First result · 2026-09-30 20:41 UTC
on-record / derived-at-read — say whether a status word is stated by a record or was computed when you asked
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
- -0.5 tokens per declared item
Reported interval: -4.5 to -0.5.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_baseReader 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.
- Is this result within the cost allowance?
- This headline is within the allowance.
The reported difference is -0.5 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?
- Agrees with the named original.
This replication reports -0.5 tokens; the named original reported -0.5.
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.
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.
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 16 English inputs reuse text from either side of the original.
- 0 of 16 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
fe694ffa73ed52c4c067f77ceada3e20bf6c997e3eb09d034f32438e13cef40fInspect 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 16 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
- ticket A204: closed, computed now by status-rule-501@3; no record states it.
- Ainglish input
- ticket A204: closed derived-at-read(status-rule-501@3).
Input 2
- English input
- task C215: timed_out, computed now by status-rule-502@3; no record states it.
- Ainglish input
- task C215: timed_out derived-at-read(status-rule-502@3).
Input 3
- English input
- claim E226: confirmed, computed now by status-rule-503@3; no record states it.
- Ainglish input
- claim E226: confirmed derived-at-read(status-rule-503@3).
Input 4
- English input
- construct G237: deprecated, computed now by status-rule-504@3; no record states it.
- Ainglish input
- construct G237: deprecated derived-at-read(status-rule-504@3).
Input 5
- English input
- test I248: passed, computed now by status-rule-505@3; no record states it.
- Ainglish input
- test I248: passed derived-at-read(status-rule-505@3).
Input 6
- English input
- order L259: cancelled, computed now by status-rule-506@3; no record states it.
- Ainglish input
- order L259: cancelled derived-at-read(status-rule-506@3).
Recorded input digest: ea46906e76feffb26f9594e2e1d8a629f67d5fe0f51c3ff86f8d2c5e35d68515
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 derived-at-read statement minus the fixed concise complete-English renderer in the semantic review, with identical subject/status/reference/time. This tests only derived-at-read, not a pooled two-form message.
- Tested population
- 16 authored complete status reports across tickets, tasks, claims, constructs, tests, orders, shipments, subscriptions, appeals, grants, invoices, inspections, reservations, batches, accounts and cases. One fixed form renderer per status. Eight computations at message composition and eight cached/relayed reports of a pinned earlier computation; equal weights.
- Unit tested
- One complete status-production report, including subject, status, reference and any original computation timestamp.
- How results combine
- Equal item mean within this single form, then maximum tokenizer mean. The companion form is a separate original; the declared joint cost is the larger of their headlines. An equal-form pooled matrix is diagnostic only.
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": -4.5
},
{
"model": "o200k_base",
"value": -4.5
},
{
"model": "p50k_base",
"value": -0.5
}
]
Condition results
Not recorded
Exact result and immutable specificationExperiment history
Attempt 9b438545-0805-408b-944f-cb070aa4dc8c
Content 2504873fa064fb380a8876f61ac0f22b2e5a30fdca52e41464d63793c8a6172d