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 percentage points, not bare percent — a change to a percentage is stated in points, endpoints attached when known. 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 · 50 percentage points

First result · 2026-08-30 14:25 UTC

percentage points, not bare percent — a change to a percentage is stated in points, endpoints attached when known

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
50 percentage points
Reported interval: 0 to 85.7143.

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

English comparison
English comparison not recorded as a structured label

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

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
deepseek-v4-flash-0731@bf16

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
Agrees with the named original

This eligible row adds one agreement to the named original’s settlement tally.

This result checks a named original, not every experiment on the proposal. Read its target original

Compare with the exact target attempt

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 identity4274686df67d83ec8fb12f9468142140564436fb898e65941a8e8ef6c468b559

How often did each version lead to the right answer?

English comparison
0.00%
0.00%
Ainglish version
50.00%
50.00%

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 interval (method not identified here): 0 to 85.7143 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: 8 · 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 8 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 1 · ds-pp-r1

English input
The task success rate changed in the new build.
Ainglish input
The task success rate rose 7 percentage points in the new build.
Question
Which kind of percentage change did the writer explicitly declare?
Recorded answer options
cannot tell from the sentence · additive percentage-point change · relative-percent change
Submitted answer key
additive percentage-point change. This is the supplied key, not an independent validation of it.

No per-item reader answers are stored alongside this inline example.

Input 2 · ds-pp-r2

English input
The task success rate changed in the new build.
Ainglish input
The task success rate rose 7% in the new build.
Question
Which kind of percentage change did the writer explicitly declare?
Recorded answer options
cannot tell from the sentence · additive percentage-point change · relative-percent change
Submitted answer key
relative-percent change. This is the supplied key, not an independent validation of it.

No per-item reader answers are stored alongside this inline example.

Input 3 · ds-pp-r3

English input
The request latency changed after the change.
Ainglish input
The request latency rose 3 percentage points after the change.
Question
Which kind of percentage change did the writer explicitly declare?
Recorded answer options
cannot tell from the sentence · additive percentage-point change · relative-percent change
Submitted answer key
additive percentage-point change. This is the supplied key, not an independent validation of it.

No per-item reader answers are stored alongside this inline example.

Input 4 · ds-pp-r4

English input
The request latency changed after the change.
Ainglish input
The request latency rose 3% after the change.
Question
Which kind of percentage change did the writer explicitly declare?
Recorded answer options
cannot tell from the sentence · additive percentage-point change · relative-percent change
Submitted answer key
relative-percent change. This is the supplied key, not an independent validation of it.

No per-item reader answers are stored alongside this inline example.

Input 5 · ds-pp-r5

English input
The activation rate changed for the cohort.
Ainglish input
The activation rate rose 9 percentage points for the cohort.
Question
Which kind of percentage change did the writer explicitly declare?
Recorded answer options
cannot tell from the sentence · additive percentage-point change · relative-percent change
Submitted answer key
additive percentage-point change. This is the supplied key, not an independent validation of it.

No per-item reader answers are stored alongside this inline example.

Input 6 · ds-pp-r6

English input
The activation rate changed for the cohort.
Ainglish input
The activation rate rose 9% for the cohort.
Question
Which kind of percentage change did the writer explicitly declare?
Recorded answer options
cannot tell from the sentence · additive percentage-point change · relative-percent change
Submitted answer key
relative-percent change. This is the supplied key, not an independent validation of it.

No per-item reader answers are stored alongside this inline example.

Recorded input digest: f4498a250214cb73012b48cddffeba86962bba20ad85b0e0d5f9084b612e4fcc

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,
    "ainglish": 0.5,
    "chance": 0.333299999999999985167420391007908619940280914306640625
}

Reader or tokenizer results

[
    {
        "model": "deepseek-v4-flash-0731",
        "value": 50,
        "precision": "bf16"
    }
]

Condition results

Not recorded

Exact result and immutable specificationExperiment history

Attempt 61ca8d8c-c048-4fff-b7e2-c07ef6160c9b
Content 239b4ea1a98dc8067ea7915b03fafb615d94fecf3fea086db8260f7eecdfac81

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.