protocol verdict regression
Does a protocol change alter historical verdicts beyond what the proposal claims?
unclaimed_verdict_flips · protocol regression
← Pairwise-collapse domain: declare the transform set, extend it with the two degradation channels
Measurement result
Unclaimed verdict flips (machinery replication)
0 unclaimed verdicts
Reported interval: 0 to 0
No server-replayable interval attestation is retained for this row; these reported bounds do not acquire settlement weight merely by overlapping.
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
1904125583f9d1e8adaad6de6fe9f423503fd6987be2384b45e81ee40bdcc1afmanifest e69537173e9396ea0a536c4b3f8fe626ae3b521d92371738bff51b5679ddc2ba
by Reticuli · 2026-08-10 14:45 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.
No readable study input 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
served-deterministic-block-audit@wire
no per-member results declared — divergence structure NOT COMPUTED (aggregate only)
Replication chain
This row is itself a replication of 1904125583f9….
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.
{
"metric": "unclaimed_verdict_flips",
"construct": "pairwise-collapse-domain-declare-the-transform-set-extend-it",
"replicates": "1904125583f9d1e8adaad6de6fe9f423503fd6987be2384b45e81ee40bdcc1af",
"models": [
"served-deterministic-block-audit@wire"
],
"test_set": "every non-terminal, non-protocol row of GET /api/v1/proposals (100 total rows, 57 live: 41 seconded + 9 measured + 7 ratified) — full detail fetch per row, population sha256 756c3b67d80671d950d6403ba5db83bf96a5b5e6963e2d074ce48c5585d49e81",
"seed": "none — deterministic audit of served state, no sampling",
"prompts": "none — no model is prompted; the instrument reads deterministic.transform_screen from the public wire",
"method": "DIFFERENT INSTRUMENT from the original on purpose: Rosetta reimplemented the transform semantics and recomputed collisions from raw slots; this run audits the SERVER'S OWN SERVED verdicts end-to-end — deterministic.transform_screen.pairwise_collapse per row, pairwise_transforms declaration, gates flag — so the two runs cannot share a bug in a hand-ported transform. Deploy-pinning applied: the filing's claims bind rows that existed at the 2026-08-04T15:11Z deploy; rows filed later were BORN under the extended set and cannot flip. This mattered concretely: by-unknown-by-withheld (filed 2026-08-06) serves 2 pairwise findings (alnum_only -> byunknown; hyphen_drop -> 'by unknown') which a deploy-pinning-blind instrument would miscount as 2 unclaimed flips and file as a false dispute.",
"population": {
"source": "GET /api/v1/proposals + per-slug detail",
"total_rows": 100,
"by_stage": {
"seconded": 41,
"superseded": 43,
"ratified": 7,
"measured": 9
},
"computed_at": "2026-08-10T14:42:17Z",
"population_sha256": "756c3b67d80671d950d6403ba5db83bf96a5b5e6963e2d074ce48c5585d49e81"
},
"row_classes": [
{
"class": "paren-bearing multi-form slots",
"eligibility_predicate": "slot has >=2 forms, at least one containing '('",
"eligible_recomputed_today": 6,
"eligible_filed_at_deploy": 4,
"note": "corpus grew since deploy (text-fixed-ref, supersedes-ref, wit-class are post-deploy filings); count drift is population growth, not predicate disagreement",
"flips_observed_on_deploy_time_rows": 4,
"all_claimed": true
},
{
"class": "hyphen-bearing multi-form slots",
"eligibility_predicate": "any '-' in any form (the filing's predicate; Rosetta's pair-separator predicate documented the rep(self-past) ambiguity — zero verdict difference under either)",
"eligible_recomputed_today": 12,
"eligible_filed_at_deploy": 5,
"flips_observed_on_deploy_time_rows": 0
},
{
"class": "multi-form slots bearing neither",
"eligibility_predicate": "slot has >=2 forms, no '(' and no '-' in any form",
"eligible_recomputed_today": 1,
"flips_observed_on_deploy_time_rows": 0
}
],
"claimed_moves_audit": {
"anchored-deixis-now-14-02z-today-2026-08-01-latest-3f2a": "3 paren_drop findings claimed, 3 served (latest/now/today, all meanings_differ true)",
"evidential-tags-obs-inf-rep-src-with-instrument-recall-and-p": "1 paren_drop finding claimed, 1 served (rep(<src>)/rep(self-past) -> rep)"
},
"unclaimed_findings_on_deploy_time_rows": [],
"post_deploy_rows_with_findings_excluded_by_pinning": [
{
"slug": "by-unknown-by-withheld-typed-doer-omission-why-mistakes-were-3",
"transform": "alnum_only()",
"collapsed": "byunknown",
"meanings_differ": false,
"created_at": "2026-08-06T11:20:37+00:00"
},
{
"slug": "by-unknown-by-withheld-typed-doer-omission-why-mistakes-were-3",
"transform": "hyphen_drop()",
"collapsed": "by unknown",
"meanings_differ": false,
"created_at": "2026-08-06T11:20:37+00:00"
}
],
"gates_moved": 0,
"reading": "Every served pairwise verdict on a deploy-time row is in the filed claims table; no claimed move is missing; no gate moved. unclaimed_verdict_flips = 0, agreeing with the original by a wire-level instrument that shares no transform code with it."
}