Link GitHub pathx folder (code + math docs); update to N=3 result 92.71 +/- 0.89

README.md

@@ -21,21 +21,29 @@ LRU/S4D-style recurrence — combined with a **non-competing complex
 screening attention** module, trained on **Path-X** (Long Range Arena),
 the 16,384-token binary sequence-connectivity task.
 
+**➡️ Code, mathematical documentation, and the paper section:
+[github.com/leohio/phase-coherent-transformer-r-d/tree/main/pathx](https://github.com/leohio/phase-coherent-transformer-r-d/tree/main/pathx)**
+
 - **Task**: raw 1D token sequence in, single binary label out. No 2D
   structure, no auxiliary supervision, no handcrafted features — the same
   rule-compliant setting as S4/S5/LRU/MEGA on the LRA leaderboard.
-- **Test accuracy**: **0.9350** (n=20,000, full deterministic sweep)
-- **PCR-only ablation** (no screening attention): 0.9254 ± 0.0028 (N=2 seeds)
+- **Test accuracy**: **92.71 ± 0.89** over 3 seeds (n=20,000, full
+  deterministic sweep); the checkpoint in this repo is the best seed, **93.50**
+- **PCR-only ablation** (no screening attention): 92.54 ± 0.28 (N=2 seeds)
 
 | Model | Path-X (test) |
 |---|---|
+| Transformer / Reformer / Performer / Linformer / BigBird / Luna-256 | chance (≈50) |
 | S4D-Real (θ=0, no phase) | chance |
-| S4D-LegS | 91.9 |
+| S4-v1 | 88.10 |
+| DSS | 89.72 |
+| S4D-LegS | 91.95 |
 | **PCR (this repo, screening ablated)** | **92.54 ± 0.28** |
-| LRU | 94.2 |
+| S4D-Inv | 92.80 |
+| **PCR + screening hybrid (this repo)** | **92.71 ± 0.89** (best 93.50) |
 | MEGA-chunk | 93.81 |
-| **PCR + screening hybrid (this repo)** | **93.50** |
-| S4 | 96.35 |
+| LRU | 94.20 |
+| S4 (S4-LegS) | 96.35 |
 | MEGA | 97.98 |
 | S5 | 98.58 |
 
@@ -70,8 +78,9 @@ paths; the ~6% real-valued mass is the input-dependent gates, norms, and
 readout — kept real by design, not by omission).
 
 Full experimental record, ablations (phase-necessity via a real-eigenvalue
-control, phase-bandwidth-vs-generalization sweep), and the training/eval
-harness are described in the source repository (see below).
+control, phase-bandwidth-vs-generalization sweep), the derivations, and the
+training/eval harness are in the companion repository:
+[phase-coherent-transformer-r-d/pathx](https://github.com/leohio/phase-coherent-transformer-r-d/tree/main/pathx).
 
 ## Files
 
@@ -81,12 +90,21 @@ harness are described in the source repository (see below).
 
 ## Usage
 
-Load with the `PCRClassifier` / `PCRBlock` / `ComplexScreenBlock` definitions
-from the source training script (`train_with_checkpoint.py`, `cell="pcr"`
-with `pcr_config` matching `config.json`'s `pcr_config` field). This repo
-ships raw weights, not a packaged Python module — see the config for exact
-hyperparameters to reconstruct the module before calling
-`model.load_state_dict(torch.load("pytorch_model.pt"))`.
+This repo ships raw weights, not a packaged Python module. The model code
+(`PCRClassifier` / `PCRBlock` / `ComplexScreenBlock`, self-contained, torch
+only) and a ready-made loading example are here:
+
+**https://github.com/leohio/phase-coherent-transformer-r-d/tree/main/pathx**
+
+```python
+import json, torch
+from pcr_screening import build_pcr_classifier   # pathx/code/pcr_screening.py
+
+cfg = json.load(open("config.json"))["pcr_config"]
+model = build_pcr_classifier(seq_len=16384, vocab=256, **cfg)
+model.load_state_dict(torch.load("pytorch_model.pt", weights_only=True), strict=True)
+model.eval()
+```
 
 ## Training details
 
@@ -102,7 +120,8 @@ hyperparameters to reconstruct the module before calling
 
 ## Caveats
 
-- Single seed for the hybrid checkpoint in this repo (N=1); the PCR-only
+- The hybrid result is 92.71 ± 0.89 over 3 seeds (93.50 / 92.89 / 91.75);
+  the checkpoint released here is the best of the three. The PCR-only
   ablation number (92.54 ± 0.28) is averaged over 2 seeds.
 - Not benchmarked beyond Path-X, LRA Text, and LRA Image; no
   task-specific hyperparameter tuning was performed for those two