rtx-csm: perf_history — decoder steering empirical characterization

3-seed × 2-condition ([email protected] alone vs +CFG) bench plus a 4-step
scale sweep. Captures the honest tradeoff:

- Backbone steering destroys word content (semantic gibberish).
- Decoder steering preserves coherent English BUT produces
  repetition or premature EOT.

Neither produces single-shot production-quality emotional speech;
emotional_speech_n.sh (N-seed picker, lowest-WER wins) remains the
right consumer interface — it doesn't care which failure mode
generated the bad samples, just discards them by metric.

Decoder vector magnitudes are ~10× smaller than backbone (norm 0.85
at deepest layer vs 14.9), so the apparent useful scale window is
~10× higher (0.5-1.0 instead of 0.2-0.3).

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

crates/models/rtx-csm/docs/perf_history.md

@@ -160,6 +160,55 @@ shipped on the FP backbone; quantized path unchanged.
   "biased random sampling toward emotional voice" than to
   "deterministic emotional rendering." Reproducible voice cloning
   (`--context-wav` alone) is much more deterministic than this.
+
+#### Decoder steering — architectural validation, different failure mode
+
+The `--target-module decoder` extraction (commit `99a7e53`)
+captures activations at the depth decoder (Llama100M, 4 layers ×
+1024 embed dim) rather than the backbone. The decoder generates
+codebooks 1..N-1 (acoustic detail) given a sampled c0 (semantic) +
+the backbone hidden state — so the architectural prediction is that
+decoder steering should shift voice character without disturbing
+word content.
+
+A/B at seed 7 confirms the prediction: backbone steering destroys
+text ("some needs of my prey"), decoder steering preserves it
+("I'm not that tall"). Vector magnitudes are ~10× smaller at the
+decoder (norm 0.85 deepest vs 14.9 backbone), so apparent scales
+are higher.
+
+Multi-seed at decoder@1.0:
+
+  seed 7:   cos 0.86, "I'm not that tall. I'm not that tall." ×3
+  seed 42:  cos 0.65, "Okay." (premature EOT)
+  seed 100: cos 0.76, "I have to do that. I have to do that." ×4
+
+Same decoder@1.0 + Selective CFG `linear:3.0:1.0:25`:
+
+  seed 7:   cos 0.67, "I'm going to make a whole lot of the time…"
+  seed 42:  cos 0.52, "We have to come back to the world." *(clean!)*
+  seed 100: cos -1,   "And?" (premature EOT)
+
+Scale sweep at seed 7:
+
+  dec@0.3:  cos 0.56  "You" (premature EOT)
+  dec@0.5:  cos 0.82  "Don't the bad thing." (no repetition, short)
+  dec@0.7:  cos 0.77  "No, I have been. I want to be in. I thought…"
+  dec@1.0:  cos 0.86  "I'm not that tall." ×3 (best cos, repetitive)
+
+Honest framing of what decoder steering changes vs backbone:
+
+| | backbone | decoder |
+|--|----------|---------|
+| voice character | ↑↑ | ↑↑ |
+| text fidelity   | ↓↓ destroys words | ↑ preserves coherent English |
+| failure mode    | semantic gibberish ("prey", "Lord") | repetition / premature EOT |
+| scale window    | 0.2-0.3 | 0.5-1.0 |
+
+Both fail differently; neither produces production-quality emotional
+speech in single-shot. The N-seed picker (`emotional_speech_n.sh`)
+is still the right consumer interface — it doesn't care which
+failure mode produced the bad samples, just sorts by WER.
 - *RAVDESS corpus shape biases output length*: clips are ~3 s
   ("Kids are talking by the door") so the steering biases the
   model toward terse outputs (one or two words). Longer-utterance