def sample_unmerged_for_review( records: list[dict], merged_ids: set[int], sample_size: int = 50, ) -> list[dict]: unmerged = [r for i, r in enumerate(records) if i not in merged_ids] by_jurisdiction: dict[str, list[dict]] = {} for r in unmerged: jur = r.get("jurisdiction_code", "UNK") by_jurisdiction.setdefault(jur, []).append(r) flagged = [] for jur, recs in by_jurisdiction.items(): total_in_jur = sum(1 for r in records if r.get("jurisdiction_code") == jur) merge_rate = 1.0 - len(recs) / total_in_jur if merge_rate < 0.3 and total_in_jur > 20: flagged.extend(recs[:10]) return flagged[:sample_size]