Upload README.md with huggingface_hub

README.md

@@ -33,7 +33,9 @@ No transformer here. The `PreTrainedModel` wrapper exists only so the weights se
 
 ## The gate this model passed
 
-Every sequence carries exactly 8 events with identical type and exit-code bags across labels, and identical final state (exit 0, clean). A field-only MLP on aggregates scores 0.2362 and 0.2537 across two seeds, chance level on four classes. The GRU scores 1.0000 on both seeds. Ordering carries all the signal by construction, and the replication confirms it.
+Every sequence carries exactly 8 events with identical type and exit-code bags across labels, and identical final state (exit 0, clean). A field-only MLP on aggregates scores 0.2362 and 0.2537 across two seeds, chance level on four classes. The GRU scores 1.0000 on both seeds. Order is therefore sufficient for perfect separation against the declared order-blind baseline, and the replication confirms it.
+
+Order is not the only field that differs. Event durations are weakly label-bearing, because the fixed 2.0s wait sits at a different point in each procedure. An order-blind model given duration aggregates alone reaches 0.6996, and the first execute event duration alone reaches 0.5829. Counts and exit codes carry no such signal: both sit at exactly 0.2500. The 1.0000 result is a claim about order being sufficient, not about order being the sole difference between procedures.
 
 ## Usage
 
@@ -57,7 +59,7 @@ print(model.predict_label(sequence))
 
 ![Field-only versus ordered GRU accuracy on both seeds](flow_gate.png)
 
-The publish gate as measured: a field-only MLP on aggregates sits at chance on both seeds, while the ordered GRU scores 1.0000 on both. Same data, same split procedure, only the information access differs. This is the evidence the model was published on, not an illustration of it.
+The publish gate as measured: a field-only MLP on aggregates sits at chance on both seeds, while the ordered GRU scores 1.0000 on both. Same data and same split procedure, with the baseline restricted to counts and exit codes. Reproduce both families with the benchmark in [coccinella-labs/sandbox-lifecycle](https://github.com/coccinella-labs/sandbox-lifecycle). This is the evidence the model was published on, not an illustration of it.
 
 ## Limitations