diff --git a/evalharness/model/runner.py b/evalharness/model/runner.py
index 23eb5ec..16fbaa6 100644
--- a/evalharness/model/runner.py
+++ b/evalharness/model/runner.py
@@ -606,10 +606,16 @@ async def run_eval(
 
                 fs_spec = dataclasses.replace(spec, split=fs_split) if spec is not None else None
                 if fs_spec is not None:
-                    from ..data.loader import load_raw_records
+                    # go through the CACHED materialization path (not raw hub
+                    # loads): a cached few-shot split never touches the
+                    # network; first use downloads and caches it for offline
+                    # runs afterwards
+                    from ..data.dataset import Dataset
 
                     fn = prov.resolve_record_fn()
-                    fs_raw = load_raw_records(fs_spec)
+                    fs_ds = Dataset(fs_spec, fn)
+                    fs_ds.materialize()
+                    fs_samples_all = list(fs_ds)
                     # keep the WHOLE dev split when samples carry a category:
                     # es selects domain-MATCHED exemplars per subject (mmlu
                     # biology questions get biology exemplars), we do the same
@@ -617,16 +623,16 @@ async def run_eval(
                     def _lv_of(md):
                         return (md or {}).get('category') or (md or {}).get('level')
 
-                    cats = {_lv_of(fn(r).metadata) for r in fs_raw[:200]}
+                    cats = {_lv_of(s.metadata) for s in fs_samples_all[:200]}
                     style_is = getattr(spec, 'prompt_style', '') if spec is not None else ''
                     if len(cats) > 1 and spec is not None and \
                             (style_is.startswith('cot_letter') or style_is == 'imo_es'):
                         # mmlu-style per-subject OR math per-Level exemplars:
                         # load the WHOLE few-shot split; assemble-time picks
                         # domain-matched first-N (es reformat_subset semantics)
-                        few_shot_samples = [fn(r) for r in fs_raw]
+                        few_shot_samples = fs_samples_all
                     else:
-                        few_shot_samples = [fn(r) for r in fs_raw[:few_shot_num]]
+                        few_shot_samples = fs_samples_all[:few_shot_num]
             except Exception as e:
                 print(f'few-shot: could not load {fs_split} split ({type(e).__name__}: '
                       f'{str(e)[:80]}); continuing 0-shot', flush=True)