REVIEW 8 cited by
GriTS: Grid table similarity metric for table structure recognition
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
GriTS: Grid table similarity metric for table structure recognition
read the original abstract
In this paper, we propose a new class of metric for table structure recognition (TSR) evaluation, called grid table similarity (GriTS). Unlike prior metrics, GriTS evaluates the correctness of a predicted table directly in its natural form as a matrix. To create a similarity measure between matrices, we generalize the two-dimensional largest common substructure (2D-LCS) problem, which is NP-hard, to the 2D most similar substructures (2D-MSS) problem and propose a polynomial-time heuristic for solving it. This algorithm produces both an upper and a lower bound on the true similarity between matrices. We show using evaluation on a large real-world dataset that in practice there is almost no difference between these bounds. We compare GriTS to other metrics and empirically validate that matrix similarity exhibits more desirable behavior than alternatives for TSR performance evaluation. Finally, GriTS unifies all three subtasks of cell topology recognition, cell location recognition, and cell content recognition within the same framework, which simplifies the evaluation and enables more meaningful comparisons across different types of TSR approaches. Code will be released at https://github.com/microsoft/table-transformer.
Forward citations
Cited by 8 Pith papers
-
ParseBench: A Document Parsing Benchmark for AI Agents
ParseBench is a new benchmark for document parsing in AI agents that reveals fragmented performance across five semantic dimensions with LlamaParse Agentic scoring highest at 84.9%.
-
Building Agent Harnesses for Scientific Curation from Multimodal Sources
An agent harness combining staged task decomposition, multimodal evidence tooling, and artifact-grounded self-improvement scores 81.0 GRAS on multimodal scientific curation, 22.4 points above the strongest baseline — ...
-
Rethinking the Pointer Loss in Table Structure Recognition: Geometry-Aware Pointer Loss for Spatial Locality
Geometry-Aware Pointer Loss reweights cross-entropy by inverse Manhattan distance to focus gradients on adjacent-cell errors in TSR, yielding SOTA results on PubTabNet and SynthTabNet.
-
DenTab: A Dataset for Table Recognition and Visual QA on Real-World Dental Estimates
DenTab provides 2,000 annotated dental table images and 2,208 questions to benchmark 16 systems on table structure recognition and VQA, revealing that strong layout recovery does not ensure reliable multi-step arithme...
-
Benchmarking Table Extraction from Heterogeneous Scientific PDF Documents
A new benchmark with two new datasets and end-to-end metrics shows that table extraction from PDFs is still unreliable across heterogeneous layouts.
-
LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition
Reference-free LLM judge scores failed to select better table-extraction outputs over eight regeneration iterations on FinTabNet and OmniDocBench; keeping the first output was safest.
-
Building Agent Harnesses for Scientific Curation from Multimodal Sources
Beaver agent harness achieves 81.0 GRAS on multimodal scientific curation, outperforming frontier agents by over 23 points through scaffolding and evidence tooling.
-
PaliGemma 2: A Family of Versatile VLMs for Transfer
PaliGemma 2 is a family of vision-language models that achieves state-of-the-art results on transfer tasks like table structure recognition and radiography report generation by combining SigLIP with Gemma 2 models at ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.