Prompt complexity predicts code-gen failure, but the breakpoint moves with task type.

arXiv 2609.19616 argues complexity measured from generated code is failure-dependent, since a hard prompt producing a short broken program scores as low complexity. Scoring 5,000 Python prompts on a six-dimension prompt-side index before generation, with 19,997 rescoring rows from four out-of-panel LLM raters at ICC 0.872 and 21 models per prompt for 105,000 generations, the pooled pass rate breaks at composite 13.75. Task-type fixed effects move the breakpoint to 10.75 and shrink the regime gap from 7.6 points to 2.1. arXiv Per-task-type calibration tool, not a universal cutoff.