The comparison & result
One policy could call chows normally; the other was prevented from calling them. Both used the same scoring rules and the normal AI for other decisions.
The published win rates were very close, and the net-points difference was small. That does not make every chow equally good. Ask whether this call improves your hand enough to justify losing concealment or narrowing your options.
At your table
Use the result to question a blanket habit. A particular hand can still favor a different decision because of its value, wait, available tiles or opponents.
Check your table’s scoring rules before applying the finding. Read the Taiwanese Classic reference.
How it was tested
Published experiment: 100,000 simulated hands under Taiwanese Classic; chow-veto seats compared with seats using normal calls. No clear overall difference was reported.
The players were software policies, not human participants. This report describes the published experiment; it does not establish the best move for every possible hand or opponent.
Results without a published uncertainty interval should be read as point estimates. Similar results do not prove two choices are equivalent.
Read the Lab’s method and limitationsPublished by Hé Fēn Mahjong. Ask about this finding or suggest a correction.