cuda.core: refresh frozen CUresult explanation table for CUDA 13.3

[Symbioose]

Description

closes #2370

This regenerates the frozen CUresult fallback explanation table
(driver_cu_result_explanations_frozen.py) for CUDA 13.3, which added
CUDA_ERROR_GRAPH_RECAPTURE_FAILURE (code 918). This table is only used
as a fallback for cuda-bindings versions that don't yet expose usable
enum __doc__ text (see enum_explanations_helpers.py), but it needs to
stay in sync with new CUDA Toolkit error codes so those users still get
an informative error message.

Changes:

• Added the 918: "..." entry to _FALLBACK_EXPLANATIONS and bumped the
  version comment to CUDA Toolkit v13.3.
• Added a tripwire test (test_frozen_driver_table_covers_all_curesult_members)
  that compares cuda.bindings.driver.CUresult members against the frozen
  table keys, so future toolkit bumps that add new driver error codes are
  caught automatically.
• Documented the refresh step in the cuda.core release checklist
  (RELEASE-core.md).

Checklist

• New or existing tests cover these changes.
• The documentation is up to date with these changes.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[Symbioose]

Hi @leofang, this is ready for review. First-time contributor, let me know if I'm missing anything 👍, and could you add an assignee/milestone so the metadata check passes? Thanks!