Fix #6: Correct README.md paths to match actual repo structure
Browse files
README.md
CHANGED
|
@@ -4,9 +4,9 @@ Short summary
|
|
| 4 |
The Pre‑Emergence Mechanics Framework (PEMF) frames ARC tasks as a boundary‑constrained field problem solved by minimizing irreducible residue (o) under writability gates. PEMF implements four core primitives — **Scalar Potential (+)**, **Gradient Ordering (V)**, **Residue (o)**, and **Boundary Charge (p_q)** — and composes atomic transforms (tile, shifted tile, fill_enclosed, rotate, reflect, etc.) in a beam search to drain residue and produce stable outputs.
|
| 5 |
|
| 6 |
Quick verification
|
| 7 |
-
- Run the
|
| 8 |
```bash
|
| 9 |
-
python SKILLS/
|
| 10 |
```
|
| 11 |
- Run a single experiment (example):
|
| 12 |
```bash
|
|
@@ -14,8 +14,8 @@ python scripts/entrypoint.py --task example1 --out_dir experiments
|
|
| 14 |
```
|
| 15 |
- Postprocess logs to attach candidate snapshot and coerce gates:
|
| 16 |
```bash
|
| 17 |
-
python
|
| 18 |
```
|
| 19 |
|
| 20 |
Where to find skill artifacts
|
| 21 |
-
- `SKILLS/
|
|
|
|
| 4 |
The Pre‑Emergence Mechanics Framework (PEMF) frames ARC tasks as a boundary‑constrained field problem solved by minimizing irreducible residue (o) under writability gates. PEMF implements four core primitives — **Scalar Potential (+)**, **Gradient Ordering (V)**, **Residue (o)**, and **Boundary Charge (p_q)** — and composes atomic transforms (tile, shifted tile, fill_enclosed, rotate, reflect, etc.) in a beam search to drain residue and produce stable outputs.
|
| 5 |
|
| 6 |
Quick verification
|
| 7 |
+
- Run the minimal runner to verify primitives:
|
| 8 |
```bash
|
| 9 |
+
python SKILLS/arc_agi_project/references/examples/minimal_runner.py
|
| 10 |
```
|
| 11 |
- Run a single experiment (example):
|
| 12 |
```bash
|
|
|
|
| 14 |
```
|
| 15 |
- Postprocess logs to attach candidate snapshot and coerce gates:
|
| 16 |
```bash
|
| 17 |
+
python scripts/fix_and_inspect_logs.py
|
| 18 |
```
|
| 19 |
|
| 20 |
Where to find skill artifacts
|
| 21 |
+
- `SKILLS/arc_agi_project/` — howto, runnable example `references/examples/minimal_runner.py`, and README for the ARC‑AGI skill.
|