gate_w1 amendment 1 (draft — ceremony pending): family-B DI bands (#164)

* gate_w1 amendment 1 proposal: the family-B DI bands (forensics-1 Q4)

DRAFT proposal (ceremony step 1 of proposal -> referee -> fixes ->
verification -> ratify -> flip). gates.yaml is UNTOUCHED; no threshold moves.

W1 forensics 1 Q4 (runs/gate_w1_forensics1_v1.json, registration 4951218279,
grading 4951430002) established, against the currently locked contract blob
cd6411d, that the 8 family-B DI age-composition prevalence bands are
unclearable by any contract-consistent candidate: the gate scores an M4
work-disability point-prevalence against the SSA disabled-worker beneficiary
STOCK (DI ASR Table 19) across a concept bridge it never defined. The concept
delta dominates (share 0.595; +21.3pp duration-accumulation vs +2.6pp M4 hazard
shape at 60-FRA), and all 8 bands miss by 2.9x-21.9x their tolerances. Because
family B is a conjunction, gate_w1 as locked is unpassable (faithful-candidate
gate OC structurally 0).

The proposal (docs/amendments/gate_w1_amendment_1_family_b_di_bands.md) analyses
two options and recommends option (a): demote the 8 DI bands to report-only with
machine reason concept_bridge_undefined_di_stock, leaving family B gating the 2
disability-conversion M4-simulated margins. Option (b) (re-anchor to a
transportable work-disability prevalence) is deferred: no defensible anchor is
archived, and the SSA-native re-anchor is blocked by the unarchived Supplement
4.C2 insured denominator.

OC consequence: family A is untouched, so its half-normal characteristic is
byte-identical (p_seed 0.922 / p_gate 0.9481, the 8 DI cells absent from the
family-A OC machinery); the overall gate OC moves from a structural 0 to the
family-A characteristic 0.9481 on the residual 57-cell surface (65 -> 57 gated,
67 -> 75 report-only).

No-self-rescue: candidate 1 (runs/gate_w1_candidate1_v1.json, PR #162) stands
FAIL under both surfaces -- it fails family A (0/5 seeds), the 2 RETAINED
conversion cells (dev 8.30/8.07 vs tol 1.89/1.91), and family C -- so the
demotion rescues nothing; the amendment is prospective; the forensics evidence
is train/frame-side.

tests/test_gate_w1_amendment1_proposal.py (12 tests, always-runnable, artifact
tier) binds every proposal figure to the committed artifacts; tier manifest +
README refreshed CI-equivalent (artifact 834 -> 846, total 2528).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* gate_w1 amendment 1 fixes round: referee findings (comment 4951701300)

Adversarial round (PR #164 comment 4951701300, AMEND THE AMENDMENT) required
extending the family-B demotion to all 10 gated cells; the 2 conversion margins
fail the same candidate-independence test on committed evidence.

A (blocker): all 10 family-B cells demoted to report-only. Conversion cells take
concept_bridge_undefined_di_stock (same undefined DI-stock numerator, read at the
FRA boundary) + conversion_level_match_never_certified (m4_disability_v1.json
conversion_validation: ratio 0.267/0.322, 'never a level match'; window floor
>=12.21/12.59 = anchor 14.1/14.5 - tol 1.89/1.91). Family B gates nothing; OC
returns to 0.9481 x I(family C) on the residual 55-cell surface (65->55 gated,
67->77 report-only). Sections 1/3/4/4a/5/7/8/9 + ledger updated; option (b)
conversion-anchor deferral row added.

B: bound the operative flip text -- the section-7 enumerated demotion list, the
section-7 roll-ups (55/77), and the section-8 history figures are parsed and
cross-checked against the ledger/artifacts; proven to FAIL under the referee's
named mutations. De-vacuoused the prose machine-reason assertion (checked outside
the ledger fence).

C: 0.595 restated as the aggregate with per-band range 0.023-0.891; CPS-ASEC
option-(b) rationale corrected to built-from-frame (not the conditioning rule).

Tier manifest refreshed CI-equivalent (artifact 846 -> 853; total 2535).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

Author: MaxGhenis