> ## Documentation Index
> Fetch the complete documentation index at: https://staging.docs.trywhitney.com/llms.txt
> Use this file to discover all available pages before exploring further.

# On-policy self-distillation (OPSD)

> Teacher = the same base model, conditioned on a golden-answer demonstration.

**Contract:** teacher = the same base model, conditioned on a golden-answer
demonstration; student trains to match it over its own on-policy rollouts.

**Caller math:** This is Self-Distillation Fine-Tuning (SDFT),
["Self-Distillation Enables Continual Learning"](https://arxiv.org/abs/2601.19897)
(Shenfeld et al., 2026) — the technique current survey literature groups
under "on-policy self-distillation": a single LLM acts as teacher and student
under *different contexts*, and the student trains to match the teacher's
distribution over its own on-policy rollouts. This is SDFT's per-token
importance-sampling fallback (`topk=0`): `advantage = teacher_logprob -
student_logprob`. SDFT's primary, paper-validated mode (top-K soft-label
`cross_entropy`, default `topk=20`) needs a `(N, K)`-shaped soft-target datum
built from Whitney's `topk_prompt_logprobs` sample field — a real extension,
not shown here.

**Whitney mapping:** The teacher is a [frozen second Whitney run](/distillation),
synced once and never trained — SDFT's own default
(`teacher_sync_every=None`, "works comparably to EMA in our experiments").
The teacher prompt is a fixed demonstration template (question + a golden
answer as an in-context demonstration), tokenized on the caller side —
Whitney's HTTP contract speaks only token IDs:

```text theme={null}
{question}

This is an example for a response to the question:
{golden_answer}

Now answer with a response of your own, including the thinking process.
```

**Fail closed:** You must supply a real tokenized demonstration prompt —
there is no default golden answer.

```python theme={null}
def golden_answer_prompt_tokens() -> list[int]:
    """Your own tokenized demonstration prompt (question + golden answer)."""
    ...


def build_loss(student_sample, teacher_logprobs, cycle, request, ctx):
    del teacher_logprobs  # recomputed below against the golden-answer demo prompt instead
    prompt_tokens = request["prompt"]["token_ids"]
    teacher_prompt = golden_answer_prompt_tokens()
    data = []
    for sequence in student_sample["sequences"]:
        completion_tokens = sequence["tokens"]
        full_tokens = teacher_prompt + completion_tokens
        result = ctx.client.sampler_operation(
            ctx.teacher_run_id, ctx.teacher_sampler_id, "logprobs", {"input": {"token_ids": full_tokens}}
        )
        teacher_seq_logprobs = [float(v) for v in result["logprobs"][-len(completion_tokens):]]
        student_seq_logprobs = sequence["logprobs"]
        per_token_advantage = [
            teacher_lp - student_lp
            for student_lp, teacher_lp in zip(student_seq_logprobs, teacher_seq_logprobs, strict=True)
        ]
        data.append(rl_datum(prompt_tokens, completion_tokens, student_seq_logprobs, per_token_advantage))
    return forward_backward_payload(data, "importance_sampling")
```

`rl_datum` and `forward_backward_payload` are the shared [datum helpers](/cookbooks/helpers#datum-helpers).