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?2026-09-07 18:47 UTC	removed-from(<surface>) / erased-from(<inventory>) — did “deleted” mean absent here, or unrecoverable from every declared copy?2026-09-09 22:20 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?	0.625 tokens per declared itemReported interval: -5 to 0.625Not yet counting in evidence decisions	-0.125 tokens per declared itemReported interval: -6 to -0.125Counts in current 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?	DisputedEligible replications disagree and this original does not hold a settlement majority.	Disagrees with the named originalThis eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

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 · Same recorded value

First result

cl100k_base/o200k_base/p50k_base

Second result

cl100k_base/o200k_base/p50k_base

Unit tested · Same recorded value

First result

pair

Second result

pair

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 · Same recorded value

First result

{
    "reducer": "least_favourable",
    "rule": "maximum tokenizer mean"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "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 · 0.625 tokens per declared item

First result · 2026-09-07 18:47 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: 0.625 tokens per declared item
Reported interval: -5 to 0.625.
More 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: Disputed
Eligible replications disagree and this original does not hold a settlement majority.

Is this result within the cost allowance?

This headline is outside the allowance. The reported difference is 0.625 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?

Disputed.

Eligible replications disagree and this original does not hold a settlement majority.

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.

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 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 21:00 UTC, no query admissible under account-surface receipt r7 for its named principal class, region, and consistency bound returned Customer 42's profile; other surfaces and copies remain unasserted.
Ainglish input: customer-42 profile, removed-from(account-surface-receipt@r7) as_of(2026-08-28T21:00Z).

Input 2

English input: At 21:00 UTC, no recoverable representation of Customer 42's profile remained in any locus enumerated by immutable inventory receipt v7 under its declared recovery model; unlisted or later copies remain unasserted.
Ainglish input: customer-42 profile, erased-from(storage-inventory-receipt@v7) as_of(2026-08-28T21:00Z).

Input 3

English input: At the stated epoch, no customer-class query admitted by helpdesk receipt r3 returned Ticket 812's attachment; support-staff visibility is outside that receipt.
Ainglish input: ticket-812 attachment, removed-from(helpdesk-customer-query-receipt@r3) as_of(2026-08-28T21:00Z).

Input 4

English input: At the stated epoch, no trace of Ticket 812's attachment remained in any locus enumerated by the backup inventory receipt v9 under its declared recovery model.
Ainglish input: ticket-812 attachment, erased-from(backup-inventory-receipt@v9) as_of(2026-08-28T21:00Z).

Input 5

English input: At 14:00 UTC, no API call admissible under public-surface receipt r1 for its named principal class and region returned User 99's settings; cached copies remain unasserted.
Ainglish input: user-99 settings, removed-from(public-surface-receipt@r1) as_of(2026-09-01T14:00Z).

Input 6

English input: At 14:00 UTC, no recoverable representation of User 99's settings remained in any locus enumerated by the archival inventory receipt v4 under its declared recovery model.
Ainglish input: user-99 settings, erased-from(archival-inventory-receipt@v4) as_of(2026-09-01T14:00Z).

Recorded input digest: 7710c2c177db1bcafaa3f6269456f5051097bdf5f978d399923077fae4ad49b3

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: token_delta
Tested population: cl100k_base/o200k_base/p50k_base
Unit tested: pair
How results combine: 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, 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": -5
    },
    {
        "model": "o200k_base",
        "value": -4.5
    },
    {
        "model": "p50k_base",
        "value": 0.625
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 6ba44854-f59d-4ba2-98d8-6b6f3a1f0ad6
Content 903b67a697f5e000b7c57ab64f491e33a7b05aacc67fd5d05a0a99d7c1a6a670

Second result: full recordtoken cost · -0.125 tokens per declared item

Second result · 2026-09-09 22:20 UTC

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

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: token cost · token_delta
How does the wording change tokenizer units for the declared tokenizer population?
Reported result: -0.125 tokens per declared item
Reported interval: -6 to -0.125.
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: Disagrees with the named original
This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is -0.125 tokens; the current declaration allows at most 0 tokens.

Has the original estimate been independently reproduced?

Disagrees with the named original. This replication reports -0.125 tokens; the named original reported 0.625.

This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

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

Declared target content identity

903b67a697f5e000b7c57ab64f491e33a7b05aacc67fd5d05a0a99d7c1a6a670

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 03:30 UTC, no support query admissible under case-portal receipt c4 for its named principal class, region, and consistency bound returned Case 204's notes; auditor copies remain unasserted.
Ainglish input: case-204 notes, removed-from(case-portal-receipt@c4) as_of(2026-09-08T03:30Z).

Input 2

English input: At the stated epoch, no editor-class query admitted by drafting receipt d9 returned Draft 336's image; reviewer visibility is outside that receipt.
Ainglish input: draft-336 image, removed-from(drafting-editor-receipt@d9) as_of(2026-09-08T03:30Z).

Input 3

English input: At 19:15 UTC, no read request admissible under member-feed receipt m2 for its named principal class returned Member 51's activity log; admin exports remain unasserted.
Ainglish input: member-51 activity log, removed-from(member-feed-receipt@m2) as_of(2026-09-08T19:15Z).

Input 4

English input: At the freeze epoch, no artifact query admitted by pipeline receipt p8 for its named principal class returned Release 940's binary; nightly mirrors remain unasserted.
Ainglish input: release-940 binary, removed-from(pipeline-artifact-receipt@p8) as_of(2026-09-08T19:15Z).

Input 5

English input: At 03:30 UTC, no recoverable representation of Case 204's notes remained in any locus enumerated by the tape-archive inventory receipt t6 under its declared recovery model.
Ainglish input: case-204 notes, erased-from(tape-archive-inventory-receipt@t6) as_of(2026-09-08T03:30Z).

Input 6

English input: At the stated epoch, no recoverable representation of Draft 336's image remained in any locus enumerated by the snapshot-store inventory receipt s1 under its declared recovery model; offline duplicates remain unasserted.
Ainglish input: draft-336 image, erased-from(snapshot-store-inventory-receipt@s1) as_of(2026-09-08T03:30Z).

Recorded input digest: f25fd227ac02bcafdd74ddcdd7bf84d4e7a9c11bc9c188b02ba9721049209324

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: token_delta
Tested population: cl100k_base/o200k_base/p50k_base
Unit tested: pair
How results combine: 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": -6
    },
    {
        "model": "o200k_base",
        "value": -5.375
    },
    {
        "model": "p50k_base",
        "value": -0.125
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt da6eb4c9-9550-41a0-ac6c-a3772504bf5e
Content f9cb0712c4eba244648cef748ebaf7c4ab79c8d1ebf8df0cdcbd2adfa81b6bbd

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.