Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).
C-Rank Grade: D (Risky) - 30/100
External PR Merge Rate: -
Response Time: 2h
First Timer Success: -
SimplexLab/TorchJD has a recorded first-timer success rate of 0.0%. Repositories ranked D typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in SimplexLab/TorchJD respond to incoming external pull requests in approximately 1.9 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.
The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 29.9 places SimplexLab/TorchJD in the D tier.
The external contributor pull request merge rate for SimplexLab/TorchJD is 0.0%, based on public PR activity from non-core contributors.
SimplexLab/TorchJD currently has 3 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Active maintainer team in SimplexLab/TorchJD welcoming community pull requests and bug fixes.
Average Response Latency
Tracks hours until a maintainer leaves a review, comment, or PR response.
External Acceptance Rate
Percentage of community pull requests successfully merged into main.
First PR Conversion
Rate at which developers submitting their first repository PR succeed.
Show contributors that your repository actively reviews and merges external pull requests.
[](https://getmerged.abhishekco.de/SimplexLab/TorchJD?utm_source=github&utm_medium=badge)
Historical health & responsiveness evolution
External PR acceptance
First PR success rate
50% receive response in
90% receive response in
Maintainer review activity heatmap & prime window prediction
Calculating local time...
Calculating local time...
Detected: UTC
Maintainers are most responsive around 15:00 UTC (15:00 UTC in your timezone). Recommended submission window is Monday - Wednesday from 14:00 to 18:00 UTC (14:00 - 18:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~4 hours (81% approval). Large PRs (>500 lines) take ~9 hours (29% approval). Keep your diff compact for rapid review.
It would be really nice to be able to play with the interactive plotter directly from the docs of torchjd. For that, we would need some kind of webapp, that has access to an environment with python and torchjd installed. At first, the URL could be anything, but then if it works well enough we can assign this to some subdomain of torchjd.org, like visualization.torchjd.org, and we can add a link to it from the docs, and / or from the README, and / or from the paper itself. The required python deps to run this should be at least "torchjd[full]", dash and plotly, on top of whatever is required to make the webapp. At first I think we can get away with only the features that are currently available in the interactive plotter (resizing gradients, changing angle, and so on). The code is available at: TorchJD/tests/plots/interactive_plotter.py. Note that the current interactive plotter is already something that is used from within a web browser, so the transition should be doable easily. It cu
This issue tracks the candidate methods that could maybe be implemented as Scalarizer in torchjd.scalarization. Status Name Ref Stateful Existing implementations Special Remarks - - - - - - Feel free to suggest missing scalarization methods in the comments!
This issue tracks some candidate aggregators that could maybe be added to TorchJD. Feel free to suggest other methods, or to add more information about the methods in the table. If you're interested in implementing one, please tell it so that we can investigate the method in a bit more details (in particular, we need to verify that it can be implemented as an aggregator), and so that we don't work concurrently on the same thing. Status Name Ref Stateful Existing implementations Special Remarks 🟡 In progress (#676) MoCo (Multi-Objective Gradient Correction) Mitigating gradient bias in multi-objective learning (ICLR 2023 oral, 95 citations) Yes (Jacobian EMA) LibMTL 🟣 To Do PCD (Priority-Constrained Descent) Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization (TMLR 2026) Yes (EMA of row norms) official Asymmetric: first row is the primary 🟣 To Do GradNorm GradNorm: Gradient Normalization for Adaptive Loss Bala
Rate what actually matters after opening a pull request here.
Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.
When evaluating whether to contribute to SimplexLab/TorchJD, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.
Currently, maintainers of SimplexLab/TorchJD acknowledge new external contributions in approximately 1 hours. Out of all submitted pull requests from non-core authors in the last 180-day window, 0.0% were successfully merged into the primary branch.
SimplexLab/TorchJD has a recorded first-timer success rate of 0.0%. Repositories ranked Risky typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~1 hours. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.
The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 29.9 places SimplexLab/TorchJD in the Risky tier.
The external pull request merge rate is 0.0%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, SimplexLab/TorchJD currently has 3 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for SimplexLab/TorchJD are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.