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.

Choose experiments to compareSearch 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

One result selected. Choose a second to complete the comparison.

First result: full recordcomprehension accuracy · -2.0767 percentage points

First result · 2026-09-04 08:43 UTC

by-construction / by-rule / in-practice — mark whether a standing property is enforced, required, or merely observed

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
-2.0767 percentage points
Reported interval: -18.4572 to 13.3387.

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 same-claim mapping.

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
Sat-Qwen7-Q4, Sat-Gemma12-Q4, Sat-Mistral24-Q4

Reader population not separately declared.

Conditions covered
Separate outcomes retained for all 3 declared conditions

b, r, i

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
27.84%
27.84%
Ainglish version
25.77%
25.77%

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: -18.4572 to 13.3387 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.

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: 36 · Named readers: 3. 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
b5.26 Not recorded 0.00%5.26%
r-3.75 Not recorded 60.00%56.25%
i-7.74 Not recorded 23.53%15.79%

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 36 readable, inline study items, in stored order—not a selection of successes. 6 control items are kept separate.

Each result has its own input pages. Positions across the two studies do not imply matched cases.

Input 1 · b01

English input
Export bundles are immutable; the mechanism makes any exception require a change.
Ainglish input
Export bundles are immutable by-construction.
Question
An export bundle changes, system same. Then? A=false B=breach C=new D=valid E=?
Recorded answer options
A · B · C · D · E
Submitted answer key
A. This is the supplied key, not an independent validation of it.
Condition
b

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • Sat-Gemma12-Q4 · English: did not match the submitted key.
  • Sat-Mistral24-Q4 · English: did not match the submitted key.
  • Sat-Qwen7-Q4 · English: did not match the submitted key.

Input 2 · b02

English input
Jobs have exactly one run ID; the mechanism makes any exception require a change.
Ainglish input
Jobs have exactly one run ID by-construction.
Question
A job has two run IDs, system same. Then? A=false B=breach C=new D=valid E=?
Recorded answer options
E · A · B · C · D
Submitted answer key
A. This is the supplied key, not an independent validation of it.
Condition
b

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • Sat-Gemma12-Q4 · English: did not match the submitted key.
  • Sat-Mistral24-Q4 · English: did not match the submitted key.
  • Sat-Qwen7-Q4 · Ainglish: did not match the submitted key.

Input 3 · b03

English input
Transactions fully commit or roll back; the mechanism makes any exception require a change.
Ainglish input
Transactions fully commit or roll back by-construction.
Question
A transaction half-commits, system same. Then? A=false B=breach C=new D=valid E=?
Recorded answer options
D · E · A · B · C
Submitted answer key
A. This is the supplied key, not an independent validation of it.
Condition
b

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • Sat-Gemma12-Q4 · English: did not match the submitted key.
  • Sat-Mistral24-Q4 · Ainglish: did not match the submitted key.
  • Sat-Qwen7-Q4 · English: did not match the submitted key.

Input 4 · b04

English input
Audit rows retain their creation time; the mechanism makes any exception require a change.
Ainglish input
Audit rows retain their creation time by-construction.
Question
An audit row loses its creation time, system same. Then? A=false B=breach C=new D=valid E=?
Recorded answer options
C · D · E · A · B
Submitted answer key
A. This is the supplied key, not an independent validation of it.
Condition
b

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • Sat-Gemma12-Q4 · English: did not match the submitted key.
  • Sat-Mistral24-Q4 · Ainglish: matched the submitted key.
  • Sat-Qwen7-Q4 · Ainglish: did not match the submitted key.

Input 5 · b05

English input
Archive checksums match their bytes; the mechanism makes any exception require a change.
Ainglish input
Archive checksums match their bytes by-construction.
Question
An archive checksum mismatches its bytes, system same. Then? A=false B=breach C=new D=valid E=?
Recorded answer options
B · C · D · E · A
Submitted answer key
A. This is the supplied key, not an independent validation of it.
Condition
b

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • Sat-Gemma12-Q4 · Ainglish: did not match the submitted key.
  • Sat-Mistral24-Q4 · English: did not match the submitted key.
  • Sat-Qwen7-Q4 · English: did not match the submitted key.

Input 6 · b06

English input
Schema records have one owner; the mechanism makes any exception require a change.
Ainglish input
Schema records have one owner by-construction.
Question
A schema record has no owner, system same. Then? A=false B=breach C=new D=valid E=?
Recorded answer options
A · B · C · D · E
Submitted answer key
A. This is the supplied key, not an independent validation of it.
Condition
b

Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.

  • Sat-Gemma12-Q4 · Ainglish: did not match the submitted key.
  • Sat-Mistral24-Q4 · Ainglish: did not match the submitted key.
  • Sat-Qwen7-Q4 · English: did not match the submitted key.

Recorded input digest: 44aab8b9596cbe0a4c284f17a558b2bda9a9988fa8ecdfa6210dacab3968122c

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": 0.278399999999999980815346134477294981479644775390625,
    "ainglish": 0.257699999999999984634513339187833480536937713623046875,
    "chance": 0.200000000000000011102230246251565404236316680908203125
}

Reader or tokenizer results

[
    {
        "model": "Sat-Qwen7-Q4",
        "value": -8.410000000000000142108547152020037174224853515625
    },
    {
        "model": "Sat-Gemma12-Q4",
        "value": 5.713300000000000267164068645797669887542724609375
    },
    {
        "model": "Sat-Mistral24-Q4",
        "value": -3.966699999999999892708046900224871933460235595703125
    }
]

Condition results

[
    {
        "id": "b",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": 5.2599999999999997868371792719699442386627197265625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0,
            "ainglish": 0.052600000000000000921485110438879928551614284515380859375,
            "chance": 0.200000000000000011102230246251565404236316680908203125
        },
        "resolution_bound": "floor"
    },
    {
        "id": "r",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -3.75,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.59999999999999997779553950749686919152736663818359375,
            "ainglish": 0.5625,
            "chance": 0.200000000000000011102230246251565404236316680908203125
        },
        "resolution_bound": "resolvable"
    },
    {
        "id": "i",
        "weight": 1,
        "share": 0.333333333333333314829616256247390992939472198486328125,
        "value": -7.7400000000000002131628207280300557613372802734375,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 0.235300000000000009148237722911289893090724945068359375,
            "ainglish": 0.1579000000000000125677246387567720375955104827880859375,
            "chance": 0.200000000000000011102230246251565404236316680908203125
        },
        "resolution_bound": "floor"
    }
]

Exact result and immutable specificationExperiment history

Attempt bf6a6e1c-f6c0-458d-bf8b-0cf33ef80b95
Content 40702354347269f4230a1e2964522d8da3081fc7a188229204a00b833dba0d0e

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.