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.

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

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

256 cells: 16 authored domains, 8 response situations and 2 delivery states; equal form weights; domain and identifier variants are not independent grammatical frames

Second result

256 cells: 16 authored domains, 8 response situations and 2 delivery states; equal form weights; domain and identifier variants are not independent grammatical frames

Unit tested · Same recorded value

First result

complete vignette and scoped claim

Second result

complete vignette and scoped claim

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": "equal cell means then maximum tokenizer mean; preserve separate reply and no-observed-reply strata"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "equal cell means then maximum tokenizer mean; preserve separate reply and no-observed-reply strata"
}

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) · Same recorded value

First result

[
    {
        "id": "replied-no",
        "weight": 1
    },
    {
        "id": "no-reply-from",
        "weight": 1
    }
]

Second result

[
    {
        "id": "replied-no",
        "weight": 1
    },
    {
        "id": "no-reply-from",
        "weight": 1
    }
]

First result · 2026-09-07 12:56 UTC

replied-no / no-reply-from — did they say no, or did no answer arrive?

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

6.875 tokens per declared item
Reported interval: 2.625 to 6.875.

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

Separate outcomes retained for all 2 declared conditions

replied-no, no-reply-from

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.

Is this result within the cost allowance?

This headline is outside the allowance. The reported difference is 6.875 tokens; the current declaration allows at most 3 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?

Confirmed by eligible settlement.

Eligible fresh-input replications currently give this original 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.

Does the overall result hide differences between conditions?

Every stored condition, without new pooling. Differences and intervals use tokens. Condition names come from the frozen experiment.
Condition	Reported difference	Reported interval
`replied-no`	3.875	Not recorded
`no-reply-from`	9.875	Not recorded

A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.

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 256 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: The exact request is invitations-71-0-revision-2. Delivery to Mira is unknown. The separate workflow policy is to go without assent. Mira replied no to invitations-71-0-revision-2.
Ainglish input: The exact request is invitations-71-0-revision-2. Delivery to Mira is unknown. The separate workflow policy is to go without assent. Mira replied-no(to=invitations-71-0-revision-2).
Condition: replied-no

Input 2

English input: The exact request is invitations-71-0-revision-2. Delivery to Mira is confirmed by a read receipt. The separate workflow policy is to go without assent. Mira replied no to invitations-71-0-revision-2.
Ainglish input: The exact request is invitations-71-0-revision-2. Delivery to Mira is confirmed by a read receipt. The separate workflow policy is to go without assent. Mira replied-no(to=invitations-71-0-revision-2).
Condition: replied-no

Input 3

English input: The exact request is invitations-71-1-revision-2. Delivery to Mira is unknown. The separate workflow policy is to wait for explicit assent. Mira replied no to invitations-71-1-revision-2.
Ainglish input: The exact request is invitations-71-1-revision-2. Delivery to Mira is unknown. The separate workflow policy is to wait for explicit assent. Mira replied-no(to=invitations-71-1-revision-2).
Condition: replied-no

Input 4

English input: The exact request is invitations-71-1-revision-2. Delivery to Mira is confirmed by a read receipt. The separate workflow policy is to wait for explicit assent. Mira replied no to invitations-71-1-revision-2.
Ainglish input: The exact request is invitations-71-1-revision-2. Delivery to Mira is confirmed by a read receipt. The separate workflow policy is to wait for explicit assent. Mira replied-no(to=invitations-71-1-revision-2).
Condition: replied-no

Input 5

English input: The exact request is invitations-71-2-revision-2. Delivery to Mira is unknown. The separate workflow policy is to leave the next action undecided. Mira replied no to invitations-71-2-revision-2.
Ainglish input: The exact request is invitations-71-2-revision-2. Delivery to Mira is unknown. The separate workflow policy is to leave the next action undecided. Mira replied-no(to=invitations-71-2-revision-2).
Condition: replied-no

Input 6

English input: The exact request is invitations-71-2-revision-2. Delivery to Mira is confirmed by a read receipt. The separate workflow policy is to leave the next action undecided. Mira replied no to invitations-71-2-revision-2.
Ainglish input: The exact request is invitations-71-2-revision-2. Delivery to Mira is confirmed by a read receipt. The separate workflow policy is to leave the next action undecided. Mira replied-no(to=invitations-71-2-revision-2).
Condition: replied-no

Recorded input digest: 810d6fe4014319d92c6de699152c3de760d5eefaccc78ad108ee7ed9e914c723

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: registered exact-request reply or scoped observation claim versus concise meaning-complete careful English, with identical surrounding facts
Tested population: 256 cells: 16 authored domains, 8 response situations and 2 delivery states; equal form weights; domain and identifier variants are not independent grammatical frames
Unit tested: complete vignette and scoped claim
How results combine: equal cell means then maximum tokenizer mean; preserve separate reply and no-observed-reply strata

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": 2.625
    },
    {
        "model": "o200k_base",
        "value": 3.25
    },
    {
        "model": "p50k_base",
        "value": 6.875
    }
]

Condition results

[
    {
        "id": "replied-no",
        "weight": 1,
        "share": 0.5,
        "value": 3.875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "no-reply-from",
        "weight": 1,
        "share": 0.5,
        "value": 9.875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 263eabf3-a47e-4fc0-ae0b-8e9176501dbf
Content 69debfe93b28a7062486f4b8cfc7311c3e21fba9b99217347fa300ad24493e30

Second result · 2026-09-08 15:26 UTC

replied-no / no-reply-from — did they say no, or did no answer arrive?

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

7.3125 tokens per declared item
Reported interval: 2.875 to 7.3125.

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

Separate outcomes retained for all 2 declared conditions

replied-no, no-reply-from

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.

Is this result within the cost allowance?

This headline is outside the allowance. The reported difference is 7.3125 tokens; the current declaration allows at most 3 tokens.

Has the original estimate been independently reproduced?

Agrees with the named original. This replication reports 7.3125 tokens; the named original reported 6.875.

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

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

Every declared condition must agree. Overlapping overall intervals alone do not confirm this original.

Declared target content identity

69debfe93b28a7062486f4b8cfc7311c3e21fba9b99217347fa300ad24493e30

Does the overall result hide differences between conditions?

Every stored condition, without new pooling. Differences and intervals use tokens. Condition names come from the frozen experiment.
Condition	Reported difference	Reported interval
`replied-no`	4.1875	Not recorded
`no-reply-from`	10.4375	Not recorded

A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.

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 256 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: The exact request is bookings-83-4-revision-1. Delivery to Ana is confirmed by a read receipt. The separate workflow policy is to leave the next action undecided. By 2026-09-08T17:00Z, no email reply from Ana to bookings-83-4-revision-1 was observed.
Ainglish input: The exact request is bookings-83-4-revision-1. Delivery to Ana is confirmed by a read receipt. The separate workflow policy is to leave the next action undecided. no-reply-from(Ana, to=bookings-83-4-revision-1, via=email) as_of(2026-09-08T17:00Z).
Condition: no-reply-from

Input 2

English input: The exact request is bookings-83-4-revision-1. Delivery to Dan is unknown. The separate workflow policy is to wait for explicit assent. By 2026-09-08T17:00Z, no email reply from Dan to bookings-83-4-revision-1 was observed.
Ainglish input: The exact request is bookings-83-4-revision-1. Delivery to Dan is unknown. The separate workflow policy is to wait for explicit assent. no-reply-from(Dan, to=bookings-83-4-revision-1, via=email) as_of(2026-09-08T17:00Z).
Condition: no-reply-from

Input 3

English input: The exact request is bookings-83-5-revision-1. Delivery to Ana is unknown. The separate workflow policy is to leave the next action undecided. By 2026-09-08T17:00Z, no email reply from Ana to bookings-83-5-revision-1 was observed.
Ainglish input: The exact request is bookings-83-5-revision-1. Delivery to Ana is unknown. The separate workflow policy is to leave the next action undecided. no-reply-from(Ana, to=bookings-83-5-revision-1, via=email) as_of(2026-09-08T17:00Z).
Condition: no-reply-from

Input 4

English input: The exact request is bookings-83-5-revision-1. Delivery to Ben is confirmed by a read receipt. The separate workflow policy is to go without assent. By 2026-09-08T17:00Z, no email reply from Ben to bookings-83-5-revision-1 was observed.
Ainglish input: The exact request is bookings-83-5-revision-1. Delivery to Ben is confirmed by a read receipt. The separate workflow policy is to go without assent. no-reply-from(Ben, to=bookings-83-5-revision-1, via=email) as_of(2026-09-08T17:00Z).
Condition: no-reply-from

Input 5

English input: The exact request is bookings-83-6-revision-1. Delivery to Ben is unknown. The separate workflow policy is to go without assent. By 2026-09-08T17:00Z, no email reply from Ben to bookings-83-6-revision-1 was observed.
Ainglish input: The exact request is bookings-83-6-revision-1. Delivery to Ben is unknown. The separate workflow policy is to go without assent. no-reply-from(Ben, to=bookings-83-6-revision-1, via=email) as_of(2026-09-08T17:00Z).
Condition: no-reply-from

Input 6

English input: The exact request is bookings-83-6-revision-1. Delivery to Cora is confirmed by a read receipt. The separate workflow policy is to wait for explicit assent. By 2026-09-08T17:00Z, no email reply from Cora to bookings-83-6-revision-1 was observed.
Ainglish input: The exact request is bookings-83-6-revision-1. Delivery to Cora is confirmed by a read receipt. The separate workflow policy is to wait for explicit assent. no-reply-from(Cora, to=bookings-83-6-revision-1, via=email) as_of(2026-09-08T17:00Z).
Condition: no-reply-from

Recorded input digest: 8f41e53e3f7f30dd2c4c857a32c4e884d4fee6a98a60ad720f16b722e3349eb2

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: registered exact-request reply or scoped observation claim versus concise meaning-complete careful English, with identical surrounding facts
Tested population: 256 cells: 16 authored domains, 8 response situations and 2 delivery states; equal form weights; domain and identifier variants are not independent grammatical frames
Unit tested: complete vignette and scoped claim
How results combine: equal cell means then maximum tokenizer mean; preserve separate reply and no-observed-reply strata

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": 2.875
    },
    {
        "model": "o200k_base",
        "value": 3.5
    },
    {
        "model": "p50k_base",
        "value": 7.3125
    }
]

Condition results

[
    {
        "id": "replied-no",
        "weight": 1,
        "share": 0.5,
        "value": 4.1875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "no-reply-from",
        "weight": 1,
        "share": 0.5,
        "value": 10.4375,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 301e2ad1-d52c-4250-8e72-f4d9c88e8fdb
Content fc91e45de176720265baf3e5fe6fe3d8895015c7d8ca00a9e636c48332738b10

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.