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
-0.125 tokens per declared item Reported interval: -3.4375 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
Separate outcomes retained for all 2 declared conditions
assignment, default
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 within the allowance.
The reported difference is -0.125 tokens; the current declaration allows at most 4 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.
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
assignment
2.25
Not recorded
default
-2.5
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 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
scheduler-retry.max_attempts uses 7 because the explicit assignment rollout-88#retry.max_attempts supplied that value.
gateway-v12.timeout_ms uses 4500 because the explicit assignment GATEWAY_TIMEOUT_MS in rm-441 supplied that value.
Ainglish input
gateway-v12.timeout_ms resolved-by-assignment(4500, source=GATEWAY_TIMEOUT_MS in rm-441)
Condition
assignment
Input 3
English input
telemetry.batch_size uses 512 because the explicit assignment batch_size in streamer.conf supplied that value.
Ainglish input
telemetry.batch_size resolved-by-assignment(512, source=batch_size in streamer.conf)
Condition
assignment
Input 4
English input
db-replica-v9.pool_size uses 24 because the explicit assignment pool_size in deploy-9 supplied that value.
Ainglish input
db-replica-v9.pool_size resolved-by-assignment(24, source=pool_size in deploy-9)
Condition
assignment
Input 5
English input
cache-ttl.seconds uses 900 because the explicit assignment cache-ttl in profile warm-2 supplied that value.
Ainglish input
cache-ttl.seconds resolved-by-assignment(900, source=cache-ttl in profile warm-2)
Condition
assignment
Input 6
English input
queue.visibility_timeout uses 120 because the explicit assignment visibility_timeout by infra supplied that value.
Ainglish input
queue.visibility_timeout resolved-by-assignment(120, source=visibility_timeout by infra)
Condition
assignment
Recorded input digest: 712fcd80978a1cc7685d44d8a608c19bf6f4de6573bf79056cd35c907574538f
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
marked form minus the proposal's declared honest English disclosure, with opaque reference strings preserved verbatim on both sides
Tested population
sixteen complete statements, eight per form (assignment / default), over deployment configuration, environment variables, service baselines, feature flags, telemetry and queue settings; power-of-two sample
Unit tested
one complete configuration-resolution statement: either the marked form verbatim from the proposal's declared form, or the proposal's declared honest English disclosure for the same (K, V, A/R) substitution
How results combine
maximum tokenizer mean across cl100k_base, o200k_base, p50k_base (least-favourable tokenizer)
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.
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.
