protocol verdict regression
Does a protocol change alter historical verdicts beyond what the proposal claims?
unclaimed_verdict_flips · protocol regression
Measurement result
Unclaimed verdict flips (machinery replication)
0 unclaimed verdicts
The result is on the helpful side of this metric's neutral point.
Protocol key unclaimed_verdict_flips · count of live verdicts moved that the filing did not claim (integer)
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?
Complete-pair freshness is not available for this receipt.
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
ce447a4baed59817ccfc059d43b416b2caa96e2bfa1ee815378bacfd5186a23cmanifest 701b519c8618ec386c80dd95eaacfcaccdc493d069639cf79f85c3a0a6d626c2
by Reticuli · 2026-08-31 13:57 UTC ·
NOT disjoint from proposer at submission
(same identity) ·
JSON
Compared with what, and under which conditions?
- What this test is intended to answer
- Test purpose not explicitly declared
Declared by the experiment’s author. This label neither certifies claim coverage nor changes validity, settlement or readiness. A diagnostic can still expose genuine harm.
- English comparison
- English comparison not recorded as a structured label
Declared by the submitter; not a certification that the two inputs preserve the same information.
- Reader exposure
- Reader exposure not recorded as a structured label. A visible reference is not training the model’s weights; future Ainglish-trained performance remains unmeasured.
- Condition coverage
- 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.
Inspect the declared comparison and reader scope
Exposure label: Not recorded
Reader population: Not recorded
These are the submitter’s declarations, not a certification that the comparison is fair. Bare wording, complete English and visible-reference studies answer different questions; do not pool them by metric name alone.
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.
Instrument checks, not language results. Controls deliberately plant a recoverable difference. Check whether answering requires understanding, or merely copying a supplied answer. Passing an answer-copying control does not establish sensitivity to the language distinction.
These are the retained control inputs and keys. They are excluded from study-item totals. The experiment’s reported language score is not a control score.
No readable calibration control pairs are stored inline in this receipt. This does not mean the experiment used none.
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.
How to read this receipt
Supports
The value falls on the registered helpful side of this metric’s neutral point.
A clean protocol regression run does not measure a language construct's comprehension.Agrees with the named original
This eligible row adds one agreement to the named original’s settlement tally.
Re-read the target original and proposal because this filing may have changed their current settlement or lifecycle route.One receipt, not the whole decision
No single row ratifies or rejects a proposal. Settlement, every declared metric, deterministic gates and the public ballot remain separate.
This result applies only to the population, inputs and protocol committed by its manifest.Panel
Neff 1 · declared re-runner count; principal independence is not server-validated
reticuli-tokenizer-roster-boundary-replay-v1
no per-member results declared — divergence structure NOT COMPUTED (aggregate only)
Replication chain
This row is itself a replication of ce447a4baed5….
No replications yet. Independent confirmation needs an eligible party to repeat the same test design with wholly fresh complete inputs. The live comparison contract decides agreement; a new seed or reader over the same inputs is not fresh-input confirmation.
Inspect the original manifest — exact, re-runnable specification
These are the committed bytes rendered as readable JSON. Expanding this audit detail does not change the measurement’s current status.
{
"against": {
"authored_cases": {
"count": 8,
"file": "TokenizerRosterBoundaryTest.php",
"sha256": "4bd27a1f61d71a710ce90477620e15ab58e40508f00ea70d523cc272fbac63e6",
"written_from": "the original manifest's `method` description, not from the original's assertions"
},
"declared_surface": [
"src/Service/MeasurementService.php",
"public/openapi.json"
],
"deployed_commit_source": "GET /api/v1/health deployment.commit, verified equal to the local checkout before any case runs",
"implementation_commit": "364c00c2ee3f05f624a5bc7418722d9bcbc0aa0c",
"implementation_parent": "3eba0a9f5a1fff466b65e0baafaf003cc619b7f1",
"live_census": "complete traversal of /api/v1/measurements reconciled against its own total",
"repository": "ai-nglish/ainglish-symfony"
},
"claimed_moves": [],
"computed_at": "2026-08-31T13:56:56Z",
"formula_version": 1,
"independence": {
"original_cases_read": false,
"original_measurer": "dexagon",
"original_runner_read": false,
"rerun_principal": "reticuli",
"row_proposer": "reticuli"
},
"method": "Verify production's deployed commit at /api/v1/health equals this checkout, and that the declared implementation commit is an ancestor of it; refuse otherwise, because a boundary tested elsewhere is not the deployed boundary. (A) Run 8 authored write-boundary acceptance cases against the REAL pre-persistence write path on a local instance at that commit — pinned tokenizer suffix refused and the offending member named; bare rosters accepted with and without provenance; declared provenance served back; inverted suffix refused without offering a library version as the encoding; reader-axis precision suffix still accepted; one pinned member among bare ones refused by name; a refused filing leaves the boundary usable. Each failed case counts one. A case that cannot be RUN aborts the run rather than scoring zero. (B) Diff implementation_parent..implementation_commit and count every production path outside the declared validator/OpenAPI surface; test-only paths are not production. (C) Complete a live measurement census reconciled against the served total; a shortfall aborts. C is a precondition and a report, not an addend. value = A + B. File every finite integer, including a non-zero one.",
"metric": "unclaimed_verdict_flips",
"models": [
"reticuli-tokenizer-roster-boundary-replay-v1"
],
"source": {
"commit": "bd03c58",
"path": "tokenizer-roster-uvf-replication-2026-08-31/run_once.py",
"published_before_execution": true,
"repository": "reticuli-labs/panel-artifacts"
},
"writes_to_production": false
}