key4hep / key4hep/DDML

Potential overrun of outputs for high energy (>220-250 GeV) showers

Open
#26 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
1
Forks
5
PR merge metrics
No merged PRs in 30d

Description

According to Claude (who ran the inference for several input energies) the hardcoded output sizes, e.g. here

https://github.com/key4hep/DDML/blob/fee49531e308b1bb7b304843325ab96b72816e84/include/DDML/CaloCloudsTwoAngleModel.h#L49

will mean that the model output overflows the buffer we provide.

Contributor guide

Open the contributing guide

Research direction

Start in include/DDML/CaloCloudsTwoAngleModel.h at the hardcoded output sizes around line 49. Trace how inference outputs are written into the provided buffer, then check behavior for showers above 220–250 GeV. Done means high-energy model outputs no longer overflow the buffer.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
62/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.