Update model card to improve readability . move usage up front.

README.md

@@ -18,9 +18,9 @@ language:
 
 A QLoRA adapter that turns Gemma 4 E4B into a **System One** decision model: it reads a
 state, reads a typed question about it, and returns a calibrated probability distribution
-over the allowed answers — from **one forward pass**, with no generation.
+over the allowed answers from a single **forward pass**, with no generation.
 
-Because the answer is read from the logits at the option letters, it **cannot** answer
+Since the answer is read from the logits at the option letters, it **cannot** answer
 outside the options it was given. There is no parsing, no retry loop, and no
 "as an AI language model".
 
@@ -32,50 +32,6 @@ It implements the three [TypeSafe](https://docs.typesafe.ai) primitives:
 | `score` | rate against ordered levels | expected level, legend, probabilities, confidence |
 | `noul` | is this true? | a single probability |
 
-## Results
-
-Evaluated on 1,898 held-out rows — 31 Super-NaturalInstructions **tasks** the model never
-saw, 78 synthetic **states** it never saw, and SST-2 held out in its entirety. The split is
-by task and by state, never by row, so these are questions of kinds it was not trained on.
-
-| | accuracy | ECE | NLL | Brier |
-|---|---|---|---|---|
-| **overall** | **0.816** | **0.019** | 0.430 | 0.222 |
-| choice (n=1196) | 0.809 | — | 0.431 | 0.238 |
-| noul (n=547) | 0.819 | — | — | — |
-| score (n=155) | 0.852 | — | — | — |
-
-Score answers are off by **0.216 levels** on average (mean absolute error of the expected
-level).
-
-**Calibration is the point.** ECE of 0.019 means that when it reports 80% confidence it is
-right about 80% of the time. Accuracy was flat from step 250 to the end of training while
-ECE fell 0.086 → 0.019: the model did not learn to be right more often, it learned to be
-honest about when it isn't.
-
-Operationally, gating on confidence:
-
-| band | share of traffic | accuracy |
-|---|---|---|
-| ≥ 0.80 — act automatically | 62% | 93% |
-| 0.50–0.80 — confirm or review | 36% | 60% |
-| < 0.50 — route to a human | 2% | 32% |
-
-## Confidence
-
-`confidence` is the model's probability that the answer it returned is the correct one:
-
-- **choice** — the probability of the selected option (`p_max`)
-- **score** — the probability mass that rounds to the reported expected level
-- **noul** — no confidence field; the probability *is* the answer
-
-This was chosen by measurement, not taste. Over 1,430 gold-labelled held-out rows,
-`p_max` beat normalized entropy, margin, chance-corrected top and collision entropy on
-**both** AUROC (0.816, ranking right answers above wrong ones) and ECE (0.036). Normalized
-entropy — the obvious first guess — was the worst of the lot: it is dominated by small
-probabilities, so it reads a decisive 0.85/0.08/0.07 as low confidence and routes 45% of
-traffic to human review at 64% accuracy.
-
 ## Usage
 
 The adapter is only meaningful with the exact prompt format it was trained on, so
@@ -155,6 +111,51 @@ a thinking budget the teacher commits to its answer with probability 1.0 on esse
 every row, which is useless for distillation — the measured mean entropy was 0.000 with
 reasoning versus 0.211 without.
 
+
+## Results
+
+Evaluated on 1,898 held-out rows — 31 Super-NaturalInstructions **tasks** the model never
+saw, 78 synthetic **states** it never saw, and SST-2 held out in its entirety.
+
+| | accuracy | ECE | NLL | Brier |
+|---|---|---|---|---|
+| **overall** | **0.816** | **0.019** | 0.430 | 0.222 |
+| choice (n=1196) | 0.809 | — | 0.431 | 0.238 |
+| noul (n=547) | 0.819 | — | — | — |
+| score (n=155) | 0.852 | — | — | — |
+
+Score answers are off by **0.216 levels** on average (mean absolute error of the expected
+level).
+
+**Calibration is the point.** ECE of 0.019 means that when it reports 80% confidence it is
+right about 80% of the time. Accuracy was flat from step 250 to the end of training while
+ECE fell 0.086 → 0.019: the model did not learn to be right more often, it learned to be
+honest about when it isn't.
+
+Operationally, gating on confidence:
+
+| band | share of traffic | accuracy |
+|---|---|---|
+| ≥ 0.80 — act automatically | 62% | 93% |
+| 0.50–0.80 — confirm or review | 36% | 60% |
+| < 0.50 — route to a human | 2% | 32% |
+
+## Confidence
+
+`confidence` is the model's probability that the answer it returned is the correct one:
+
+- **choice** — the probability of the selected option (`p_max`)
+- **score** — the probability mass that rounds to the reported expected level
+- **noul** — no confidence field; the probability *is* the answer
+
+This was chosen by measurement, not taste. Over 1,430 gold-labelled held-out rows,
+`p_max` beat normalized entropy, margin, chance-corrected top and collision entropy on
+**both** AUROC (0.816, ranking right answers above wrong ones) and ECE (0.036). Normalized
+entropy — the obvious first guess — was the worst of the lot: it is dominated by small
+probabilities, so it reads a decisive 0.85/0.08/0.07 as low confidence and routes 45% of
+traffic to human review at 64% accuracy.
+
+
 ## Limitations
 
 - **English only.**