diff --git a/backend/documents_parser/tests/test_pashub_sap_accuracy.py b/backend/documents_parser/tests/test_pashub_sap_accuracy.py
index 1f23d4a68..e79120322 100644
--- a/backend/documents_parser/tests/test_pashub_sap_accuracy.py
+++ b/backend/documents_parser/tests/test_pashub_sap_accuracy.py
@@ -62,12 +62,14 @@ _FIXTURES_DIR = Path(__file__).parent / "fixtures" / "pashub_accuracy"
 _MANIFEST_PATH = _FIXTURES_DIR / "manifest.json"
 
 # --- Ratchets (never loosen), mirroring test_sap_accuracy_corpus.py. ----------
-# TODO(pashub-fuel-code): every fixture is currently blocked on the pashub
-# main-fuel-code mapper gap, so the aggregate xfails and these bootstrap values
-# are never asserted. Once that mapper fix lands and the aggregate first
-# computes, ratchet these to the observed within-0.5 and MAE.
-_MIN_WITHIN_HALF: float = 0.0
-_MAX_SAP_MAE: float = 100.0
+# First real aggregate: the main-heating control-code mapper fix (#1557) is the
+# gap that unblocks computation for the cohort. Before it, every fixture raised
+# `UnmappedSapCode: main_heating_control` (0/205 computed, aggregate xfailed);
+# with it, 201/205 compute (4 still blocked on the residual fuel-code gap,
+# e.g. Bulk LPG). Observed at that point: SAP within-0.5 = 10.9% (22/201),
+# MAE = 2.792. Ratchet up as later field fixes land, per #1568.
+_MIN_WITHIN_HALF: float = 0.109
+_MAX_SAP_MAE: float = 2.793
 
 _KNOWN_GAP_REASON = (
     "pashub `from_site_notes` mapper does not int-code a main-heating string "