From 154e33683e040bf778518658bcc5a082ce18365f Mon Sep 17 00:00:00 2001
From: wassname <1103714+wassname@users.noreply.github.com>
Date: Thu, 4 Jun 2026 15:20:04 +0800
Subject: [PATCH] paper: HARVE byline cross-verified arXiv==S2 (keyed
 semantic-search .env)

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
---
 docs/writeup/refs.bib | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/docs/writeup/refs.bib b/docs/writeup/refs.bib
index 26ab416..7ea8ea0 100644
--- a/docs/writeup/refs.bib
+++ b/docs/writeup/refs.bib
@@ -240,8 +240,9 @@
 % Closest published analogue to our contrastive-SVD extraction, but on the static
 % reward MODEL not the live policy gradient: build a multi-directional hacking
 % subspace from residual-stream diffs of contrastive gold-vs-hacked pairs, project
-% the reward-head vector off it. Authors scraped from arXiv (S2/DBLP not yet
-% indexed as of 2026-06-04); abstract from arXiv. "\model" -> HARVE inlined.
+% the reward-head vector off it. 7-author byline cross-verified arXiv == Semantic
+% Scholar (keyed S2 API via the semantic-search skill .env); abstract from arXiv.
+% "\model" -> HARVE inlined.
 @misc{liu2026harve,
   title        = {HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models},
   author       = {Liu, Shuang and Bo, Yuxuan and Zhao, Qiuyang and Huang, Caiyue and Chen, Xiaorong and Liu, Yanguang and Du, Mengnan},