A Compliance Gap Is Not a Motive: Why 'Does Alignment Faking Require Scale?' Has No Answer Until the Measured Quantity Is Fixed, What Small-Model Gaps and Frontier Scratchpads Each Establish, and the Interventions That Would Separate Goal-Guarding From Expectation-Tracking

APA

Mahendrakar, P. (2026). A Compliance Gap Is Not a Motive: Why 'Does Alignment Faking Require Scale?' Has No Answer Until the Measured Quantity Is Fixed, What Small-Model Gaps and Frontier Scratchpads Each Establish, and the Interventions That Would Separate Goal-Guarding From Expectation-Tracking [Preprint]. Life of Research. https://doi.org/10.5281/zenodo.23478872

Copy APA

BibTeX

@misc{lor1202026,
  title        = {A Compliance Gap Is Not a Motive: Why 'Does Alignment Faking Require Scale?' Has No Answer Until the Measured Quantity Is Fixed, What Small-Model Gaps and Frontier Scratchpads Each Establish, and the Interventions That Would Separate Goal-Guarding From Expectation-Tracking},
  author       = {Pranay Mahendrakar},
  year         = {2026},
  publisher    = {Life of Research},
  doi          = {10.5281/zenodo.23478872},
  url          = {https://lifeofresearch.com/preprints/120},
  keywords     = {alignment faking, deceptive alignment, compliance gap, scheming evaluations, construct validity, evaluation awareness, chain-of-thought faithfulness, model scale},
  note         = {LOR-00120}
}

Copy BibTeX More on the record page