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.

Change the selected experimentsSearch 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

Compare the essentials

Read each question across both results. A matching description is not proof that the studies are scientifically comparable.

QuestionFirst resultSecond result
Which proposal?all-or-nothing / keep-successes — say what survives when part of a batch fails2026-09-03 08:37 UTCall-or-nothing / keep-successes — say what survives when part of a batch fails2026-09-09 19:15 UTC
What was measured?comprehension accuracyHow does the wording change correct answers from the declared reader panel?comprehension accuracyHow does the wording change correct answers from the declared reader panel?
What was the result?-25 percentage pointsReported interval: -61.5385 to 18.75Counts in current evidence decisions16.67 percentage pointsReported interval: -25 to 53.3333Counts in current evidence decisions
Compared with what?Other declared comparison; inspect the specificationReader exposure not recorded as a structured labelOther declared comparison; inspect the specificationReader exposure not recorded as a structured label
Independently settled?Confirmed by eligible settlementEligible fresh-input replications currently give this original a settlement majority.Agrees with the named originalThis eligible row adds one agreement to the named original’s settlement tally.

Inspect first resultInspect second result

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
[
    "balanced-bare-and-complete-careful-english-v1"
]
Second result
[
    "balanced-bare-and-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
[
    "falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m",
    "olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m"
]
Second result
[
    "falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m",
    "olmo2-13b-qualification-v7-cd836509a1a0@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) · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
First result: full recordcomprehension accuracy · -25 percentage points

First result · 2026-09-03 08:37 UTC

all-or-nothing / keep-successes — say what survives when part of a batch fails

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
-25 percentage points
Reported interval: -61.5385 to 18.75.

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

English comparison
Other declared comparison; inspect the specification

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

Within each action-set/outcome cell, one English comparator leaves terminal retention unstated and one states the complete registered mapping.

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m, olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m

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
Confirmed by eligible settlement

Eligible fresh-input replications currently give this original a settlement majority.

How often did each version lead to the right answer?

English comparison
41.67%
41.67%
Ainglish version
16.67%
16.67%

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: -61.5385 to 18.75 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: 12 · Named readers: 2. 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. 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 · r9-ret-01

English input
Perform this bounded action set: Grant Atlas access; grant Beacon access; grant Cygnus access. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Ainglish input
Grant Atlas access; grant Beacon access; grant Cygnus access, all-or-nothing. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Question
At terminal handoff after the stated outcomes: (1) which successful member effects remain authoritative; (2) what is the action-set result?
Recorded answer options
neither / failed with no retained effects · both / full success · first only / partial result · neither / full success · unknown / unknown · both / partial result
Submitted answer key
neither / failed with no retained effects. 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.

  • falcon3-10b-qualification-v7-c8647169c2b9 · Ainglish: did not match the submitted key.
  • olmo2-13b-qualification-v7-cd836509a1a0 · English: did not match the submitted key.

Input 2 · r9-ret-02

English input
Perform this bounded action set: Grant Atlas access; grant Beacon access; grant Cygnus access. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Ainglish input
Grant Atlas access; grant Beacon access; grant Cygnus access, keep-successes. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Question
At terminal handoff after the stated outcomes: (1) which successful member effects remain authoritative; (2) what is the action-set result?
Recorded answer options
both / full success · first only / partial result · neither / full success · unknown / unknown · both / partial result · neither / failed with no retained effects
Submitted answer key
both / partial result. 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.

  • falcon3-10b-qualification-v7-c8647169c2b9 · Ainglish: matched the submitted key.
  • olmo2-13b-qualification-v7-cd836509a1a0 · English: did not match the submitted key.

Input 3 · r9-ret-03

English input
Perform this bounded action set: Grant Atlas access; grant Beacon access; grant Cygnus access. If any required member fails, no successful member effect may remain authoritative at terminal handoff. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Ainglish input
Grant Atlas access; grant Beacon access; grant Cygnus access, all-or-nothing. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Question
At terminal handoff after the stated outcomes: (1) which successful member effects remain authoritative; (2) what is the action-set result?
Recorded answer options
first only / partial result · neither / full success · unknown / unknown · both / partial result · neither / failed with no retained effects · both / full success
Submitted answer key
neither / failed with no retained effects. 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.

  • falcon3-10b-qualification-v7-c8647169c2b9 · English: did not match the submitted key.
  • olmo2-13b-qualification-v7-cd836509a1a0 · English: matched the submitted key.

Input 4 · r9-ret-04

English input
Perform this bounded action set: Grant Atlas access; grant Beacon access; grant Cygnus access. If a required member fails, each successful sibling effect remains authoritative and the failures stay disclosed. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Ainglish input
Grant Atlas access; grant Beacon access; grant Cygnus access, keep-successes. The Atlas and Beacon grants succeeded, but the Cygnus grant failed.
Question
At terminal handoff after the stated outcomes: (1) which successful member effects remain authoritative; (2) what is the action-set result?
Recorded answer options
neither / full success · unknown / unknown · both / partial result · neither / failed with no retained effects · both / full success · first only / partial result
Submitted answer key
both / partial result. 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.

  • falcon3-10b-qualification-v7-c8647169c2b9 · Ainglish: did not match the submitted key.
  • olmo2-13b-qualification-v7-cd836509a1a0 · Ainglish: did not match the submitted key.

Input 5 · r9-ret-05

English input
Perform this bounded action set: Publish the policy; publish the schema; publish the examples. The policy and schema publications succeeded, but the examples publication failed.
Ainglish input
Publish the policy; publish the schema; publish the examples, all-or-nothing. The policy and schema publications succeeded, but the examples publication failed.
Question
At terminal handoff after the stated outcomes: (1) which successful member effects remain authoritative; (2) what is the action-set result?
Recorded answer options
unknown / unknown · both / partial result · neither / failed with no retained effects · both / full success · first only / partial result · neither / full success
Submitted answer key
neither / failed with no retained effects. 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.

  • falcon3-10b-qualification-v7-c8647169c2b9 · English: did not match the submitted key.
  • olmo2-13b-qualification-v7-cd836509a1a0 · Ainglish: did not match the submitted key.

Input 6 · r9-ret-06

English input
Perform this bounded action set: Publish the policy; publish the schema; publish the examples. The policy and schema publications succeeded, but the examples publication failed.
Ainglish input
Publish the policy; publish the schema; publish the examples, keep-successes. The policy and schema publications succeeded, but the examples publication failed.
Question
At terminal handoff after the stated outcomes: (1) which successful member effects remain authoritative; (2) what is the action-set result?
Recorded answer options
both / partial result · neither / failed with no retained effects · both / full success · first only / partial result · neither / full success · unknown / unknown
Submitted answer key
both / partial result. 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.

  • falcon3-10b-qualification-v7-c8647169c2b9 · Ainglish: did not match the submitted key.
  • olmo2-13b-qualification-v7-cd836509a1a0 · English: did not match the submitted key.

Recorded input digest: 2ecbabb42ba4b9bccd1aa561e64a05292d4d86144011af9ea22af68d1390086a

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": 0.416700000000000014832579608992091380059719085693359375,
    "ainglish": 0.1666999999999999870770039933631778694689273834228515625,
    "chance": 0.1666999999999999870770039933631778694689273834228515625
}

Reader or tokenizer results

[
    {
        "model": "falcon3-10b-qualification-v7-c8647169c2b9",
        "value": -25.71000000000000085265128291212022304534912109375,
        "precision": "q4_k_m"
    },
    {
        "model": "olmo2-13b-qualification-v7-cd836509a1a0",
        "value": -22.8599999999999994315658113919198513031005859375,
        "precision": "q4_k_m"
    }
]

Condition results

Not recorded

Exact result and immutable specificationExperiment history

Attempt 8b2701f1-8a67-43c7-9db2-a6433fc830e3
Content 921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436

Second result: full recordcomprehension accuracy · 16.67 percentage points

Second result · 2026-09-09 19:15 UTC

all-or-nothing / keep-successes — say what survives when part of a batch fails

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
16.67 percentage points
Reported interval: -25 to 53.3333.

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

English comparison
Other declared comparison; inspect the specification

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

Within each action-set/outcome cell, one English comparator leaves terminal retention unstated and one states the complete registered mapping.

Reader exposure
Reader exposure not recorded as a structured label
Named instruments
falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m, olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m

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

Declared target content identity921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436

How often did each version lead to the right answer?

English comparison
25.00%
25.00%
Ainglish version
41.67%
41.67%

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: -25 to 53.3333 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: 2. These are different units; multiple answers to one case are not new cases.

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: ba9e9d68ce00dfea3ef4647bb10ea911625adc09b81cc9812c8ccdd9fc28058c. 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": 0.25,
    "ainglish": 0.416700000000000014832579608992091380059719085693359375,
    "chance": 0.1666999999999999870770039933631778694689273834228515625
}

Reader or tokenizer results

[
    {
        "model": "falcon3-10b-qualification-v7-c8647169c2b9",
        "value": 16.6700000000000017053025658242404460906982421875,
        "precision": "q4_k_m"
    },
    {
        "model": "olmo2-13b-qualification-v7-cd836509a1a0",
        "value": 16.6700000000000017053025658242404460906982421875,
        "precision": "q4_k_m"
    }
]

Condition results

Not recorded

Exact result and immutable specificationExperiment history

Attempt f3865b42-2b86-41a7-8ebe-ed19018641b3
Content 84d2e0e690eb298da5ff9bb0e134867dd16cc1e42f27b7aa594526cfdc3e80c0

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.