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

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.

Question	First result	Second result
Which proposal?	none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?2026-09-06 20:56 UTC	none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?2026-09-16 15:13 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?	-33.33 percentage pointsReported interval: -100 to 0Counts in current evidence decisions	0 percentage pointsReported interval: 0 to 0Counts in current evidence decisions
Compared with what?	Complete, careful EnglishReader exposure not recorded as a structured label	Complete, careful EnglishReader 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 result Inspect 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

[
    "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) · Recorded values differ

First result

[
    "spark-zen-13-minimal"
]

Second result

[
    "deepseek-flash-minimal"
]

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 · -33.33 percentage points

First result · 2026-09-06 20:56 UTC

none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?

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

-33.33 percentage points
Reported interval: -100 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.

The proposal complete careful English mapping.

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

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: 100.00%; 100.00%
Ainglish version: 66.67%; 66.67%

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: -100 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: 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 5 · `real-n1`

English input: No mirrors are fresh; every mirror failed the freshness check.
Ainglish input: none-of(mirrors): fresh. Every mirror failed the freshness check.
Question: How many mirrors are fresh?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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-n2`

English input: No gates are open; every gate was found shut at inspection.
Ainglish input: none-of(gates): open. Every gate was found shut at inspection.
Question: How many gates are open?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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 7 · `real-n3`

English input: No snapshots are verified; each snapshot failed verification.
Ainglish input: none-of(snapshots): verified. Each snapshot failed verification.
Question: How many snapshots are verified?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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 8 · `real-n4`

English input: No jobs are done; all jobs are still running.
Ainglish input: none-of(jobs): done. All jobs are still running.
Question: How many jobs are done?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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-h1`

English input: Not all vans are loaded; one van left empty and the rest have not been checked.
Ainglish input: not-all-of(vans): loaded. One van left empty and the rest have not been checked.
Question: How many vans are loaded?
Recorded answer options: zero · at least one · unknown
Submitted answer key: unknown. 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-h2`

English input: Not all invoices are paid; one is overdue and the others are unreconciled.
Ainglish input: not-all-of(invoices): paid. One is overdue and the others are unreconciled.
Question: How many invoices are paid?
Recorded answer options: zero · at least one · unknown
Submitted answer key: unknown. 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.

Recorded input digest: 09e623729cce04ca1dbef98d130a820c27248b45033f05cca04eb4be6419c886

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": 0.66669999999999995932142837773426435887813568115234375,
    "chance": 0.333299999999999985167420391007908619940280914306640625
}

Reader or tokenizer results

[
    {
        "model": "spark-zen-13-minimal",
        "value": -33.3299999999999982946974341757595539093017578125
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 90ca5efc-e5c8-4a5c-b67b-2ff7a14601a6
Content 243ab77e31a80bc0c4426c3f236762d64be2d0b1dd7c8255973bd5bcfd0d0d2f

Second result: full recordcomprehension accuracy · 0 percentage points

Second result · 2026-09-16 15:13 UTC

none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?

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

0 percentage points
Reported interval: 0 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.

The proposal complete careful English mapping.

Reader exposure

Reader exposure not recorded as a structured label

Named instruments

deepseek-flash-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

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?

100.0% of complete English–Ainglish pairs are fresh.

0 of 12 English inputs reuse text from either side of the original.
0 of 12 Ainglish inputs reuse text from either side of the original.

Declared item-bank digests: different. This compares bank identity, not shared sentences; different bank digests can still contain identical pairs.

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 identity

243ab77e31a80bc0c4426c3f236762d64be2d0b1dd7c8255973bd5bcfd0d0d2f

How often did each version lead to the right answer?

English comparison: 100.00%; 100.00%
Ainglish version: 100.00%; 100.00%

Reported item-bootstrap interval: 0 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.

The reported accuracy is near a measurement boundary; read the resolution diagnostics before claiming a small effect.

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 · `r44c-n1`

English input: No archives are indexed; every archive is still queued for indexing.
Ainglish input: none-of(archives): indexed. Every archive is still queued for indexing.
Question: How many archives are indexed?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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.

deepseek-flash-minimal · Ainglish: matched the submitted key.

Input 2 · `r44c-n2`

English input: No trenches are backfilled; all trenches are still open.
Ainglish input: none-of(trenches): backfilled. All trenches are still open.
Question: How many trenches are backfilled?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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.

deepseek-flash-minimal · English: matched the submitted key.

Input 3 · `r44c-n3`

English input: No receipts are validated; each receipt failed the validator.
Ainglish input: none-of(receipts): validated. Each receipt failed the validator.
Question: How many receipts are validated?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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.

deepseek-flash-minimal · Ainglish: matched the submitted key.

Input 4 · `r44c-n4`

English input: No vats are cleaned; every vat is still waiting for the wash cycle.
Ainglish input: none-of(vats): cleaned. Every vat is still waiting for the wash cycle.
Question: How many vats are cleaned?
Recorded answer options: zero · at least one · unknown
Submitted answer key: zero. 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.

deepseek-flash-minimal · English: matched the submitted key.

Input 5 · `r44c-h1`

English input: Not all pallets are wrapped; one pallet came off the line unwrapped and the others are still unverified.
Ainglish input: not-all-of(pallets): wrapped. One pallet came off the line unwrapped and the others are still unverified.
Question: How many pallets are wrapped?
Recorded answer options: zero · at least one · unknown
Submitted answer key: unknown. 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.

deepseek-flash-minimal · English: matched the submitted key.

Input 6 · `r44c-h2`

English input: Not all speakers are mounted; one speaker is still in its crate and the rest have not been surveyed.
Ainglish input: not-all-of(speakers): mounted. One speaker is still in its crate and the rest have not been surveyed.
Question: How many speakers are mounted?
Recorded answer options: zero · at least one · unknown
Submitted answer key: unknown. 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.

deepseek-flash-minimal · English: matched the submitted key.

Recorded input digest: 5ba816175736786b96aa146a2271d6928b2bd40bf942e1d7d9eedf747b408c51

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

{
    "english": 1,
    "ainglish": 1,
    "chance": 0.333299999999999985167420391007908619940280914306640625
}

Reader or tokenizer results

[
    {
        "model": "deepseek-flash-minimal",
        "value": 0
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt e47c1bcc-4006-42a2-87fb-8da704564d8f
Content a2427de72a591043e4f1036a88676d66f09b4501524ae958616b61031ab53c68

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.

Compare two experiments

Find experiments by proposal

Compare the essentials

none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?

How often did each version lead to the right answer?

Input 5 · real-n1

Input 6 · real-n2

Input 7 · real-n3

Input 8 · real-n4

Input 9 · real-h1

Input 10 · real-h2

Absolute arm results

Reader or tokenizer results

Condition results

none-of / not-all-of — did ‘all ... not’ mean zero, or fewer than all?

How often did each version lead to the right answer?

Input 1 · r44c-n1

Input 2 · r44c-n2

Input 3 · r44c-n3

Input 4 · r44c-n4

Input 5 · r44c-h1

Input 6 · r44c-h2

Absolute arm results

Reader or tokenizer results

Condition results

Input 5 · `real-n1`

Input 6 · `real-n2`

Input 7 · `real-n3`

Input 8 · `real-n4`

Input 9 · `real-h1`

Input 10 · `real-h2`

Input 1 · `r44c-n1`

Input 2 · `r44c-n2`

Input 3 · `r44c-n3`

Input 4 · `r44c-n4`

Input 5 · `r44c-h1`

Input 6 · `r44c-h2`