559999999999998276933865781757049262523651123046875,
            "ainglish": 0.57140000000000001900701818158267997205257415771484375,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "gap",
        "weight": 1,
        "share": 0.125,
        "value": 13.4199999999999999289457264239899814128875732421875,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.0476000000000000034194869158454821445047855377197265625,
            "ainglish": 0.1817999999999999893862678845835034735500812530517578125,
            "chance": 0.25
        },
        "resolution_bound": "floor"
    },
    {
        "id": "recurring-civil",
        "weight": 1,
        "share": 0.125,
        "value": 57.1400000000000005684341886080801486968994140625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.42859999999999998099298181841732002794742584228515625,
            "ainglish": 1,
            "chance": 0.25
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "recurring-utc",
        "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 a96a6eea-c747-4b23-84ca-82225ce616f2
Content 158383ee7346428911d758236b395697ee0afc9ee74db2b9f692b97cb83a72a1

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.