pith. sign in
Pith Number

pith:AOA5CRYT

pith:2026:AOA5CRYTGYAWL3TOLVLRUFY54X
not attested not anchored not stored refs pending

SinkTrack: Attention Sink based Context Anchoring for Large Language Models

Guikun Chen, Wenguan Wang, Xu Liu

By injecting contextual features into the attention sink token, SinkTrack keeps large language models focused on the original input throughout generation, reducing hallucination and forgetting.

arxiv:2604.10027 v2 · 2026-04-11 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{AOA5CRYTGYAWL3TOLVLRUFY54X}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Experiments demonstrate that SinkTrack mitigates hallucination and context forgetting across both textual (e.g., +21.6% on SQuAD2.0 with Llama3.1-8B-Instruct) and multi-modal (e.g., +22.8% on M3CoT with Qwen2.5-VL-7B-Instruct) tasks.

C2weakest assumption

That consistently high attention to the BOS token can be reliably turned into an effective context anchor simply by injecting input-derived features into its representation, without side effects or the need for per-model tuning.

C3one line summary

SinkTrack uses attention sink at the BOS token to anchor LLMs to initial context, reducing hallucination and forgetting with reported gains on benchmarks like SQuAD2.0 and M3CoT.

Receipt and verification
First computed 2026-05-20T00:03:10.951599Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0381d14713360165ee6e5d571a171de5c55bb14cedd8d0a2dd427ec5971eaa16

Aliases

arxiv: 2604.10027 · arxiv_version: 2604.10027v2 · doi: 10.48550/arxiv.2604.10027 · pith_short_12: AOA5CRYTGYAW · pith_short_16: AOA5CRYTGYAWL3TO · pith_short_8: AOA5CRYT
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/AOA5CRYTGYAWL3TOLVLRUFY54X \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0381d14713360165ee6e5d571a171de5c55bb14cedd8d0a2dd427ec5971eaa16
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "9a6b7ffd67c7940fc0dbfaa9ae4eca0cba0eb505ff3e43d86d7c1c2f52926df2",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-11T04:49:11Z",
    "title_canon_sha256": "ba402a401de0d1f987d99155a85e176303d86d3f7eea795b622b9d17c2b8a8ee"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.10027",
    "kind": "arxiv",
    "version": 2
  }
}