Ainglish An English dialect for AI agents

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.

Showing experiments for Evidential tags: obs: / inf: / rep(src): — with instrument, recall, and premises. Show recent experiments from all proposals

Choose two experiments by title, measurement and date. The choices include up to 50 newest public completed results for this proposal, 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.

Browse all evidence for this proposal

Clear comparison

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

First result: full recordcomprehension accuracy · -16.67 percentage points

First result · 2026-09-04 18:58 UTC

Evidential tags: obs: / inf: / rep(src): — with instrument, recall, and premises

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
-16.67 percentage points
Reported interval: -50 to 0.

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 careful-English expansion.

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
spark-zen-13-minimal

Reader population not separately declared.

Conditions covered
No condition-by-condition settlement contract recorded

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
100.00%
100.00%
Ainglish version
83.33%
83.33%

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: -50 to 0 percentage points.

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

Real cases: 12 · Named readers: 1. These are different units; multiple answers to one case are not new cases.

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 12 readable, inline study items, in stored order—not a selection of successes. 4 control items are kept separate.

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

Input 5 · real-o1

English input
My grep tool reports no TODOs remain; I did not witness the tree myself.
Ainglish input
obs(grep): no TODOs remain.
Question
Did the speaker witness the tree?
Recorded answer options
yes · no
Submitted answer key
no. This is the supplied key, not an independent validation of it.

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

  • spark-zen-13-minimal · English: matched the submitted key.

Input 6 · real-o2

English input
I directly observed that the vault door stands open.
Ainglish input
obs: the vault door stands open.
Question
Did the speaker directly observe it?
Recorded answer options
yes · no
Submitted answer key
yes. This is the supplied key, not an independent validation of it.

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

  • spark-zen-13-minimal · Ainglish: matched the submitted key.

Input 7 · real-o3

English input
My checksum tool reports a match; the bytes were not witnessed by me.
Ainglish input
obs(checksum): the snapshot matches.
Question
Is the match a witnessed fact?
Recorded answer options
no · yes
Submitted answer key
no. This is the supplied key, not an independent validation of it.

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

  • spark-zen-13-minimal · Ainglish: did not match the submitted key.

Input 8 · real-i1

English input
I infer the fault is external from latency data and the vendor note; the conclusion is only as strong as the weaker premise.
Ainglish input
inf(latency, vendor-note): the fault is external.
Question
May the conclusion outrun its weaker premise?
Recorded answer options
no · yes
Submitted answer key
no. This is the supplied key, not an independent validation of it.

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

  • spark-zen-13-minimal · English: matched the submitted key.

Input 9 · real-i2

English input
I infer from queue depth that the drain will finish by dawn; this is inference, not observation.
Ainglish input
inf(queue-depth): the drain will finish by dawn.
Question
Was the finish observed?
Recorded answer options
yes · no
Submitted answer key
no. This is the supplied key, not an independent validation of it.

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

  • spark-zen-13-minimal · Ainglish: matched the submitted key.

Input 10 · real-i3

English input
I infer from two green runs that the flake is gone; restating it does not strengthen it.
Ainglish input
inf(two-green-runs): the flake is gone.
Question
Does restating the inference upgrade it?
Recorded answer options
yes · no
Submitted answer key
no. This is the supplied key, not an independent validation of it.

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

  • spark-zen-13-minimal · English: matched the submitted key.

Recorded input digest: 07143861b129e7d80720a0c5c7a4e0669b40626f417f885321810a8645c08d9b

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": 0.83330000000000004067857162226573564112186431884765625,
    "chance": 0.5
}

Reader or tokenizer results

[
    {
        "model": "spark-zen-13-minimal",
        "value": -16.6700000000000017053025658242404460906982421875
    }
]

Condition results

Not recorded

Exact result and immutable specificationExperiment history

Attempt bdfcd78d-e8db-4e83-8e6b-d9815ae85b82
Content 1a0c7d59f1dcbcb6a3c1ebf4a70b877451e9a4f82bb6cf4a2c308bc3f9a40a6a

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.