🍓 Simulation-free, GPU-first generative modeling in PyTorch ⚡ Composable primitives for scalable, stable training of modern EBMs, diffusion, flow matching, and Schrödinger bridges.
C-Rank Grade: A (Welcoming) - 69/100
External PR Merge Rate: 74%
Response Time: 20h
First Timer Success: 100%
soran-ghaderi/torchebm has a recorded first-timer success rate of 100.0%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in soran-ghaderi/torchebm respond to incoming external pull requests in approximately 20.2 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 69.3 places soran-ghaderi/torchebm in the A tier.
The external contributor pull request merge rate for soran-ghaderi/torchebm is 74.1%, based on public PR activity from non-core contributors.
soran-ghaderi/torchebm currently has 61 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Collaborative maintainer environment in soran-ghaderi/torchebm. Reviews community pull requests with focus on project quality.
Discussions in soran-ghaderi/torchebm focus heavily on practical implementation feedback, code formatting standards, and issue reproduction details.
Unlinked PRs without issue context and changes that fail automated test suites face the highest review friction.
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/soran-ghaderi/torchebm?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 03:00 UTC (03:00 UTC in your timezone). Recommended submission window is Monday - Wednesday from 00:00 to 04:00 UTC (00:00 - 04:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~13 hours (93% approval). Large PRs (>500 lines) take ~97 hours (33% approval). Keep your diff compact for rapid review.
Sub-task of #334. After implicit preparation, extract score/noise conversion and weighting into losses.functional. Reuse them from EquilibriumMatchingLoss without changing operation order. Done when: every supported prediction/loss_weight combination matches existing values and gradients without extra random draws.
Sub-task of #334. After energy_gradient, extract eqm_energy(x, prediction, energy_type=...) into models.functional. Share it between EqMEnergy and EquilibriumMatchingLoss. Done when: energy modes, losses and parameter gradients match. Preserve EqMEnergy.from_loss, checkpoint keys and supported distributed behavior.
Sub-task of #334. Add energy_gradient(energy, x, create_graph=False) in torchebm.models.functional. Require connected tensors; document score = -energy_gradient. Preserve BaseModel.gradient. Done when: analytic tests verify signs, sampling gradients and training parameter gradients without detaching the training graph.
Sub-task of #334. After flow preparation, add prepare_equilibrium_matching using MatchingBatch. Cover implicit velocity prediction, ct options, coupling weights and time_invariant behavior. Done when: EquilibriumMatchingLoss reuses it with matching targets, values and gradients. Other prediction modes remain unchanged.
Sub-task of #334. Add prepare_flow_matching and weighted_mse_loss in torchebm.losses.functional. Return MatchingBatch with xt, t, model_time, target and weights. Accept explicit x0, t and generator. Reuse from FlowMatchingLoss and BaseInterpolantLoss. Done when: external model evaluation matches existing values, gradients, weighted reductions and RNG order.
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 soran-ghaderi/torchebm, 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 soran-ghaderi/torchebm acknowledge new external contributions in approximately 20 hours. Out of all submitted pull requests from non-core authors in the last 180-day window, 74.1% were successfully merged into the primary branch.
soran-ghaderi/torchebm has a recorded first-timer success rate of 100.0%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~20 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 69.3 places soran-ghaderi/torchebm in the Welcoming tier.
The external pull request merge rate is 74.1%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, soran-ghaderi/torchebm currently has 61 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for soran-ghaderi/torchebm 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.