Monotone CDT autoencoder bottleneck / reference implementation
Mechanism confirmed, baseline not beaten
Monotone CDT autoencoder bottleneck — 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_report.json— 5.7 KBcustom_transport_track.py— 0.9 KBexperiment.py— 4.4 KBreport.md— 1.6 KBreport_bench_2026-08-31T115721.md— 7.7 KBresults.json— 2.8 KBstage2_transport_bench.py— 5.6 KB