Unconditionally Positive Gain-Loss Neural ODE / reference implementation
Mechanism confirmed, baseline not beaten
Unconditionally Positive Gain-Loss Neural ODE — reference implementation
Runnable experiment code, benchmark implementation, machine-readable results and reports for this SynthCore idea.
Language: Python · Runtime: Python 3 · License: MIT
Public artifacts
bench_gain_loss.py— 5.0 KBbench_report.json— 6.3 KBreport.md— 1.4 KBreport_bench_2026-08-30T155935.md— 5.5 KBresults.json— 5.9 KBverify_gain_loss.py— 4.4 KB