Files
foxhunt/docs/ml-supervised-to-dqn-concept-audit.md
jgrusewski e47d067390 plan4(task7): Part E audit close-out — every supervised concept landed or OUT
Updates the supervised → DQN concept audit doc to its terminal state per
Plan 4 Task 7. Every Part E row + the cross-Plan-2 D.1/D.8 rows now cite
the commit SHA in which they landed; xLSTM/KAN remain OUT-intentional
(redundant with Mamba2+TLOB and not a bottleneck respectively); Liquid
is AUDITED-LANDED (deleted from DQN per D.7's identity-at-fixed-point
finding).

Landed SHAs:
- E.1 (TFT VSN): 31e0f219a (Plan 4 Task 1B chain final)
- E.2 (GRN ADOPT): f94d857eb (Plan 4 Task 2c.3c.4 backward wire-up)
- E.3 (Multi-quantile IQN): 005ed3a4f (fixed-τ {0.05,0.25,0.50,0.75,0.95})
- E.4 (encoder/decoder split): fbc299fa2 (Rust API split, additive)
- E.5 (attention-focus ISV Mode A): cfc4ccb72
- E.6 (multi-task aux heads): 5478e7c82 (Commit A) + 647f15f9d (Commit B)
- D.1 (Mamba2 backward, Plan 2): 345867c59
- D.8 (TLOB, Plan 2): 3c18ebd63

Pre-commit check passes:
- No row marked TBD or evaluate
- No row still marked pending

Per Invariant 9 (no deferred work): every entry is now IN, OUT, or
AUDITED-LANDED. Part E is closed.

Note: E.5 Mode B (full per-feature-group VSN attention ISV expose) was
blocked on E.1 in the original spec; with E.1 now LANDED, Mode B
unblocks as a follow-up but is OUT of Plan 4 scope (Mode A is sufficient
for the Plan 4 retention check).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-26 10:36:03 +02:00

19 lines
2.8 KiB
Markdown

# Supervised → DQN Concept Audit (Part E deliverable)
Authoritative decisions on which ml-supervised concepts the DQN adopts. Per Invariant 9 (no deferred work), every entry is either `IN`, `OUT`, or `AUDIT-THEN-DECIDE` with the audit producing one of the two terminal classifications during this spec's implementation.
| Concept | Supervised home | Classification | Action plan | Status |
|---|---|---|---|---|
| TFT Variable Selection Network | ml-supervised::tft | IN | E.1: extend vsn_mag/vsn_dir to full VSN over state feature groups | LANDED `31e0f219a` (Plan 4 Task 1B chain final — kernel+params+forward+backward+Polyak EMA target sync) |
| Gated Residual Network | ml-supervised::tft | IN | E.2: branch A (ADOPT) — Linear→ReLU→Linear replaced with GRN blocks at h_s1+h_s2 | LANDED `f94d857eb` (Plan 4 Task 2c.3c.4 — backward wire-up; ADOPT branch confirmed via 2a audit) |
| TFT multi-quantile heads | ml-supervised::tft | IN | E.3: extend IQN to 5/25/50/75/95 quantile decomposition | LANDED `005ed3a4f` (Plan 4 Task 3 — fixed-τ {0.05, 0.25, 0.50, 0.75, 0.95}) |
| TLOB attention encoder | ml-supervised::tlob | IN | D.8 (Plan 2): wire to DQN trunk | LANDED-via-Plan-2 `3c18ebd63` (D.8 cuBLAS port, train+val parity) |
| Mamba2 forward | ml-supervised::mamba2 | WIRED | already in DQN trunk | — |
| Mamba2 backward | ml-supervised::mamba2 | IN | D.1 (Plan 2): complete | LANDED-via-Plan-2 `345867c59` (D.1 grad-check — "already wired"; test landed) |
| Liquid Time-constant | ml-supervised::liquid | OUT (deleted from DQN) | D.7 (2026-04-24): ODE f(x)=(1/tau)*(1-x) is identity at fixed point x=1.0; initialised to 1.0 and never moved. c51_grad spread_scale multiplied by 1.0 unconditionally. No ISV slot (§4.C.6 violation). Kernel + buf deleted. Supervised LiquidTrainableAdapter unchanged. | AUDITED-LANDED |
| xLSTM | ml-supervised::xlstm | OUT | Redundant with Mamba2 + TLOB; no DQN wiring | OUT-intentional |
| KAN | ml-supervised::kan | OUT | Function-approx not a bottleneck; no DQN wiring | OUT-intentional |
| Encoder-decoder separation | ml-supervised::tft | IN | E.4: extend D.3 horizon-decomposed V to full trunk/head separation | LANDED `fbc299fa2` (Plan 4 Task 4 — Rust API split, additive, no behaviour change) |
| Attention-weight interpretability | various | IN | E.5: ISV-expose attention weights from all temporal heads | LANDED `cfc4ccb72` (Plan 4 Task 5 Mode A — attention-focus ISV, GPU-driven; Mode B blocks on Plan 4 Task 1 = E.1, now itself LANDED so Mode B unblocks for follow-up) |
| Multi-task auxiliary heads | ml-supervised | IN | E.6: next-return + regime-classification auxiliary heads | LANDED `5478e7c82` (Commit A — scaffolding) + `647f15f9d` (Commit B — behavioural wiring + ISV-driven aux_weight + HEALTH_DIAG observability verified in smoke) |