kiholee/TMC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Document new output files in README

Browse Source
This commit is contained in:
kiholee
2026-07-27 14:04:22 +09:00
parent 5274ef8abe
commit 9ff3538682
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -2
View File
@@ -18,13 +18,15 @@ Builds on the published shared-embedding multiple-access framework
SNR sweeps, closed-form overlays) → `data/e1_*.csv` SNR sweeps, closed-form overlays) → `data/e1_*.csv`
- `code/exp2_structure.py` — E2: embedding-structure optimization on - `code/exp2_structure.py` — E2: embedding-structure optimization on
real BERT embeddings (spectral recovery, learned adapter, held-out real BERT embeddings (spectral recovery, learned adapter, held-out
evaluation ladder) → `data/e2_*.csv`, `data/e2_exponents.txt` evaluation ladder, paired spec-vs-adapter confidence intervals) →
`data/e2_*.csv`, `data/e2_exponents.txt`
- `code/exp3_mobility.py` — E3: time-varying affinity tracking under - `code/exp3_mobility.py` — E3: time-varying affinity tracking under
mobility (scene traversal and speed sweep) → `data/e3_*.csv` mobility (scene traversal and speed sweep) → `data/e3_*.csv`
- `code/exp4_mismatch.py` — E4: robustness to affinity estimation - `code/exp4_mismatch.py` — E4: robustness to affinity estimation
error → `data/e4_mismatch.csv` error → `data/e4_mismatch.csv`
- `code/exp5_learned.py` — E5: comparison with a trained user-wise - `code/exp5_learned.py` — E5: comparison with a trained user-wise
attention receiver → `data/e5_learned.csv`, `data/e5_train_log.csv` attention receiver → `data/e5_learned.csv`, `data/e5_train_log.csv`,
`data/e5_valcurve.csv` (fixed-affinity validation curve)
- `code/check_mask_realization.py` — realized Haar-mask front end vs - `code/check_mask_realization.py` — realized Haar-mask front end vs
the expected cross-Gram model → `data/e_mask_check.csv` the expected cross-Gram model → `data/e_mask_check.csv`
- `code/replot_all.py` — the single canonical figure generator; reads - `code/replot_all.py` — the single canonical figure generator; reads