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?	removed-from(<surface>) / erased-from(<inventory>) — did “deleted” mean absent here, or unrecoverable from every declared copy?2026-08-31 17:26 UTC	removed-from(<surface>) / erased-from(<inventory>) — did “deleted” mean absent here, or unrecoverable from every declared copy?2026-09-02 22:12 UTC
What was measured?	token costHow does the wording change tokenizer units for the declared tokenizer population?	token costHow does the wording change tokenizer units for the declared tokenizer population?
What was the result?	2 tokens per declared itemReported interval: 2 to 2Result invalid	-19.375 tokens per declared itemReported interval: -23.25 to -19.375Not yet counting in evidence decisions
Compared with what?	English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension	English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension
Independently settled?	Inactive historyThis is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.	Incommensurable pending repairA comparison key does not match, so the row cannot presently vote on settlement.

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

token_delta

Second result

token_delta

English comparison declarations · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

Tested population · Only recorded on one side

First result

Not recorded in this structured field

Second result

8 frozen disjoint removed/erased pairs, Spark 1.3 replication

Unit tested · Only recorded on one side

First result

Not recorded in this structured field

Second result

complete message

Named instruments (including order) · Same recorded value

First result

[
    "cl100k_base",
    "o200k_base",
    "p50k_base"
]

Second result

[
    "cl100k_base",
    "o200k_base",
    "p50k_base"
]

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 · Only recorded on one side

First result

Not recorded in this structured field

Second result

{
    "reducer": "least_favourable",
    "rule": "equal item mean, then maximum tokenizer mean"
}

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 recordtoken cost · 2 tokens per declared item

First result · 2026-08-31 17:26 UTC

removed-from(<surface>) / erased-from(<inventory>) — did “deleted” mean absent here, or unrecoverable from every declared copy?

Result invalid. This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.

What was measured: token cost · token_delta
How does the wording change tokenizer units for the declared tokenizer population?
Historical reported result: 2 tokens per declared item
Reported interval: 2 to 2.
This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.
English comparison: English comparison not recorded as a structured label
Declared by the submitter; not a certification of equivalent information.
Tokenizer conditions: Literal encoding cost on the named current tokenizers; not comprehension.
Named instruments: cl100k_base, o200k_base, p50k_base
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: Inactive history
This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.

Is this result within the cost allowance?

This headline is outside the allowance. The reported difference is 2 tokens; the current declaration allows at most 0 tokens.

This compares Ainglish minus English with the current declaration, which may differ from the declaration when the result was filed. It checks the headline only: inspect any required per-form and per-tokenizer results too.

Has the original estimate been independently reproduced?

Inactive history.

This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.

Reproduction asks whether fresh-input findings agree under the settlement rule. It does not ask whether either value satisfies the cost allowance.

Being within the cost allowance is not a completed prerequisite. Reproducing an original estimate is a separate check, not proof that the allowance is met. Current evidence status, settlement and every declared result still determine readiness. This historical row does not count.

How can one check pass while the other does not?

For example, an allowance of at most +3 tokens and an original estimate of +3 ask different questions. A replication of −0.5 is within that allowance but may disagree with the original. A replication of +3.25 may reproduce +3 within the settlement tolerance while exceeding the allowance.

These are illustrative numbers, not a new settlement rule. A cost saving is not a comprehension result, and a reproduced premium does not by itself mean a proposal should be adopted or rejected.

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 6 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.

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

Input 1

English input: At 2026-08-01T00:00Z, no admissible query in the exact bounded retrieval surface receipt customer-profile-surface-receipt@001-r1 returns or addresses customer-profile-001; other surfaces and storage copies are unasserted.
Ainglish input: customer-profile-001 removed-from(customer-profile-surface-receipt@001-r1) as_of(2026-08-01T00:00Z).

Input 2

English input: At 2026-08-01T00:00Z, no representation matching customer-profile-001s declared boundary remains recoverable in any storage locus enumerated by customer-profile-inventory-receipt@001-v1 under its declared recovery model; outside and later copies are unasserted.
Ainglish input: customer-profile-001 erased-from(customer-profile-inventory-receipt@001-v1) as_of(2026-08-01T00:00Z).

Input 3

English input: At 2026-08-02T01:00Z, no admissible query in the exact bounded retrieval surface receipt support-ticket-surface-receipt@002-r1 returns or addresses support-ticket-002; other surfaces and storage copies are unasserted.
Ainglish input: support-ticket-002 removed-from(support-ticket-surface-receipt@002-r1) as_of(2026-08-02T01:00Z).

Input 4

English input: At 2026-08-02T01:00Z, no representation matching support-ticket-002s declared boundary remains recoverable in any storage locus enumerated by support-ticket-inventory-receipt@002-v1 under its declared recovery model; outside and later copies are unasserted.
Ainglish input: support-ticket-002 erased-from(support-ticket-inventory-receipt@002-v1) as_of(2026-08-02T01:00Z).

Input 5

English input: At 2026-08-03T02:00Z, no admissible query in the exact bounded retrieval surface receipt document-surface-receipt@003-r1 returns or addresses document-003; other surfaces and storage copies are unasserted.
Ainglish input: document-003 removed-from(document-surface-receipt@003-r1) as_of(2026-08-03T02:00Z).

Input 6

English input: At 2026-08-03T02:00Z, no representation matching document-003s declared boundary remains recoverable in any storage locus enumerated by document-inventory-receipt@003-v1 under its declared recovery model; outside and later copies are unasserted.
Ainglish input: document-003 erased-from(document-inventory-receipt@003-v1) as_of(2026-08-03T02:00Z).

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

Not recorded

Reader or tokenizer results

[
    {
        "model": "cl100k_base",
        "value": 2
    },
    {
        "model": "o200k_base",
        "value": 2
    },
    {
        "model": "p50k_base",
        "value": 2
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt df64b436-c1d8-4b8d-bd73-6602eb25cd6d
Content 2b64b2699aa2921d6cef9adecc75622d7212c09034217c2f290566a99439230c

Second result: full recordtoken cost · -19.375 tokens per declared item

Second result · 2026-09-02 22:12 UTC

removed-from(<surface>) / erased-from(<inventory>) — did “deleted” mean absent here, or unrecoverable from every declared copy?

Not yet counting in evidence decisions. This row remains available for assessment, but does not currently carry a counting evidence result.

What was measured: token cost · token_delta
How does the wording change tokenizer units for the declared tokenizer population?
Reported result: -19.375 tokens per declared item
Reported interval: -23.25 to -19.375.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
English comparison: English comparison not recorded as a structured label
Declared by the submitter; not a certification of equivalent information.
Tokenizer conditions: Literal encoding cost on the named current tokenizers; not comprehension.
Named instruments: cl100k_base, o200k_base, p50k_base
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: Incommensurable pending repair
A comparison key does not match, so the row cannot presently vote on settlement.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is -19.375 tokens; the current declaration allows at most 0 tokens.

Has the original estimate been independently reproduced?

Incommensurable pending repair. This replication reports -19.375 tokens; the named original reported 2.

A comparison key does not match, so the row cannot presently vote on settlement.

Reproduction asks whether fresh-input findings agree under the settlement rule. It does not ask whether either value satisfies the cost allowance.

How can one check pass while the other does not?

These are illustrative numbers, not a new settlement rule. A cost saving is not a comprehension result, and a reproduced premium does not by itself mean a proposal should be adopted or rejected.

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.

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 identity

2b64b2699aa2921d6cef9adecc75622d7212c09034217c2f290566a99439230c

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. 0 control items are kept separate.

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

Input 1

English input: At 2026-09-02T22:10Z, no admissible query in the exact bounded retrieval surface receipt checkout-surface-receipt@214-r2 returns or addresses order-4271; other surfaces and storage copies are unasserted.
Ainglish input: order-4271 removed-from(checkout-surface-receipt@214-r2) as_of(2026-09-02T22:10Z).

Input 2

English input: At 2026-09-02T22:11Z, no admissible query in the exact bounded retrieval surface receipt edge-cache-snapshot@089-c4 returns or addresses session-9f3c; other surfaces and storage copies are unasserted.
Ainglish input: session-9f3c removed-from(edge-cache-snapshot@089-c4) as_of(2026-09-02T22:11Z).

Input 3

English input: At 2026-09-02T22:12Z, no admissible query in the exact bounded retrieval surface receipt billing-surface-receipt@312-r7 returns or addresses invoice-55821; other surfaces and storage copies are unasserted.
Ainglish input: invoice-55821 removed-from(billing-surface-receipt@312-r7) as_of(2026-09-02T22:12Z).

Input 4

English input: At 2026-09-02T22:13Z, no admissible query in the exact bounded retrieval surface receipt auth-surface-receipt@501-r3 returns or addresses token-77ab; other surfaces and storage copies are unasserted.
Ainglish input: token-77ab removed-from(auth-surface-receipt@501-r3) as_of(2026-09-02T22:13Z).

Input 5

English input: At 2026-09-02T22:10Z, no representation matching order-4271s declared boundary remains recoverable in any storage locus enumerated by order-inventory-receipt@214-v2 under its declared recovery model; outside and later copies are unasserted.
Ainglish input: order-4271 erased-from(order-inventory-receipt@214-v2) as_of(2026-09-02T22:10Z).

Input 6

English input: At 2026-09-02T22:11Z, no representation matching session-9f3cs declared boundary remains recoverable in any storage locus enumerated by session-inventory-receipt@089-v1 under its declared recovery model; outside and later copies are unasserted.
Ainglish input: session-9f3c erased-from(session-inventory-receipt@089-v1) as_of(2026-09-02T22:11Z).

Recorded input digest: c124d9cc19710f460142f3439a3f59f3e6805fc241ac0d08f6eaf7c33a3ac31b

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

Compared with: Ainglish removed-from/erased-from form versus complete careful English
Tested population: 8 frozen disjoint removed/erased pairs, Spark 1.3 replication
Unit tested: complete message
How results combine: equal item mean, then maximum tokenizer mean

These are the study author’s declarations. A finding applies to this tested scope; this summary does not establish that another study is comparable.

Absolute arm results

Not recorded

Reader or tokenizer results

[
    {
        "model": "cl100k_base",
        "value": -22.75
    },
    {
        "model": "o200k_base",
        "value": -23.25
    },
    {
        "model": "p50k_base",
        "value": -19.375
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 2aab5f94-9256-4656-90d0-bcc21690d23c
Content d150f755cb11bbd2db5dda8667966a423093a4e321ac5907b7cab019db6e0535

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.