gate_w1 amendment 2 (draft — ceremony pending): family-A concept cells (#169)

* gate_w1 amendment 2 proposal: the family-A concept cells (forensics-2)

DRAFT proposal (ceremony pending). Demotes 7 structurally-unclearable cells to
report-only: the C1 fingerprint (fingerprint_reversal_not_realized), the two
18-24 participation cells (population_concept_delta_head_spouse_universe, a
22.1pp head/spouse-vs-all-person gap), and the four 65+ marital/coresident cells
(cohort_vintage_hazard_frame_mismatch, divorce over-accumulation -- a
cohort-vintage hazard/frame mismatch; six permitted-lever construction-attempts
each fail). Zero threshold movement; gates.yaml untouched.

Family-A faithful OC recomputes 0.922/0.9481 -> 0.9344/0.9623 on the residual 47
cells (removing 6 family-A cells, unlike amendment 1's invariance); overall gate
OC 0.9623 x I(C2) on the 48-cell surface (55 -> 48 gated). No-self-rescue is
over-determined: both candidate 1 (PR #162) and candidate 2 (PR #167) still fail
family A (0/5 seeds on the 47) AND family C (C2 tau 0.333) -- the rescue set is
empty. Consistency bindings in tests/test_gate_w1_amendment2_proposal.py string-
bind the section-7 flip text/roll-ups and section-8 history (amendment-1 fix-B
standard, mutation-checked). Tier artifact 879 -> 897 (CI-equivalent recount).

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

* gate_w1 amendment 2 fixes: per-cell grounds + retained-surface candor (referee 4953763322)

Adversarial referee round (PR #169 comment 4953763322) ruled AMEND THE AMENDMENT;
demotion set of 7 survives, grounds and candor corrected. Zero threshold movement;
gates.yaml untouched; OC numbers unchanged (referee reproduced them exact).

F1 (per-cell truth): the blanket "no candidate can clear any of the 7" was false --
candidate 1 PASSED coresident_spouse.65+|female 4/5 seeds. The 65+ quad now carries
TWO machine reasons: cohort_vintage_hazard_frame_mismatch (married pair +
coresident-65+|male, the stationary ceiling ~0.577 F / ~0.717 M the deployment
cannot reach; married-65+|female caps 2-3/5 by ceiling-vs-window, Q1 entry-0 0.5767
vs Q6 entry-0.58 0.5728) and scored_duplicate_of_demoted_married_quantity
(coresident-65+|female, deployed coresident/married ratio 1.0, straddles an easier
window; demoted on duplicate/composition-blind grounds not impossibility). Per-seed
pass records added to the doc + ledger + bindings; the c1 4/5 pass stated plainly.

F2 (candor): the 48-cell surface is stated NOT KNOWN PASSABLE -- Q7 graded REFUTED
for hh_size (all 5 cells 0/5 both candidates; "not closable by these two entry-state
levers alone"); C2 is one bit-identical measurement (deployed cap_150k 16.7y vs
Smith rank-4 1y; corrected-tail tau -1/3; robust only for the elim<->+2pp pair).
Series forecast added: amendment-3 risks (5 hh_size + C2 cap_150k) pre-named, each
reopenable only via the same forensics-then-ceremony standard.

F3: section-3 sigma range corrected 3-8 -> 2.0-6.6 (0.11-0.44 ln vs 0.027-0.072
sigma; sub-3sigma end = the female cells that sometimes pass).

F4: the referee's per-band-entry (0.4228/0.6004), entry-55 (0.4951/0.6090), and
max-entry-bound construction-attempts incorporated into the 4c table (cite 4953763322).

F9: section-4a Mermin sentence rewritten; C1 empirical legs qualified as one
bit-identical measurement.

Tests: 24 bindings (from 18), mutation-checked incl. the corrected sentences.
Tier artifact 897 -> 903 (CI-equivalent recount).

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

* gate_w1 amendment 2 fixes 2: per-cell truth for §2c/§3.1 + MM4/MM6 bindings (verification 4954135376)

The verification round (comment 4954135376, verdict FURTHER FIXES) ruled the
scored_duplicate_of_demoted_married_quantity ground PRINCIPLED but caught two
per-cell-false survivors introduced/inherited by the fixes commit, plus a stale
body and one hh_size count (note N2).

- §2c: the fixes commit re-instantiated the F1 blanket ("the 65+ cells cannot be
  cleared by any permitted entry-state lever") — false for
  coresident_spouse.65+|female, which candidate 1 clears 4/5 because the ~0.577
  stationary ceiling sits INSIDE that cell's lower window on 4 of 5 seeds
  (lower edges [0.5478, 0.5759, 0.5717, 0.5769, 0.5813]). Rewritten to per-cell
  truth: ceiling-below-window holds for the married pair + coresident male; the
  coresident-female window straddles the ceiling, which is why its ground is
  duplication, not unreachability. Bound by
  test_section2c_no_blanket_65plus_impossibility_coresident_inside_window (MM4).

- §3.1: dropped marital_share.never_married.25-34|male from the "5/5 for both
  candidates" list — candidate 1 clears it 1/5 (seed 1 0.1707 vs tol 0.192,
  flags [T,F,F,F,F]). The complete gate-eligible 5/5-fail retained set is
  hh_size_share.{1..5plus} + marital_share.married.25-34|male +
  earnings_participation.35-44|female; never_married is retained a fortiori.
  Bound by test_section3_1_5of5_fail_list_per_cell_true_excludes_never_married
  (MM6).

- §4c: folded the verifier's principled ruling + deployment-contingent guard into
  the duplicate ground — ratio==1.0 is a machine-checkable identity per candidate
  (both deployments' spec_resolutions regenerate coresident_spouse as
  (terminal marital_state == married), bit-identical); the ground dissolves for a
  future candidate modeling coresidence separately, and re-gating then requires
  the standing forensics-then-ceremony path. Cites comment 4954135376.

- N2: reconciled the amendment-3 hh_size risk count to FOUR (sizes 1/3/4/5+) in
  §1/§5/§8/§9 prose — Q7's joint lever clears only size-2. All five hh_size cells
  still fail 5/5. Bound in test_c2_record_bound_and_amendment3_forecast.

Frontmatter + §11 checklist updated to record the verification round and this
fixes-2 revision.

Bindings 24 -> 26; artifact tier 903 -> 905, total 2,601 -> 2,603
(tests/tier_counts.json + tests/README-tiers.md, enforced by test_tier_policy).
Mutation battery re-run against the corrected sentences: prior FM1-8 / MM1-2 stay
caught, and the MM4 / MM6 analogues the verification round found unbound are now
caught. gates.yaml byte-identical to origin/master; the draft moves nothing.

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

---------

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

Author: MaxGhenis