diff --git a/backend/app/models/__init__.py b/backend/app/models/__init__.py
index da42323..04025ed 100644
--- a/backend/app/models/__init__.py
+++ b/backend/app/models/__init__.py
@@ -8,6 +8,7 @@ from .base import Base
 from .credential import Credential
 from .download_event import DownloadEvent
 from .external_link import ExternalLink
+from .head_training_run import HeadTrainingRun
 from .image_prediction import ImagePrediction
 from .image_provenance import ImageProvenance
 from .image_record import ImageRecord
@@ -26,7 +27,6 @@ from .series_suggestion import SeriesSuggestion
 from .source import Source
 from .subscribestar_failed_media import SubscribeStarFailedMedia
 from .subscribestar_seen_media import SubscribeStarSeenMedia
-from .head_training_run import HeadTrainingRun
 from .tag import Tag, TagKind, image_tag
 from .tag_alias import TagAlias
 from .tag_allowlist import TagAllowlist
diff --git a/backend/app/services/ml/heads.py b/backend/app/services/ml/heads.py
index 08e649c..b0907c0 100644
--- a/backend/app/services/ml/heads.py
+++ b/backend/app/services/ml/heads.py
@@ -34,8 +34,6 @@ from ...models import (
     TagKind,
 )
 from ...models.tag import image_tag
-# Reuse the eval's proven, identical data loaders + metric math so a production
-# head's quality matches what the eval reported for the same concept.
 from .tag_eval import (
     _auto_apply_point,
     _ids_with_tag,
diff --git a/backend/app/tasks/maintenance.py b/backend/app/tasks/maintenance.py
index f4c878f..fa0397b 100644
--- a/backend/app/tasks/maintenance.py
+++ b/backend/app/tasks/maintenance.py
@@ -13,11 +13,11 @@ from ..celery_app import celery
 from ..models import (
     BackupRun,
     DownloadEvent,
+    HeadTrainingRun,
     ImageRecord,
     ImportBatch,
     ImportSettings,
     ImportTask,
-    HeadTrainingRun,
     LibraryAuditRun,
     Source,
     TagEvalRun,