write up

docs/writeup/refs.bib

@@ -70,3 +70,55 @@
   year         = {TODO},
   note         = {UNVERIFIED -- fill or remove before submission}
 }
+
+% --- gradient-routing / projection related work --------------------------
+% All three below verified against full-text local copies in
+% docs/grad_routing/ (title + arXiv id + url read from the file headers,
+% 2026-05-31). Author fields filled only where the byline was read.
+
+% THE NEAR-TWIN: singular directions of param-updates + project gradients ONTO
+% a clean reference subspace (we subtract a hack subspace instead). Byline read
+% from docs/grad_routing/paper_deng_trusted_direction.md; note the curated
+% related_work.md calls it "TDGA / Deng" -- TODO reconcile the lead-author label.
+@misc{huang2026directional,
+  title        = {Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models},
+  author       = {Huang, Jiaji and Ozkara, Kaan and Li, Yushu and Thrampoulidis, Christos and Li, Xiaoxiao and Park, Youngsuk},
+  year         = {2026},
+  eprint       = {2605.25189},
+  archivePrefix= {arXiv},
+  primaryClass = {cs.LG},
+  url          = {https://arxiv.org/abs/2605.25189}
+}
+
+% Parameter-gradient zero-mask routing (Selective Gradient Masking, SGTM)
+% tolerant to label noise; measures leakage and shows it shrinks with scale.
+% Title + author byline web-verified 2026-06-02 (arxiv.org/abs/2512.05648).
+@misc{sgtm2025localization,
+  title        = {Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs},
+  author       = {Shilov, Igor and Cloud, Alex and Gema, Aryo Pradipta and Goldman-Wetzler, Jacob and Panickssery, Nina and Sleight, Henry and Jones, Erik and Anil, Cem},
+  year         = {2025},
+  eprint       = {2512.05648},
+  archivePrefix= {arXiv},
+  primaryClass = {cs.LG},
+  url          = {https://arxiv.org/abs/2512.05648}
+}
+
+% Reward-for-confession honesty (we reject this design: invites Baker
+% obfuscation + a live judge over student rollouts). Byline read from header.
+@misc{joglekar2025confessions,
+  title        = {Training LLMs for Honesty via Confessions},
+  author       = {Joglekar, Manas and Chen, Jeremy and Wu, Gabriel and Yosinski, Jason and Wang, Jasmine and Barak, Boaz and Glaese, Amelia},
+  year         = {2025},
+  eprint       = {2512.08093},
+  archivePrefix= {arXiv},
+  primaryClass = {cs.LG},
+  url          = {https://arxiv.org/abs/2512.08093}
+}
+
+% --- abstract-only "closest twins" (NOT full-text verified) --------------
+% IDs from docs/grad_routing/{related_work,search_for_more}.md. Authors NOT
+% filled (not read) -- do not cite as @misc with invented authors. Verify
+% byline from arXiv before promoting any of these into the bibliography:
+%   GRIFT (gradient fingerprints to detect/reject hacking)  arXiv:2604.16242
+%   Spilling the Beans (SFT self-report generalises OOD)    arXiv:2511.06626
+%   Baker et al. (weak monitor -> obfuscated reward hacking) arXiv:2503.11926