End-to-end 20k A/B (seeds 0/1/2): depth-balancing gives −5.8% maple / −3.2%
harbor with OVERLAPPING arms — far less than the −11/−12% seed-floor probe,
because the 20k search erodes most of the seed advantage via divide/undivide
mutations (unlike leaf-sharing's structural leaf-count cut, which the search
cannot undo). Baseline reproduces §12.2 (maple 137.0 vs 136.0, harbor 74.0).
Promise is the additive floor with leaf-sharing (probe: bal+sh3 << share3-alone);
the decisive test is erc.7 synergy. Keep depth_balanced default OFF; close erc.4,
advance erc.7.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
_grow_leaves grew a random caterpillar, so equal-target rooms landed at
wildly different binary-tree depths — the depth-driven size maldistribution
Diagnostic B (§13.2) localized (same code at 0.05x and 14.7x target). The
depth_balanced flag always splits a shallowest leaf instead, growing a
near-complete tree so the proportion-aware sizing pass hits each target with
cut fractions near their proportional value.
Floor probe (diag_depth_balance.py): depth spread collapses 7->1, the giant
ratio falls (maxR 12->8 harbor / 16->6 maple), %undersize 54->25 / 42->22,
and the achievable floor drops -12% harbor / -11% maple at EQUAL leaf count.
Additive with leaf-sharing (bal+sh3 beats §13.3 share3-alone). Default OFF,
214 tests pass; threaded through driver.search/search_staged and exposed via
DEPTHBAL in run_staged_search.py. End-to-end 20k A/B running.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replace the area-derived share recovery with explicit, type-guarded per-leaf
multiplicity: construction stamps leaf.share=k and leaf.share_type=code; the
fitness (graph.leaf_share) honours k only while leaf.type==share_type, so any
retype/undivide auto-invalidates a stale share — no operator resets, and a
small leaf cannot retype its way into covering rooms it does not provide. Two
Node fields survive the whole search via deepcopy (genome.decode is unused in
the hot path); .dom emits `share` only on a live shared leaf.
This closes the §13.3 missing-fail leak: floor probe missing 17–44 → 0, and the
achievable floor drops −39% harbor (120.3→73.3) / −32% maple (194.7→133.0) with
no re-emergence as size fails.
Flag threaded through driver.search/search_staged → constructive_topology /
lift_base_to_storeys, exposed via LEAFSHARE/LEAFSHAREFAC in run_staged_search.py
(injects the objective into inner-loop + final-score fitness so both A/B arms
share one programme dir). run_leafshare_ab.sh runs the staged 20k A/B.
Smoke-tested end-to-end (harbor, factor 3, re-score OK). 214 tests pass;
default-OFF reproduces baseline.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Same-code rooms collapse into fewer, larger SHARED leaves so the ~1.8/leaf
shape tax (§13.1) is paid once per group. Multiplicity k is recovered from
area (k=clamp(round(area/target),1,max_share)) — no genome change — and used
in two default-OFF sites: graph.check_space_counts counts coverage (Σk vs
req.count) so one leaf covers several rooms without a missing fail, and
fitness.quality_size centres on k×target (σ scaled by k). Construction:
operators._share_rooms groups instances; _size_divisions_from_targets sizes
shared leaves to k×target via leaf_mult.
Floor probe (experiments/diag_leaf_sharing.py, harbor+maple, seeds 0/1/2,
+innerloop): total fails −27% harbor / −16% maple at share3, shape factors
fall ~linearly with leaf count (confirms §13.1). Cap: 17–44 missing fails
leak because depth maldistribution (§13.2) keeps shared leaves below k×target
so round() undercounts; inner loop can't close it. Net still positive.
Default-OFF reproduces baseline exactly (214 tests pass). Driver plumbing +
staged 20k A/B remain; §13.3 records the next design fork.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The "56% empty plot" is a misreading: sized rooms already hold 1.4-1.5x
their aggregate target area; ~46% of plot is circulation, not claimable
void. Size fails are depth-driven MALDISTRIBUTION — the same type/target
leaf lands 0.05x..14.7x by binary-tree position. The inner loop cannot
repair it (frozen topology, budget-80 size fails move only -1.6/-3.7).
=> Falsifies plot-fill-as-claim-void: re-scope erc.4 to depth-balanced /
giant-splitting construction; deprioritise erc.6 (inner-loop term, wrong
DOF). Reinforces erc.3 leaf-sharing for the starved tail.
Script: experiments/diag_slack_localization.py (self-contained evidence).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Controlled synthetic sweep (maple-court, room set fixed, circ_divisor 2->9)
shows per-leaf shape-fail is FLAT vs slicing density (1.72-1.94, no trend)
while TOTAL shape fails track leaf count linearly (139->116). Crinkliness
dominates (~0.8/leaf) and is flat; cuts are already squarest yet still pay
~1.8 fails/leaf. Floor is INTRINSIC to per-leaf slicing, not cut quality.
Verdict: prioritise leaf-sharing (erc.3); deprioritise compactness-cuts
(erc.5 -> P4). Adds experiments/diag_leaf_shapefail.py.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add interior-O courtyard seeding (ld2, construction lever, P1) and a
Tier-3 failure-directed topology-repair operator (71d + subtasks) as
children of the erc Phase-8 epic. Diagnosis from the 3M harbor-house
run: 27 fails dominated by 13 crinkliness + 7 size; ~16 are invariant
to split ratios (landlocked rooms, fitness.py:339), so the lever is
construction/topology, not the inner loop — consistent with erc's
thesis.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add epic homemaker-py-erc (lower the geometry/shape floor) with two
read-first diagnostics gating four floor-lowering experiments, plus the
island-model search bet (psk). Diagnostics decide leaf-sharing vs
compactness-cuts (A) and construction-fill vs inner-loop-fill (B).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The constructive seeder was never nondeterministic: _assign_adjacency_aware
ends every max/min with a unique leaf-idx tiebreak and uses set unions only
for membership, so iteration order never leaks. constructive_topology(seed=0)
is byte-identical across processes for every example programme. The cited
"sig 4480 vs 16064" was a measurement artifact — Python's builtin hash() of a
str is salted per process (PYTHONHASHSEED), so an identical signature hashes to
different ints run-to-run.
The real run-to-run noise was parallel-only: driver._run_batch admitted futures
via as_completed (completion order), and admit() is order-sensitive (accrues
n_evals per result; keeps the first individual of an equal-key tie as best). A
long parallel run diverged 167 vs 161 fails (maple seed 0). Fix: admit futures
in submission order (block on each result in turn; all still run concurrently),
reproducing the serial admission sequence. Two workers=4 runs are now
byte-identical. Serial (workers=1) was already byte-for-byte reproducible.
Per-seed numbers are reproducible only at a fixed worker count; serial != parallel
is expected (children/iteration 1 vs n_workers changes batch granularity).
- driver: iterate futs in submission order, not as_completed
- test: test_search_parallel_is_reproducible (fails on pre-fix, passes on fix)
- DESIGN.md §12.4: corrected the reproducibility note
Closes homemaker-py-xcy
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
End-to-end A/B (maple div6/div8, harbor div6, seeds 0/1/2, 20000 evals) vs the
§12.3 div=3 baseline: every arm within ±1.7 of baseline (maple 136.0 -> 137.0 /
134.3; harbor 74.0 -> 75.3), inside the measured ±3 noise floor with large
per-seed spread. Coarsening the circulation spine lowers the raw shape floor but
raises access/adjacency by as much; end-to-end they wash out. Verdict: keep
circ_divisor=3; the maple/harbor residual is the geometry floor of the slicing
representation at this room density — neither search machinery (§12.3) nor
construction granularity (§12.4) moves it beyond noise.
En route: the div=3 control (129 vs §12.3's 126) exposed a reproducibility bug —
_assign_adjacency_aware iterates id()-ordered sets of Node objects, so the
constructive seed is nondeterministic across processes (~±3 fail noise). Filed
homemaker-py-xcy (P2); per-seed ledger numbers are not reproducible, only
multi-seed means.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Threads circ_divisor (default 3 = unchanged) through
operators.constructive_topology/lift_base_to_storeys and
driver.search/search_staged; env CIRCDIV in run_staged_search.py. Adds
experiments/run_c3g_ab.sh.
Motivation (DESIGN.md §12.3 diagnostic): the maple shape residual is
over-granular construction (73 small leaves -> crinkliness+size). Cheap raw-seed
probe: a coarser spine lowers the SHAPE floor (maple 135->110, harbor 83->66)
but raises access/adjacency, leaving the raw TOTAL floor flat-to-worse. Because
§12.3 showed shape is the HARD residual and access/adjacency are cheap to
repair, only an end-to-end A/B settles whether trading them pays — this is the
plumbing for that run. Tests green (default path byte-identical).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Per-leaf breakdown of maple-court constructive seeds (6 seeds) overturns the
earlier 'shape-aware placement' handoff guess: shape fails are UNIFORM
(~68/73 leaves fail) at only 0.44 plot utilisation, dominated by crinkliness
(perimeter/area) then size (undersize). So the residual is neither a room->leaf
placement mismatch (no well-shaped leaves to place into) nor density-bound — it
is over-granular construction (73 small leaves for 52 rooms). Corrected the
§12.3 verdict accordingly and filed homemaker-py-c3g (construction granularity /
leaf-shape lever) as an unproven, must-be-A/B'd hypothesis.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
24-run sweep (maple-court + harbor, seeds 0/1/2, 20000 evals): M3 reassociate
and the shape-feasibility filter are both neutral-to-slightly-worse vs the
§12.2 baseline (maple 136.0 -> 139-140, harbor 74.0 -> 77-78). Baseline controls
reproduce §12.2 exactly, so the negative is real.
Verdict: the Phase-7 residual is the geometry/shape floor of the constructed
slicing layouts, not reachability/feasibility-bound — third independent negative
on search machinery (§11.4/§11.5/§12.3) vs four construction/seed wins
(§11.2/§11.6/§11.7/§12.2). A full canonical Polish rewrite is not justified: its
one testable promise (associativity reachability) was tested and did not pay.
Both operators kept default-OFF.
Closes 9gp.1, 9gp.2, 9gp; epic leu (Phase 7) auto-closed (3/3). Adds the
reproducible sweep harness experiments/run_9gp_ab.sh.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Land the two evidence-supported parts of the re-scoped 9gp capstone as
operators on the existing decoded Node tree (no Polish-expression rewrite),
each default-OFF and measured against the §12.2 leu.2 baseline.
9gp.1 shape-feasibility pre-filter: operators.predicted_shape_fails lays a
topology out at its proportion-aware target geometry and counts shape fails
(size/width/proportion/crinkliness); driver._evaluate prunes clearly-infeasible
topologies before the inner loop (1 eval vs ~80), guarded so nothing that could
beat the incumbent is discarded. search/search_staged feasibility_filter,
feasibility_max_shape_fails (env FEAS/MAXSHAPE), default OFF.
9gp.2 M3 Wong-Liu reassociate: operators.mutate_reassociate adds associativity
(a|b)|c <-> a|(b|c) on same-orientation live cuts — the canonical-slicing move
missing from swap(M1)/rotate(M2), attacking the §11.4/§11.5 reachability
bottleneck. enable_reassociate (env REASSOC), default OFF (weight 0 -> baseline
byte-identical).
Unit tests (operators + driver) green, full suite 211 passed; maple-court smoke
run clean under native fitness. A/B sweep handed off per the plan; DESIGN.md
§12.3 documents the design and the pending measurement.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Size each constructive-seed cut from leaf TARGET areas (division=[f,f] gives
left area-fraction f) and pick each cut's rotation for child squareness — both
derived from target dims, topology/type assignment untouched. Area-only
regressed (slivers); rotation choice is what makes it pay.
End-to-end (20000 evals, 3 seeds, staged): harbor 85.3->74.0 (-13%, best 69),
maple-court 151.7->136.0 (-10%, best 126). PROP=0 reproduces the §11.7/§12.1
baselines exactly. programme-house regresses at fixed budget (deeper local
optimum walls off the undivide restructuring path) but a budget sweep shows
it's convergence speed, not a worse asymptote (PROP=1 reaches 1 fail at 150k).
Default-on (seed_proportion_aware=True, env PROP=1).
cq1: n_storeys now honours storey_minimum, not just level: keys — programme-house
(storey_minimum:2, all rooms level:0) was seeded one storey short and fell
through to plain search. New programme.storey_minimum()/n_storeys_for();
driver.search passes min_storeys to the seeder; search_staged routes on the max.
No-op for harbor/maple; programme-house single-stage 8.0->5.0.
New maple-court best (126) saved as generated.dom. 204 tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
_assign_adjacency_aware gains fixed_circ (seed the connected-dominating-set from
given circulation leaves) and secondary-adjacency-aware room placement: codes
with the most non-c adjacency requirements are placed first, each onto the open
slot satisfying the most of its requirements against already-typed neighbours
(clustering k1<->da1, da1<->o). lift_base_to_storeys(reqs, adjacency_aware=True)
grows the upper-floor circulation spine off the inherited vertical core and
assigns rooms around it; threaded through driver.search_staged
(seed_adjacency_aware) and run_staged_search.py (ADJ env).
End-to-end staged harbor, 20000 evals, mean total fails over 3 seeds:
ADJ=0 99.0 (reproduces the §11.4 staged lex baseline exactly), ADJ=1 85.3
(-13.7, -14%; best 78). New best harbor configuration overall: staged baseline
99.0 -> single-stage adjacency-aware (§11.6) 90.7 -> staged + adjacency-aware
lift 85.3. Staging and adjacency-aware seeding compose.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
operators._assign_adjacency_aware spends ~one extra leaf per three rooms on a
greedy connected-dominating-set of circulation leaves (read from the geometric
leaf_graph, type-independent), so every room borders a connected circulation
spine and adjacency-to-c + access are satisfied by construction. Default-on via
constructive_topology(adjacency_aware=True), threaded through
driver.search(seed_adjacency_aware) and run_search_scaled.py (ADJ env).
End-to-end single-stage, 20000 evals, mean total fails over 3 seeds:
harbor 110.0 -> 90.7 (-17.5%; ADJ=0 reproduces the §11.2 105 baseline exactly),
programme-house 12.3 -> 9.3 (-24%). Adjacency-aware single-stage harbor (mean
90.7, best 85) beats the §11.3 staged best of 95 — the first Phase-6 fail-count
reduction from seeding. Follow-ups (lift_base_to_storeys, secondary adjacencies)
filed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
genome.signature: ratio-invariant structural topology hash (per-storey tree
shape + cut orientation + leaf types), the cheap stand-in for the 9gp canonical
encoding. driver gains niche_by_signature (one individual per topology, replaces
the fitness-scalar dedup) and restart_patience (soft restart: keep elites,
refill with fresh seeds); SearchResult gains n_distinct_signatures /
diversity_history / n_restarts.
Diversity criterion MET (final-pop distinct ~5/16 -> 16/16). Gate NOT met:
blank-slate programme-house mean fails 12.3(legacy)/12.7(niche)/13.0(restart)
over 3 seeds at 20000 evals; harbor staged 95/94/108. Niching is a tie within
seed noise, restarts strictly worse — falsifies the premise that the
fitness-scalar dedup causes premature convergence. Both flags default-off,
kept for reuse. Epic c4c complete.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Implement a graded proximity comparator key (-n_fails, grade, fitness) behind
a default-off use_grade flag: fitness._leaf_grade / score_with_grade sum
f/FAIL_THRESHOLD over failing per-leaf quality factors; scalar fitness and fail
count stay untouched so the inner-loop 0.5^n cliff (§5.4) is unaffected (0/9
regression check: PASS). Read once per child in driver._evaluate off the
already-optimised tree; threaded through search_staged (Stage 2 only).
Harbor staged A/B (20000 evals, seeds 0/1/2): lex 95/96/106 (mean 99.0) vs
lex+grade 99/98/102 (mean 99.7) — grade wins 1/3, no plateau escape. Premise
falsified: within a fixed fail-tier 0.5^n is constant so fitness still spans
~6 orders of magnitude; grade above fitness displaces that working signal.
Verdict: reject; lexicographic (-n_fails, fitness) stands. Flag kept default-off
for reproducibility / possible reuse as a §11.5 diversity signal.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Search the genome in causal dependency order. Stage 1 evolves a single-storey
base over the level-0 room set (programme auto-derived to a tempdir), ranked
with a substrate-readiness bonus (reserved core × divisible capacity) so the
base is selected as a good substrate, not just a good ground floor (anti-§4.2).
Stage 2 lifts the best base into a full multi-storey design — preserving the
inherited core, instantiating each upper storey's required set by construction —
and searches the deltas with the base mutable at low probability (base_p=0.15).
New: programme.{n_storeys_required,partition_rooms_by_storey,write_stage1_programme},
graph.substrate_readiness, operators.{lift_base_to_storeys,_pick_weighted_by_storey},
base_p threading, driver.search rank_bonus_fn/seed_factory/base_p hooks +
search_staged orchestrator, experiments/run_staged_search.py, tests/test_staging.py.
Result (harbor, 20000 evals, seed 0): staged 95 fails vs single-stage 105
(-10, -9.5%), gain in crinkliness 27->18 + edge 12->8. Anti-bungalow confirmed
(Stage-2 core moves all noop — core inherited, not carved). Programme-house
regression PASS (warmstart-2f4 still reaches whole-pop 1-fail).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Make the required programme room set a constructive invariant instead of
something the topology search must stumble onto by random divide+retype.
- operators.constructive_topology: bootstrap seeder that sizes each storey to
its required rooms (partitioned by level; level-free rooms distributed),
+1 core C and +1 O per storey, then assigns types. Stochastic for population
diversity. Wired into driver bootstrap when the programme has required spaces.
- operators.mutate_place_missing: repair op that inserts a missing required
space by dividing a host leaf into [room | remainder]. Lex-safe host ranking
(generic O first, never displace a required room); honours required level.
Weight 2.0 in the mutation mix; noops cheaply once the set is complete.
A/B on harbor-house (20k evals, seed 0, identical config):
old random-bootstrap 133 fails (103 missing, 77%)
new constructive 105 fails ( 12 missing, 11%) -21% total, missing-stack
collapsed; seed head-start 163->139.
§4.10 regression PASS: warmstart-2f4 still reaches a 1-fail population at 50k.
Verdict (DESIGN.md §11.2): construction is necessary and reframes the
bottleneck to quality-fail packing of a complete dense design (crinkliness/
size/access/edge) -> unblocks §11.3 staging, motivates §11.4 graded objective.
Follow-up filed (homemaker-py-s44): adjacency-aware seeding.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Built examples/harbor-house-l0/ (10 explicit level:0 codes, 13 instances,
single-storey constraints) and ran the memetic search from a bare plot. Best
33 fails at 20000 evals; whole population stuck 33–35, deep in the 0.5^n
high-fail regime. Fail histogram is dominated by 'missing' (13/33 = 39%): the
counted space m×3 is never constructed, with adjacency/access/size fails
downstream of the unbuilt room set.
Verdict: per-floor CONSTRUCTION is the bottleneck, not multi-storey coupling —
c4c.2 (programme-aware construction + missing-room repair) is the prerequisite
and staging (c4c.3) alone won't rescue it. Closes homemaker-py-c4c.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Records the diagnosis (§11.0) and stubs the experiment subsections (§11.1-11.5)
for epic homemaker-py-c4c children, to be filled in by the sessions that run
each experiment.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Diagnosis-driven backlog redo: delivered speedups (native fitness, geometry
inner loop) polish within a failure tier but final design quality is gated by
topology-search quality on full/multi-storey programmes. New epic + children:
construction (c4c.2), staged per-floor search (c4c.3), graded high-fail
objective (c4c.4), topology diversity (c4c.5), plus a premise experiment
(c4c.1). Reframed 9gp (canonical encoding) as the capstone and deprioritised
2g5 (occlusion) as fitness-fidelity, orthogonal to design quality.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Python fitness always pins quality_daylight to 1.0 (URB_NO_OCCLUSION semantics),
but oracle.py was invoking urb-fitness.pl without the flag, causing outside leaves
to receive real sun-model daylight scores and producing a ~9% gap.
Changes:
- oracle.py: add URB_NO_OCCLUSION=1 to score_batch env
- oracle.py: Score.fail_lines now parses structured YAML failures from the
llm-agent-mcp branch and converts them to plain-text equivalents, so
parity tests can compare oracle vs native failure sets regardless of format
- Regenerated all 36 corpus .score/.fails files with URB_NO_OCCLUSION=1
(no .score files are tracked in git; the script generates them locally)
- All 183 tests pass; closes homemaker-py-gpx
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
