OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
Claude 4.6.https://www.anthropic.com/claude
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.