pith. sign in
Pith Number

pith:KOOOY6EI

pith:2026:KOOOY6EIT5TYMEWJAVZE4RXDL3
not attested not anchored not stored refs resolved

When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context

Haobin Pan, Hao Fu, Haojun Weng, Qianqian Yang, Xinwei Lv

Stale repository context actively biases code models toward generating outdated helper references.

arxiv:2605.14478 v1 · 2026-05-14 · cs.SE · cs.AI · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KOOOY6EIT5TYMEWJAVZE4RXDL3}

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

Under neutralized prompts, stale-only retrieval induces stale helper references on 15/17 Qwen2.5-Coder-7B-Instruct samples and 13/17 gpt-4.1-mini samples, corresponding to 88.2 and 76.5 percentage-point increases over current-only retrieval.

C2weakest assumption

The curated 17-sample set of production-helper signature changes from five Python repositories is representative of typical real-world code completion scenarios and that the prompts successfully neutralize information about commit freshness.

C3one line summary

Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.

References

16 extracted · 16 resolved · 3 Pith anchors

[1] When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation 2026 · arXiv:2604.09515
[2] L. Liang, J. Gong, M. Liu, C. Wang, G. Ou, Y. Wang, X. Peng, Z. Zheng, RustEvo2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation (2025).arXiv:2503.16922. URLhttps://arxiv.org 2025
[3] arXiv preprint arXiv:2303.12570 , year= 2023
[4] S. Zhang, Y. Ding, S. Lian, S. Song, H. Li, CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion (2025).arXiv:2509.16112. URLhttps://arxiv.org/abs 2025
[5] RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems 2023 · arXiv:2306.03091

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-17T23:39:06.577950Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

539cec78889f678612c905724e46e35ed6a2ac54bc41089a901355b0958d47c6

Aliases

arxiv: 2605.14478 · arxiv_version: 2605.14478v1 · doi: 10.48550/arxiv.2605.14478 · pith_short_12: KOOOY6EIT5TY · pith_short_16: KOOOY6EIT5TYMEWJ · pith_short_8: KOOOY6EI
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KOOOY6EIT5TYMEWJAVZE4RXDL3 \
  | 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: 539cec78889f678612c905724e46e35ed6a2ac54bc41089a901355b0958d47c6
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "1464a870e7d605fb38c5b9105a1aad2e71bff0904458d47766ff1896f6d526bc",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-14T07:18:30Z",
    "title_canon_sha256": "4553a21d20eaa7c48991bf3a32b1010e027864b515607e39a4b2725a9729fd08"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14478",
    "kind": "arxiv",
    "version": 1
  }
}