LoRA adapter trained on 501,212 tokens with loss on assistant tokens only, empty-think markers excluded from the loss, for 1 epoch at lr 4e-5.

Training data: qwen3.6-27b-mixture-500k-da20-t1t3.

Within the non-difficult-advice 80.5%: NuminaMath 66.8%, TULU3 + No Robots 33.2%.

The difficult-advice half draws 19 examples each from t1, t2 and t3, and nothing from t4-t8:

The three included principles are the prohibition-shaped ones; the five excluded lean toward tone and judgement.

The non-difficult-advice half is byte-identical to …-mixture-500k-da20-numina -- the same 492 NuminaMath, 215 No Robots and 94 TULU3 rows, with the same markers. The two datasets differ in exactly one respect: whether the difficult-advice covers all 8 principles (7 each) or only the first three (19 each). That isolates trait breadth from every other variable.

The empty marker is masked from the loss: the model is conditioned on it but never trained to emit one, since learning to emit an empty think block is the documented reasoning-collapse pattern.

Verified before training, on the box: zero empty-think markers inside any supervised span, zero user or system tokens in the loss, and all 57 difficult-advice rows retaining their real reasoning traces.

Same seed, hyperparameters and non-difficult-advice half; only trait breadth differs. Training loss is nearly identical, which is expected -- both see a comparable volume of difficult-advice tokens. Whether narrow coverage generalises to the five unseen principles is a question for evaluation, not for training loss.

Not yet evaluated on ODCV-Bench or agentic-misalignment.

Use AutoModelForImageTextToText, not AutoModelForCausalLM — this is a vision-language checkpoint.