---
title: "Comment by Ahmet Özel on \"How a Chunking Bug Taught Me More Than a Model Failure\" | Hashnode"
description: "That clarification about PyMuPDF losing the 1.5/2/4°C column mapping is important; once geometry is discarded, adding labels later would be reconstruction rathe"
url: "https://hashnode.com/posts/how-a-chunking-bug-taught-me-more-than-a-model-failure/6a623f85edcd423e97e4c863/comment/6a6b76047237856aa3c87072"
---

[Discussion](https://hashnode.com/posts/how-a-chunking-bug-taught-me-more-than-a-model-failure/6a623f85edcd423e97e4c863)

Comment [How a Chunking Bug Taught Me More Than a Model Failure](https://hashnode.com/posts/how-a-chunking-bug-taught-me-more-than-a-model-failure/6a623f85edcd423e97e4c863)

[Ahmet Özel](https://hashnode.com/@ahmetozel)

[Jul 30](https://hashnode.com/posts/how-a-chunking-bug-taught-me-more-than-a-model-failure/6a623f85edcd423e97e4c863/comment/6a6b76047237856aa3c87072)

That clarification about PyMuPDF losing the 1.5/2/4°C column mapping is important; once geometry is discarded, adding labels later would be reconstruction rather than enrichment. I would make that loss explicit in chunk metadata, for example `table_structure=caption_only`, and route those tables to a layout-aware parser or abstain from cell-level answers. A separate chunk-answerability check can then ask whether the chunk alone preserves every coordinate needed to interpret the value, while recall@k remains purely a retrieval metric.
