Portfolio-796/scenario-1268 audit found the bulk of MEDIUM/HIGH anomalies
(already-meets-goal-with-works, zero-works-post-differs, plan-score-below-
baseline, and the non-fuel-switch slice of negative-bill-savings) trace to one
root cause: the persisted default plan is stale relative to the live model, so
it resolves on re-model rather than a code change. Confirmed via
run_modelling_e2e on three samples (stored vs live plans differ wholesale).
No new check added — the staleness is already surfaced by the existing checks
and addressed by the override-aware-rebaseline / persistence-fidelity work, so
a new check would only re-flag known divergence. Instead record the expectation
and the "audit the default plan only" rule in the skill Notes so the next
reviewer starts ahead. References kept to durable docs/adr (no PR numbers).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Appendix N3.7 water-heating 100% floor drops corpus MAE 0.726 -> 0.721
and lifts within-0.5 74.1% -> 74.2% on the 1000-cert RdSAP-21.0.1 sample
(cert 100110101713 moves inside +-0.5). Tighten the MAE ceiling to 0.722 and
the within-0.5 floor to 0.742, and log the slice.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
_heat_pump_apm_efficiencies applied the Table N8 in-use factor to the PCDB
water-heating efficiency but omitted the spec's "subject to a minimum
efficiency of 100%" clause (SAP 10.2 Appendix N3.7, PDF p.109). An oversized
heat pump whose PSR-extended water,3 x the 0.60 in-use factor fell below
100% therefore billed water heating at that sub-100% efficiency, over-
counting hot-water fuel.
Apply max(in_use x eta_water, 100%). Accredited Elmhurst worksheet for cert
100110101713 (golden fixture case 56, PCDB 100061): water (216) = 100.0000,
which we now match (was 77.13%). Combined with the space-heating PSR-
extension fix the cert lands 72.51 vs lodged 73 (|err| 18.32 -> 0.49).
Data-driven: only the single oversized-PSR cert moves (in-range heat pumps
keep their > 100% water COP, e.g. case 54 112.5%, case 55 179.6%). Corpus
(RdSAP-21.0.1 n=1000) MAE 0.726 -> 0.721, within-0.5 74.1% -> 74.2%.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
SAP 10.2 Appendix N3.7 ("Thermal efficiency for water heating - heat pumps",
PDF p.109): "multiply the thermal efficiency for water heating by the in-use
factor in Table N8; subject to a minimum efficiency of 100%." Our
_heat_pump_apm_efficiencies applies the in-use factor but omits the floor.
Anchored to golden fixture case 56 (PCDB 100061, cert 100110101713): an
oversized HP (PSR 3.107) extends water,3 198.9% -> 128.55%, x 0.60 in-use =
77.13% < 100% -> the accredited Elmhurst worksheet (216) reads 100.0000, we
read 77.13%. In-range PSR keeps 0.60 x 198.9 = 119.34% (above the floor).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The heat-pump PSR-extension fix (SAP 10.2 Appendix N2) drops corpus MAE from
0.740 to 0.726 on the 1000-cert RdSAP-21.0.1 sample; within-0.5 holds at
74.1%. Tighten the ceiling and log the slice.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
interpolate_heat_pump_efficiency_at_psr clamped to the smallest/largest PSR
row when the dwelling's plant size ratio fell outside the record's range.
That is the SAP 10.2 Appendix N rule for *combined heat-pump-and-boiler*
packages, not for a plain air/ground/water source heat pump.
Per Appendix N2 (PDF p.101, footnotes 44/45) a source heat pump whose PSR
exceeds the record's largest value takes a reciprocal-linear interpolation
between the largest-PSR efficiency and 100% at twice that PSR (100% beyond),
and 100% when the PSR is below the record's smallest value. Both the space-
and water-heating PSR-dependent efficiencies extend this way.
Effect: an oversized heat pump in a small dwelling is no longer credited the
full top-of-table COP. Accredited Elmhurst worksheet for cert 100110101713
(golden fixture case 56, PCDB 100061, PSR 3.107 over largest 2.0): (206)
334.4% -> 139.66% = Elmhurst exact. Corpus (RdSAP-21.0.1, n=1000) MAE
0.7397 -> 0.7258, within-0.5 0.7410 held; only two certs move (both
oversized-PSR heat pumps), 100110101713 +18.32 -> -4.97.
Exhaust-air and combined heat-pump-and-boiler packages have different
boundary rules (straight-to-100% / clamp-to-edge) but are not distinguished
by the current PCDB parse; the air/ground/water rule is applied uniformly,
a documented limitation noted in the function docstring.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
SAP 10.2 Appendix N2 (PDF p.101, footnote 44/45): for an air/ground/water
source heat pump whose plant size ratio exceeds the record's largest PSR,
the efficiency is reciprocal-interpolated between the largest-PSR value and
100% at twice the largest PSR (100% beyond that); below the smallest PSR the
efficiency is 100%. Our interpolator instead clamps to the top/bottom row.
Anchored to the accredited Elmhurst worksheet for cert 100110101713 (golden
fixture case 56, PCDB 100061): PSR 3.10665 over the record's largest 2.0
gives eta_space,1 = 147.011 -> (206) = 0.95 x 147.011 = 139.660, vs the
clamped 352.0 -> 334.4% that over-rates the dwelling by +18 SAP.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
0 = no PV, 1 = not connected to dwelling meter, 2 = connected. Decoded
empirically from the corpus + accredited Elmhurst (the gov RdSAP schema
types it as a bare int). Points readers to the crediting gate.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
within-0.5 floor 0.73->0.74 (now 0.741), MAE ceiling 0.762->0.740 (now
0.7397) on the fixed RdSAP-21.0.1 corpus. Log entry appended.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Gate PV generation/credit in cert_to_inputs on gov-API pv_connection:
credit only when ==2 ('connected'); ==1 ('present but not connected to the
dwelling's meter') contributes zero to the dwelling's cost/CO2/PE per
RdSAP 10 §11.1 / SAP 10.2 Appendix M. Non-int (None / site-notes str) keeps
the credit-if-array behaviour, so the Elmhurst/Summary + synthetic paths are
unchanged (no regression).
Corpus: all 5 pv_connection=1 PV certs move inside ±0.5 (e.g. 100051118081
+6.5→+0.5); MAE 0.760→0.740, within-0.5 73.8→74.3%, no regression
(pv_connection=2 certs keep their credit).
Also corrects a now-load-bearing latent bug: the solar-recommendation
overlay tagged recommended arrays pv_connection=1 ('not connected') — which
the new gate would zero. A new install connects to the dwelling's meter, so
it must be 2; pinned by the overlay test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
RdSAP 10 §11.1 / SAP 10.2 Appendix M: PV is included in a dwelling's
assessment only if connected to the dwelling's own electricity meter. The
gov-API pv_connection enum encodes this — 0=no PV, 1=present-but-not-
connected, 2=connected. Corpus-validated (57 PV certs: pv_connection=1 MAE
4.48->1.22 without credit, 0/5 need it; pv_connection=2 needs it, MAE 0.98
vs 10.29) and Elmhurst-proven (connected SAP 87 vs not-connected 74).
cert_to_inputs currently credits a pv_connection=1 array; the test pins that
it must contribute zero generation. Adds pv_connection to make_minimal_sap10_epc.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Runs a Summary PDF through the chain-test path (pdftotext ->
ElmhurstSiteNotesExtractor -> from_elmhurst_site_notes) into Sap10Calculator
and dumps SAP + per-end-use kWh + the intermediate worksheet trail, for
diffing our calc against the accompanying Elmhurst U985 worksheet PDF.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
_is_elmhurst_roof_window routed a vertical window (Location "External wall")
to sap_roof_windows whenever its building part's roof type was a party
ceiling (A "Another dwelling above" / NR "Non-residential space above").
That is right for an EXTENSION (cert 000565 Ext2/Ext4 score on worksheet
(27a)) but wrong for the MAIN BP: a Main "A"/"NR" roof is the dwelling's own
party ceiling — no external roof — so its windows are vertical.
Gate the BP-roof-type rooflight rule to non-Main building parts. On a mid-
floor flat (case 53 / cert 000565 re-keyed) the Main External-wall window is
now vertical: its area deducts from the wall (was over-counted ~7 W/K) and it
prices as a window. Summary-path SAP 74.0 -> 75.17, matching Elmhurst's
accredited worksheet (75; space-heat 3408.6 vs 3408.58) — confirming the
calculator is correct; the gap was the misclassification.
000565's extension rooflights, the "Roof of Room" branch, and the U>3.0
room-in-roof backstop are unchanged. gov-API path unaffected (it routes roof
windows via window_wall_type==4).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
_is_elmhurst_roof_window mis-routes a vertical window (Location "External
wall") to sap_roof_windows when the building part's roof is a PARTY ceiling
(A "Another dwelling above" / NR "Non-residential space above"). A party
ceiling has no external roof, so it cannot host a rooflight.
Surfaced by simulated case 53 (cert 000565 re-keyed as a mid-floor electric-
storage flat, roof "A Another dwelling above"): its External-wall window
(U 2.00) routed to sap_roof_windows -> window area not deducted from the wall
(wall over-counted ~7 W/K) + priced as a roof window -> our SAP 74.0 vs
Elmhurst worksheet 75. Elmhurst lodges it Type "Window", Location "External
wall".
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A gov-API flat can lodge dwelling_type="Mid-floor flat" while carrying its
own exposed roof — a top-floor flat mislabelled mid-floor. _dwelling_exposure
keyed roof exposure on the dwelling_type label alone, dropping the roof
heat-loss term: space-heating demand under-read ~32%, SAP over-read +7.
Fix: when the main building part lodges a *determined* roof_insulation_location
(an RdSAP integer code, not the "ND" Not-Defined party-ceiling sentinel),
expose the roof regardless of a contradictory label. Structured field, not a
description string and not roof_construction (which the gov-API lodges
building-wide on every unit, so it is not a per-unit signal).
On the RdSAP-21.0.1 corpus roof_insulation_location separates the classes with
zero disagreement: all 190 party-ceiling flats lodge "ND"; the 4 mid/ground
flats this exposes all move toward lodged, 0 away. within-0.5 73.3% -> 73.6%,
MAE 0.774 -> 0.761 (ratchets tightened). Verified end-to-end on the same
block: 715363 (location 6, RHI 2694) 81 -> 74 = lodged; genuine mid-floor
sibling 715395 (location ND, RHI 1024) stays party at 83 = lodged.
The override is additive (only ever exposes a label-dropped roof) and reads
the main part, so multi-part flats with a party main ceiling stay party.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A gov-API cert can lodge dwelling_type="Mid-floor flat" while carrying a
real exposed roof element (roof_construction != 7 "dwelling above") over a
"(another dwelling below)" floor — i.e. a top-floor flat mislabelled
mid-floor. Property 715363 (uprn 6027561) + sibling 715395 (6027563) do
exactly this; the correctly-labelled top-floor sibling 715871 (6027574),
same block + same flat roof, already computes the lodged SAP 74.
_dwelling_exposure keys roof exposure on the dwelling_type label alone, so
it drops the roof heat-loss term, under-reading space-heating demand ~32%
(calc 1833 vs lodged RHI 2694) and over-reading SAP +7 (81 vs 74).
Pins the fix: a mid-floor label + lodged exposed roof must expose the roof
(floor stays party). Also corrects the existing mid-floor fixture to lodge
the party-ceiling code 7 (the default 4 is an exposed pitched roof).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add Phase 6 (self-improve) to audit-ara-portfolio: when a run confirms a
novel systematic problem, codify it as a check — gated on systematic (>=5
props, root-caused), not-already-covered, and /grill-me-pressure-tested.
Each check records provenance (motivating cause + example properties) so the
registry stays sharp and compounds every run.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Script takes an optional --scenario to restrict to one scenario's plans. New
skill drives the full loop: run the deterministic scan, review groups,
deep-dive samples via run_modelling_e2e, characterise sub-classes, and
cross-reference open PRs/ADRs — then proposes new checks to codify.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A check-registry that reads property/baseline/plan/scenario and flags odd
results (plan-below-baseline, already-meets-goal-with-works, band/score
mismatch, zero-works-post-differs, effective-lodged divergence, negative
bill savings). Writes modelling_audit.md/.csv. Adding a check = one
decorated function.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Record the two load-bearing decisions and correct the CONTEXT.md
'Calculated SAP10 Performance' entry: the lodged figure is kept at >=10.2
only for a pristine lodged cert; overrides/prediction adopt the calculator.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Pin the hit-list properties: each property's real Landlord Override set still
resolves to overlays and trips physical_state_changed, and the rebaseliner
adopts the calculator output (reason physical_state_changed/both) rather than
echoing the lodged headline — so the displayed baseline and the modelled plan
agree. Scores a real cert through the live Sap10Calculator.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add Property.physical_state_changed (true on Site Notes / Landlord Overrides
/ Prediction — trigger (b)/(c)) and pass it from the
PropertyBaselineOrchestrator into the Rebaseliner. So an overridden or
predicted SAP>=10.2 property now stores calc(effective) as its Effective
baseline instead of echoing the lodged headline — closing the "81 in the DB"
divergence between the displayed baseline and the modelled plan.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
CalculatorRebaseliner uses the calculator output as Effective Performance
whenever a Rebaselining trigger fired — pre-SAP10 (a) OR overrides/prediction
moved the physical state (b)/(c) — tagging pre_sap10 / physical_state_changed
/ both. Only a pristine lodged >=10.2 cert keeps its accredited figure (the
sole case the calculator runs purely to validate). Divergence is logged only
in that pristine case. ABC + StubRebaseliner take the new keyword-only flag.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
