Paras Sharma
We lifted 7 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| Parassharmaa/pdna | canonical | 0 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| compute_ablation_table | Not yet run | Parassharmaa/pdna/src/pdna/analysis/results.py pointer only (licence: NONE) · get_code("81649647ef19f2b5") |
| compute_degradation_table | Not yet run | Parassharmaa/pdna/src/pdna/analysis/results.py pointer only (licence: NONE) · get_code("b81812b815823d5e") |
| load_all_results | Not yet run | Parassharmaa/pdna/src/pdna/analysis/results.py pointer only (licence: NONE) · get_code("c0989ee4eab81695") |
| load_config | Not yet run | Parassharmaa/pdna/src/pdna/training/config.py pointer only (licence: NONE) · get_code("acbff6ba20d01030") |
| plot_ablation_heatmap | Not yet run | Parassharmaa/pdna/src/pdna/analysis/visualize.py pointer only (licence: NONE) · get_code("05c22ade175b5060") |
| plot_degradation_curves | Not yet run | Parassharmaa/pdna/src/pdna/analysis/visualize.py pointer only (licence: NONE) · get_code("5ebf8ca5da1e30d0") |
| plot_training_curves | Not yet run | Parassharmaa/pdna/src/pdna/analysis/visualize.py pointer only (licence: NONE) · get_code("4365a06d22b5b6e1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce PDNA (Pulse-Driven Neural Architecture), a method for augmenting continuous-time recurrent networks with learnable oscillatory dynamics that maintain internal state evolution independently of external input. Built on Closed-form Continuous-time (CfC) networks, PDNA adds two components: (1) a pulse module that generates structured oscillations A • sin(ωt + φ(h)) with learnable frequencies and state-dependent phase, and (2) a self-attend module that applies recurrent self-attention to the hidden state. Through a controlled ablation study on sequential MNIST (sMNIST) with five random seeds, we evaluate gap robustness-the ability to maintain performance when portions of the input sequence are removed at test time. Our key finding is that structured oscillatory dynamics significantly improve robustness to input interruptions: the self-attend variant achieves a statistically significant 2.78 percentage point multi-gap advantage over baseline (p = 0.041), while the pulse variant shows a 4.62 pp advantage with large effect size (Cohen's d = 0.87). A noise control (random perturbation of equal magnitude) provides no benefit, confirming that the advantage is structural rather than merely dynamic. These results provide evidence that continuous-time models can benefit from biologically-inspired internal oscillatory mechanisms for temporal robustness.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2603.00153")
get_code_for_paper("2603.00153")
have("2603.00153")
Connect an agent — have() is free.