An open test for filling in missing signs
Kanichira, Singam, Katyal and Somala (IIT Hyderabad) · Zenodo 24164070
A team released code, data and predictions for a model that guesses damaged or missing signs.
Many seals are chipped, so some signs are lost. This team trained a model to fill the gaps and published everything: the code, how they split the texts for training and testing, and the model’s guesses. Because it is all open, anyone can check how good it really is.
Neural masked-sign restoration with public train/test splits and predictions (CC BY 4.0 and MIT, about 6 MB). The record page does not describe the corpus or the model. The main risk is leakage: near-copies of the same seal text can sit on both sides of a split, which inflates scores.
What we take from it: We graded it. 36% of its test texts have a near-copy in its training texts. On clean texts the neural model does no better than a simple three-sign model (28.5% vs 29.8% right on the first guess).























