MuRIL fine-tuned for native Hindi/Punjabi farmer-query intent classification (pest_id/irrigation/mandi_price/scheme_eligibility/ other). AutoScientist Challenge Part 2, Agriculture category.

Accuracy 92.5%, Macro-F1 0.240 (held-out 20% split, 40 rows).

Known limitation, disclosed honestly — the most extreme in this round's five submissions: built without ULCA registration (multi-day external dependency) to fit the deadline, using IndicCorpV2 general web text instead of genuine farmer queries. The high accuracy is almost entirely the other class's dominance (182/200 training rows), not genuine skill distinguishing pest_id/irrigation/mandi_price/ scheme_eligibility (2-6 examples each). The pipeline is validated and ready for real ULCA farmer-query data; see the source project's PART2_SUBMISSION.md for the full writeup.