Measurements & working papers
A simulated Ahmedabad mithai shop shows how a moving Diwali can mislead history-only forecasts; calendar inputs and sell-out aware planning improve decisions in this controlled study.
152 coding tasks in seven language setups: compiler feedback rescues many attempts, but every toolchain still accepts wrong programs.
A 50-task local coding run measures test passes and decode throughput, not sustained free capacity.
Five tokenizers, six languages and 300 aligned rows show a wide spread in token counts.
A measured CPU case study separates local routing performance from illustrative cost assumptions.