Any of the following is shown: recomputing from the committed rows yields any registered quantity different beyond 1e-9; the thresholds recomputed from the committed calibration scores by the contract rule differ from those recorded; the freeze commit 6ac65de does not precede the first E9 score commit; any measurement item overlaps a calibration, stress or scouting partition; the declared part of freeze/protocol.json no longer hashes to the digest freeze.json records; or the verdict run/analyze.py applied differs from the rule committed at 6ac65de.
Consequence REJECTThis is the condition and consequence recorded in the registry. The vocabulary this is published in defines what each consequence commits the author to.
Exactly the 1,000 rows committed at experiments/e9/results/observations.jsonl, set-equal to the frozen list freeze/items_measurement_mosscap-test.csv, under contract E9-2026-09-18 (frozen, sha256 43811798…). The freeze commit 6ac65de (2026-09-18) precedes the first E9 score commit. The verdict-rule limitation: the SESOI (0.05) and the equivalence margin are in the frozen contract, but the rule that combines them into DISCREPANT lives in run/analyze.py. That file was committed in the freeze commit and is byte-identical since, but the rule is neither declared in contract.json nor rendered into PREREG.md's prose. Correction C1 asks for claim-critical choices to live in the contract; this one does not, and the verdict stands on the committed code, not on the contract alone. Further limits, as RESULT.md states them: the pool was selected, as the widest scouting width among complete candidates, for intermediate marginals; scouting items are disjoint from measurement items, but the result describes a selected pool, not pools in general; the interval resamples measurement items with thresholds held fixed, and omits calibration uncertainty; the operating point is declared, not deployed: on 400 seemingly-toxic benign prompts G2's false-positive rate is 0.2675, reported and never deciding; G2's fine-tuning corpus could not be verified, and G2 has no licence file at the pinned revision (apache-2.0 is declared in card metadata only); run/admit.py appended a results block to freeze/protocol.json, so the file is not byte-immutable after freeze; the declared part still hashes to the frozen digest, and the repository graph records the append as a D5 STOP finding; one analyst ran every step, and re-running the committed scripts is replay, not reproduction. Both guards are under 1B, ungated and pinned, loaded under the 2026-09-06 host exemption. E2's guards were not loaded. This is not an E2 result and does not change CC-005.
Repairs declared unavailable in advance; using one after a failure would breach the recorded commitment.
- do not re-threshold, re-calibrate, change the 0.05 budget or the comparator and direction, and report the new numbers as this result
- do not state that a discrepancy greater than 0.05 is established; the interval's lower end is 0.0472
- do not merge exploratory intervals (nested recalibration, level-cluster or operating-point sweeps) with the preregistered item-bootstrap interval, or substitute one for it
- do not change the SESOI, the margin or the verdict rule in run/analyze.py and re-derive the verdict
- do not add, swap or re-admit a pool after outcomes are known and report it as E9
- do not carry these numbers to E2's guards, to a deployed stack, to either vendor, or to pools in general
- that guard pairs in general depart from independence, or in which direction
- anything about a deployed stack, a routing policy, or either guard's vendor
- that either guard, or the pair, is safe or unsafe
- the size of the discrepancy on other pools, other thresholds or other benign populations
- a discrepancy greater than the 0.05 SESOI; only one different from zero is established
- an E2 result; CC-005's E2 remains untested