Code walkthrough map

Function names are stable even if the combined deck is later split or reordered. Each method has a full training and sampling command in the README.

Slide unit	Code	Location
Code for classic DFM training pairs	`gat_loss`	`lecture_core.py`
Code for convert a posterior into Gat jump rates	`gat_rates`	`lecture_core.py`
Code for one valid categorical Euler step	`rate_step`	`lecture_core.py`
Code for classic DFM generation	`gat_sample`	`lecture_core.py`
Code for Dirichlet posterior training	`dirichlet_loss`	`lecture_core.py`
Code for the Dirichlet velocity module	`dirichlet_velocity`	`lecture_core.py`
Code for a Fisher conditional path	`fisher_path`	`lecture_core.py`
Code for Fisher velocity regression	`fisher_loss`	`lecture_core.py`
Code for the Gumbel conditional path	`gumbel_path`	`lecture_core.py`
Code for Gumbel velocity regression	`gumbel_loss`	`lecture_core.py`
Code for objective scores modify the base rates	`mog_rates`	`lecture_core.py`
Code for continuous rectified-flow training	`rectified_loss`	`lecture_core.py`
Code for ReDi replaces the endpoint pairing	`redi_pairs`	`lecture_core.py`
Code for the preference scalarization	`maxmin`	`lecture_core.py`
Code for enumerate every single-base DNA edit	`dna_neighbors`	`lecture_core.py`
Code for a normalized locally balanced proposal	`proposal`	`lecture_core.py`
Code for correct the refinement proposal	`mh_refine`	`lecture_core.py`
Code for run a complete Gat DFM experiment	`complete experiment`	`lecture_core.py` and `run.py`