When $\text{105}$ Becomes $10^5$: Prior-Induced Literal Override in Competitive-Programming Code Generation

Competitive-programming constraints determine which algorithms are computationally feasible. We study a specification-faithfulness failure in which an authoritative decimal literal also resembles a fused power-of-ten expression: $\text{105}$ is the integer 105 but also the surface left by deleting the exponent marker from $10^5$. We call this prior-induced literal override. The corruption itself already appears at scale in CodeContests-O: among 11,683 problem descriptions, 3,008 (25.75%) contain at least one studied fused surface, and the matched occurrences were verified as exponent-loss cases rather than intended decimals. Holding the critical digits fixed, we vary semantic context and pair every collision with a same-length non-collision control. Across four open-weight models, attractor share is effectively zero in neutral copying but rises to 74.5% in full problem statements; unprompted greedy override reaches 64.3%. Direct literal disambiguation reduces attraction by about 50–52 percentage points, whereas generic self-verification has little effect. Across ten competitive-programming problems and six frontier code models, the collision surface $\text{105}$ lowers executable performance relative to literal-scale controls and often shifts generated programs toward the regime induced by an explicit $10^5$ constraint. Supporting probability, tokenization, and residual-stream analyses connect the shift to the literal–attractor competition. The failure is not repair itself, but failure to condition repair on source authority.