Card: depth curve, and state the low-depth metric gap plainly

README.md

@@ -94,30 +94,51 @@ every loss is `real audio → latent → real audio` — so round-trip idempoten
 no reason to hold, and it does not. This adapter adds that objective after the
 fact, on the decoder only.
 
+### What it sounds like
+
+Squeaks and chirps on hi hats, snares and percussion fills — a hat turning into a
+little whistle. Present on a single generation and worse every time the audio goes
+back through the autoencoder, which a continuation and a transform both do.
+
 ### Measured effect
 
-**The win is at re-encode depth.** Every continuation and every transform
-re-encodes previously decoded audio, so a chained session compounds. Measured on
-audio the model generated (medium + a DiT LoRA), the same latents decoded through
-each adapter — HF tonality, i.e. spectral peakiness, which is what "the hi-hat
-became a whistle" looks like numerically:
+Tonal frames (>12 dB tonality, 6–16 kHz) on 2-minute generations, mean of 4, the
+decoder adapter the only variable:
 
-| | tonal p95 at 1x | after 3 re-encodes | cost of depth |
+| depth | stock | `squeakfix_v3` | |
 |---|---|---|---|
-| stock | 8.09 | 12.80 | **+4.71** |
-| `squeakfix_v3` | 8.29 | 9.06 | **+0.78** |
+| d0 — fresh generation | 363 | 422 | −16% |
+| d1 — one transform or continuation | 431 | 450 | −4% |
+| d2 | 823 | 518 | **37% fewer** |
+| d3 | 1664 | 615 | **63% fewer** |
+
+Same shape at fp16 serving precision, on two different DiT LoRAs, at 30 s and
+120 s. Because a transform and a continuation each re-encode their input,
+anything past the first generation already sits at d≥1 and a chained session
+climbs from there — that is where this earns its place.
+
+### The honest gap
+
+**The squeak is clearly audible at d0 — hi hats and snares especially, reported
+by several listeners — and no metric here shows it.** Tried and flat or slightly
+negative at d0: tonality p95 in 6–16 kHz and 1–8 kHz, frame counts over 10/12/15
+dB, onset-locked tonality excess, fp32 and fp16, both LoRAs, both lengths.
+
+The likely reason is that the measurement has no headroom at d0: ~640 of ~10,300
+frames already read as tonal before any re-encoding, because cymbals and
+distorted guitar genuinely are tonal, and a few dozen added squeak frames cannot
+move a count that size. Separating artifact from content works at depth but not
+at d0 without a clean reference, which generated audio does not have.
 
-The adapter cuts degradation-per-re-encode by ~83%. Chained continuations are
-where it earns its place.
+There is also precedent in this project for the tonality detector pointing the
+wrong way — on SAME-S the clip that sounds squeakiest scores lowest. So the d0
+−16% is not evidence the adapter hurts; it is a regime where this instrument does
+not resolve.
 
-**At 1× this metric is flat** (8.29 vs 8.09 — slightly worse, inside the noise).
-A subtle improvement on single generations is reported by ear, and it is
-plausible that it lives in pops and transient smear rather than tonality, but it
-is not something these numbers demonstrate. Treat 1× as neutral and the re-encode
-behaviour as the reason to use this.
+Listen before deciding. Do not take the d0 number as the verdict.
 
-On the round-trip ladder against real held-out audio, which is the eval the
-checkpoint was selected against:
+On the round-trip ladder against real held-out audio — the eval this checkpoint
+was selected against:
 
 | metric | stock | `squeakfix_v3` | Δ |
 |---|---|---|---|
@@ -182,6 +203,9 @@ Other things worth knowing:
   Out-of-distribution prompts produce far more of the offending frames than
   in-distribution ones. This adapter reduces the artifact; it does not make
   prompt choice irrelevant.
+- **The benefit scales with re-encode depth.** If your workflow is one-shot
+  generation and nothing else, the measurable gain is small. If you chain
+  continuations or transforms, it compounds in your favour.
 - **It is a SAME-L adapter.** SAME-S has the same patch grid but its artifact
   sits in a different band (1–8 kHz rather than 6 kHz and up) and wants a
   different recipe. Loading this on SAME-S will not error — it will just sound