diff --git a/.jules/bolt.md b/.jules/bolt.md
index d87bd6d..ff25a10 100644
--- a/.jules/bolt.md
+++ b/.jules/bolt.md
@@ -8,3 +8,6 @@
 ## 2024-03-29 - ASE Custom JSON encoding vs standard JSON
 **Learning:** ASE's custom JSON encoder (`ase.io.jsonio.encode`) will generate dicts with special keys like `__ndarray__` or `__complex__` (e.g. `{"__ndarray__": [[5], "int64", ...]}`). When optimizing JSON deserialization using faster alternatives like `orjson`, it's critical to realize that a normal `json.loads` or `orjson.loads` will deserialize this into a Python dictionary, while ASE's custom `decode` will properly reconstruct the underlying numpy array. Bypassing ASE's decoder without checking for these keys leads to downstream type errors (e.g. `KeyError: '__ndarray__'`).
 **Action:** When replacing or wrapping ASE's jsonio with `orjson`, always fall back to ASE's `decode` if the payload string contains `__ndarray__` or `__complex__` markers, to ensure custom objects are correctly reconstructed.
+## 2024-05-19 - Replacing Pandas iterrows with to_dict('records')
+**Learning:** Iterating over large Pandas DataFrames using `df.iterrows()` inside Python dictionary comprehensions creates a massive performance bottleneck. `iterrows()` creates a new pandas Series object for every row. Converting the DataFrame to a list of dicts first (`df.to_dict('records')`) and iterating over that list is 20x+ faster.
+**Action:** When row-level iteration of a pandas DataFrame is strictly necessary and vectorized operations aren't possible, always use `df.to_dict('records')` instead of `df.iterrows()`. Remember that elements accessed during iteration will now be native dictionaries rather than pandas Series, so methods like `.to_dict()` on the row objects must be removed.
diff --git a/src/lavello_mlips/verify_processed_omol25.py b/src/lavello_mlips/verify_processed_omol25.py
index 9d1c47c..d1987cd 100644
--- a/src/lavello_mlips/verify_processed_omol25.py
+++ b/src/lavello_mlips/verify_processed_omol25.py
@@ -77,8 +77,9 @@ def main() -> None:
         )
 
     logger.info(f"Loaded {len(df)} records from Parquet.")
-    parquet_by_sha = {row["geom_sha1"]: row for _, row in df.iterrows()}
-    parquet_by_argone_rel = {row["argonne_rel"]: row for _, row in df.iterrows()}
+    df_records = df.to_dict("records")
+    parquet_by_sha = {row["geom_sha1"]: row for row in df_records}
+    parquet_by_argone_rel = {row["argonne_rel"]: row for row in df_records}
     logger.info(f"Loading ExtXYZ file from {args.extxyz} (this may take a moment)...")
     all_atoms = read(str(args.extxyz), index=":")
     if not isinstance(all_atoms, list):
@@ -108,7 +109,7 @@ def get_dump_entry(at):
             info = dict(at.info)
             rel = info.get("argonne_rel")
             pq_row = parquet_by_argone_rel.get(rel)
-            pq_data = pq_row.to_dict() if pq_row is not None else None
+            pq_data = pq_row if pq_row is not None else None
             return {"xyz": info, "parquet": pq_data}
 
         duplicates = {
diff --git a/tests/noble_gas.aselmdb-lock b/tests/noble_gas.aselmdb-lock
index 21e73bd..fb10247 100644
Binary files a/tests/noble_gas.aselmdb-lock and b/tests/noble_gas.aselmdb-lock differ
diff --git a/tests/sample.aselmdb-lock b/tests/sample.aselmdb-lock
index 21e73bd..fb10247 100644
Binary files a/tests/sample.aselmdb-lock and b/tests/sample.aselmdb-lock differ
diff --git a/tests/temp_db.aselmdb-lock b/tests/temp_db.aselmdb-lock
index 21e73bd..fb10247 100644
Binary files a/tests/temp_db.aselmdb-lock and b/tests/temp_db.aselmdb-lock differ