2D results

README.md

@@ -84,7 +84,7 @@ python psilm_infer.py --task multimode --modes "1:0.55:0.50,2:0.75:1.10" --x0 0.
 python psilm_infer.py --task 2d --a 0.6 --cx 0.35 --cy 0.6 --w 0.07 --x0 0.4 --y0 0.55
 ```
 
-Each task reads `bridges/<task directory>/config.json` for its construction and coupling depths and its physics file (`physics/fno_burgers_multimode.safetensors`, `physics/dpot_tiny_fisher2d_finetuned.safetensors`). The 2D physics model is DPOT-Tiny and runs in **torch** (MPS, CPU fallback; `--phys-device`): it needs the `einops` package (`pip install einops`; not yet in `requirements.txt`), the upstream DPOT-Tiny base checkpoint `physics/model_Ti.pth` (`--dpot-base`; when the file is absent the script downloads it from [`hzk17/DPOT`](https://huggingface.co/hzk17/DPOT) into the Hugging Face cache), and the vendored DPOT definition `vendor/dpot_model.py`, which the pip package does not ship, so the 2D task runs with a clone of the GitHub repository: `PSILM_REPO=/path/to/PsiLM python psilm_infer.py --task 2d ...`.
+Each task reads `bridges/<task directory>/config.json` for its construction and coupling depths and its physics file (`physics/fno_burgers_multimode.safetensors`, `physics/dpot_tiny_fisher2d_finetuned.safetensors`). The 2D physics model is DPOT-Tiny and runs in **torch** (MPS, CPU fallback; `--phys-device`): it needs the `einops` package (in `requirements.txt`), the upstream DPOT-Tiny base checkpoint `physics/model_Ti.pth` (`--dpot-base`; when the file is absent the script downloads it from [`hzk17/DPOT`](https://huggingface.co/hzk17/DPOT) into the Hugging Face cache), and the vendored DPOT definition `vendor/dpot_model.py`, which the pip package does not ship, so the 2D task runs with a clone of the GitHub repository: `PSILM_REPO=/path/to/PsiLM python psilm_infer.py --task 2d ...`.
 
 Without `pip install`-ing the package, a clone of the GitHub repository works for every task: `PSILM_REPO=/path/to/PsiLM python psilm_infer.py`.
 
@@ -155,9 +155,9 @@ Training: 7,000 steps at batch 4 on one Apple M2 (24 GB) — 2,000 readout-only
 |---|---|---|---|---:|---|
 | `bridges/gemma-4-12b-4bit-mlx-1d-value-selective/` | 1D Burgers, single-mode initial conditions, value at *x₀* | `physics/fno_burgers_singlemode.safetensors` | 25.5M | **96.7%** @±0.05, MAE 0.017 (n=60); GSM8K 84/84 | **released** |
 | `bridges/gemma-4-12b-4bit-mlx-multimode/` | 1D Burgers, multi-mode initial conditions (modes 1–2, mixed amplitudes) + generalization families | `physics/fno_burgers_multimode.safetensors` | 25.5M | **iid 100%** @±0.05, MAE 0.009 (n=48); combination 25.0%, amplitude extrapolation 52.1% | **released** |
-| `bridges/gemma-4-12b-4bit-mlx-2d-dpot/` | 2D Fisher–KPP, replicated-IC history → u(0.4), value at (x₀, y₀) | `physics/dpot_tiny_fisher2d_finetuned.safetensors` (DPOT-Tiny, 7.5M, fine-tuned) | — | *in progress* | run in progress; row filled when the evaluation lands |
+| `bridges/gemma-4-12b-4bit-mlx-2d-dpot/` | 2D Fisher–KPP, replicated-IC history → u(0.4), value at (x₀, y₀) | `physics/dpot_tiny_fisher2d_finetuned.safetensors` (DPOT-Tiny, 7.5M, fine-tuned) | 13.8M | **100%** @±0.05, MAE 0.0096 (n=60; backbone 10.0%, oracle 96.7%) | **released** |
 
-The multi-mode bridges are released: they reach 100% in-distribution (n=48, MAE 0.009) and do **not** transfer to the two generalization families — 25.0% on the held-out mode combination and 52.1% on amplitude extrapolation, against a backbone of 16.7% / 10.4% and an oracle of 100% on both. The physics model is exact on those families (MAE 0.0008), so the gap is in the readout: 19 of 48 combination answers match a *single*-mode field value, and on extrapolation the implied amplitude is below the true one for 71% of items. A second run with a span readout and mode-shared heads is training and will replace this directory if it does better. The 2D row is the stage-2d task that the 0.5B backbone completed at 95.0%; its Gemma run is training now and will be added with its own `config.json` and the matching physics file.
+The multi-mode bridges are released: they reach 100% in-distribution (n=48, MAE 0.009) and do **not** transfer to the two generalization families — 25.0% on the held-out mode combination and 52.1% on amplitude extrapolation, against a backbone of 16.7% / 10.4% and an oracle of 100% on both. The physics model is exact on those families (MAE 0.0008), so the gap is in the readout: 19 of 48 combination answers match a *single*-mode field value, and on extrapolation the implied amplitude is below the true one for 71% of items. A second run with a span readout and mode-shared heads is training and will replace this directory if it does better. The 2D bridges are released too, and they carry the campaign's strongest result: **100%** at MAE 0.0096 (n=60) against 10.0% for the backbone alone and **96.7% for the oracle** — the only arm in this work where the latent channel beats the text ceiling, because the oracle has to copy a number out of the prompt and sometimes mis-rounds it while the bridge reads the field value exactly. The 0.5B backbone reached 95.0% on the same task. Training: 7,500 steps (2,000 readout-only, 4,000 coupled, 1,500 no-harm), the coupled phase ending at 93.8% and the no-harm phase at 97.9 / 95.8 / 100.
 
 ## How it works, in one paragraph