Skip to content

Conversation

@anyangml
Copy link
Collaborator

This PR support a downsampled test from Antoine Loew et al 2026 J. Phys. Mater. 9 015010 Universal machine learning potentials under pressure

@codecov
Copy link

codecov bot commented Jan 28, 2026

Codecov Report

❌ Patch coverage is 0% with 6 lines in your changes missing coverage. Please review.
✅ Project coverage is 64.89%. Comparing base (318c77a) to head (8d2088a).
⚠️ Report is 12 commits behind head on main.

Files with missing lines Patch % Lines
lambench/models/ase_models.py 0.00% 6 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main     #395      +/-   ##
==========================================
- Coverage   65.13%   64.89%   -0.24%     
==========================================
  Files          35       35              
  Lines        1635     1641       +6     
  Branches      201      202       +1     
==========================================
  Hits         1065     1065              
- Misses        526      532       +6     
  Partials       44       44              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new “pressure” calculator task to evaluate LAM volume predictions under elevated pressure using a downsampled dataset from Loew et al. (2026).

Changes:

  • Introduces a new pressure calculator task implementation and wires it into ASEModel.evaluate.
  • Adds task configuration (test data path + relaxation params) and includes the task in post-processing/metrics configs.
  • Extends results metadata + documentation to describe the new benchmark task.

Reviewed changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 7 comments.

Show a summary per file
File Description
lambench/tasks/calculator/pressure/pressure.py Implements the pressure-volume evaluation by relaxing structures under target pressure and comparing per-atom volumes.
lambench/tasks/calculator/calculator_tasks.yml Registers the new pressure task and its parameters (fmax/max_steps).
lambench/models/ase_models.py Routes task_name == "pressure" to the new inference implementation.
lambench/metrics/results/metadata.json Adds display/description/metric metadata for the new task.
lambench/metrics/results/README.md Updates the changelog-style “Updates” section to mention the new task.
lambench/metrics/post_process.py Includes pressure in domain-specific results aggregation.
lambench/metrics/downstream_tasks_metrics.yml Adds scoring config entry for pressure (MAE + dummy baseline).

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

anyangml and others added 4 commits January 28, 2026 12:44
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
@anyangml anyangml merged commit ff6f410 into deepmodeling:main Jan 28, 2026
2 of 3 checks passed
@anyangml anyangml deleted the feat/support-pressure-tasks branch January 28, 2026 04:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant