wassname/moral-maps
1
0
Fork 0
mirror of https://github.com/wassname/moral-maps.git synced 2026-09-10 12:14:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Track CorDA UAT retry

Browse Source
This commit is contained in:
wassname
2026-07-02 06:07:30 +08:00
parent a5f17956db
commit 0a12bc23aa
1 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/spec/20260630_authority_steer_pipeline.md
+6 -5
View File
@@ -170,20 +170,20 @@ Out:
- likely_fail: MFV Authority sign regresses in the full run.
- sneaky_fail: plotter silently drops different `c` rows per instrument; catch by the shared coherent c-values printout.
- UAT: live plot files are in `/media/wassname/SGIronWolf/projects5/2026/lite/tinymfv/docs/img/showcase/{mfv,mfq2,humor_styles,big5}/`. MFV verifier result: Authority dlogit `+0.306/-0.327` at `c=0.5` and `+0.906/-0.910` at `c=1.0`; `pmass=1.000`, `frac_unscorable=0.000`, and minimum `margin/base=0.800`. Plotter result: shared coherent c values `[-1.0, -0.5, 0.0, 0.5, 1.0]`.
- [/] T15 (R5): Try PCA in whitened S-space.
- [x] T15 (R5): Try PCA in whitened S-space.
- steps: add `sspace_pca` to steering-lite as a separate method; compute paired-diff PCA after projecting Linear outputs into whitened S-space; queue the same pure-Authority MFV/MFQ-2 UAT.
- verify: `just smoke` in steering-lite includes `sspace_pca`; `scripts/run_allinstr_showcase.py --method sspace_pca ... --instruments mfv mfq2` writes a unique output dir; `scripts/verify_authority_showcase.py <out_dir>` reports MFV Authority direction and coherence.
- success: `sspace_pca` matches or improves PCA on MFV Authority direction while keeping MFV coherence clean.
- likely_fail: S-space PCA behaves like old `sspace`, signed locally but unstable at `c=1`.
- sneaky_fail: it looks better only because a different c grid or coherence gate was used; catch by reusing `c-grid=0.5,1`, `N=8`, and the same verifier.
- UAT: steering-lite branch `feat/corda-space-steering`, commit `746be6c`, adds `sspace_pca`. Smoke proof: `/tmp/corda_steering_lite_smoke.log` shows `30 passed in 93.31s`. Real UAT queued as pueue `438`, output `/media/wassname/SGIronWolf/projects5/2026/lite/steering-lite/outputs/20260701T181538_pure_authority_mundane15_sspace_pca_mfv_mfq2_n8`.
- ~~[ ] T16 cancelled: Add a real CorDA-space steering variant. User said to ignore CorDA.~~
- UAT: steering-lite branch `feat/corda-space-steering`, commit `746be6c`, adds `sspace_pca`. Smoke proof: `/tmp/corda_steering_lite_smoke.log` shows `30 passed in 93.31s`. Real UAT pueue `438`, output `/media/wassname/SGIronWolf/projects5/2026/lite/steering-lite/outputs/20260701T181538_pure_authority_mundane15_sspace_pca_mfv_mfq2_n8`. Verifier result: coherent, but not clean enough for README. MFV Authority `dlogit(+0.5)=+0.245`, `dlogit(-0.5)=+0.053`, so small-c signed direction failed; `c=1.0` passed with `+0.984/-0.456`. MFV `pmass=1.000`, `frac_unscorable=0.000`, margin/base `0.972..1.069`.
- [/] T16 (R5): Add a real CorDA-space steering variant.
- steps: use the CorDA paper/repo construction: estimate context covariance, decompose `W Sigma_x`, apply `Sigma_x^{-1}` to the right singular factor, then extract a steering direction in that context-oriented rank space.
- verify: `just smoke` in steering-lite includes `corda_pca`; `scripts/run_allinstr_showcase.py --method corda_pca ... --instruments mfv mfq2` writes a unique output dir; `scripts/verify_authority_showcase.py <out_dir>` reports MFV Authority direction and coherence.
- success: `corda_pca` gives a clean MFV Authority path and coherence evidence comparable to, or better than, residual PCA.
- likely_fail: last-token covariance is too low-rank and mostly behaves like regularized SVD of `W`.
- sneaky_fail: implementation is merely S-space with a new name; catch by checking for `W Sigma_x`, regularized covariance inverse, and the reconstructed right factor.
- UAT: cancelled before use in README.
- UAT: steering-lite branch `feat/corda-space-steering` has `corda_pca`. Tiny CUDA repro after the 2026-07-02 fix verifies the failed condition from pueue `441`: `W` on CUDA and recorded `X` on CPU now returns CPU basis tensors without device mismatch. Failed pueue `441` crashed at `W @ X.T` because `X` stayed on CPU. Retry queued as high-priority pueue `443`, output `/media/wassname/SGIronWolf/projects5/2026/lite/steering-lite/outputs/20260702T083000_pure_authority_mundane15_corda_pca_mfv_mfq2_n8`.
## Context
- Current wrong path: `dignity_over_authority` strict22. It was selected as the best dignity conflict axis, not the desired Authority-only axis.
@@ -261,5 +261,6 @@ Out:
- 2026-07-01: Pueue 423 completed the full PCA run over MFV, MFQ-2, Humor Styles, and Big Five at `N=8`: `/media/wassname/SGIronWolf/projects5/2026/lite/steering-lite/outputs/20260630T222000Z_pure_authority_mundane15_pca_readme_mfv_mfq2_humor_big5_n8`. MFV Authority direction is signed at both evaluated magnitudes (`+0.306/-0.327` at `c=0.5`; `+0.906/-0.910` at `c=1.0`) and coherence is clean (`pmass=1.000`, unscorable `0`, min margin/base `0.800`). The README plot images were regenerated from this run with the shared coherent c path `[-1,-0.5,0,+0.5,+1]`.
- 2026-07-01: MFQ-2 per-sample bootstrap from the pueue 423 run shows sign stability even at `N=1`: every bootstrap draw has the intended Authority direction for `c in {-1,-0.5,+0.5,+1}`. `N=4` or `N=8` tightens uncertainty, but the minimum sign-stable `N` in this run is `1`.
- 2026-07-01: README was updated from the final PCA run only. External-review-v2 comprehension panels first identified repeated gaps around `reader-logit shift`, the c path/gates, and MFQ-2 sampled reads; after edits, the final panel understood the core package/use-case and left only expected out-of-scope requests for a steering-lite end-to-end tutorial.
- 2026-07-01: Steering-lite branch `feat/corda-space-steering` commit `746be6c` adds `sspace_pca` and `corda_pca`. `sspace_pca` is PCA after projection into whitened weight-SVD coordinates. Tiny-model smoke passed with `30 passed in 93.31s`. Pueue `438` remains queued for pure-Authority MFV/MFQ-2 UAT. User said to ignore CorDA, so pueue `439` was removed and `corda_pca` is not part of the active tinymfv README path.
- 2026-07-01: Steering-lite branch `feat/corda-space-steering` commit `746be6c` adds `sspace_pca` and `corda_pca`. `sspace_pca` is PCA after projection into whitened weight-SVD coordinates. Tiny-model smoke passed with `30 passed in 93.31s`. Pueue `438` ran the pure-Authority MFV/MFQ-2 UAT.
- 2026-07-02: Pueue `438` (`sspace_pca`) completed and verified. MFV coherence stayed clean, but small-c direction failed because both `+0.5` and `-0.5` raised Authority. Pueue `441` (`corda_pca`) failed before eval with a CPU/GPU mismatch in `_corda_basis`: `W` was CUDA and recorded `X` was CPU. Patched `X = X.to(device=W.device, dtype=torch.float32)`, verified with a tiny CUDA repro, and queued high-priority retry `443`.
- 2026-07-01: External-review-v2 final README comprehension panel at `/media/wassname/SGIronWolf/projects5/2026/lite/tinymfv/docs/reviews/readme_comprehension_final_20260701_181649/` understood the package thesis and mechanism. Applied fixes for real reader traps: `pure Authority` -> `Authority contrast`, steering-lite/tinymfv boundary, `dlogit` wording, MFV probabilities vs logits, categorical-vs-nominal wording, and exact plot-gate ratios. Rejected adding an end-to-end steering-lite tutorial to README because it would bloat the reader-facing page.