Database Paper Browser

Back to papers

Doctopus: A System for Budget-aware Structural Data Extraction from Unstructured Documents

Summary: Doctopus blends LLM-based attribute extraction with non-LLM methods under a budget-aware optimizer for structured data in unstructured documents. Chunking narrows to relevant content, estimates per-attr strategy quality, and budget-aware picks the optimal approach. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
7152
Venue
SIGMOD
Year
2025
Pagerank
4.1945683e-05
Overall Rank
10,438 | 27.39%
DOI
10.1145/3722212.3725103

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 2 of 2 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers