pith. sign in
Pith Number

pith:OCE52TNQ

pith:2026:OCE52TNQ2VO3NRYLE5MFIYB422
not attested not anchored not stored refs resolved

Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG

Maximilian von Zastrow, Riccardo Terrenzi, Serkan Ayvaz

In Agentic GraphRAG, accurate answers depend on both cited evidence and the uncited traversal context from the agent's graph exploration.

arxiv:2605.15109 v1 · 2026-05-14 · cs.AI · cs.IR

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{OCE52TNQ2VO3NRYLE5MFIYB422}

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

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

Our results show that cited evidence is often necessary, as removing it substantially changes answers and reduces accuracy. However, citations are not sufficient, because accurate answers can also depend on uncited traversal context and surrounding graph structure.

C2weakest assumption

The controlled ablation experiments (isolating, removing, and masking cited and uncited graph entities) accurately isolate the causal influence of traversal context without artifacts from the specific graphs, agents, or masking procedures used.

C3one line summary

In Agentic GraphRAG, cited evidence is necessary but not sufficient for accurate answers, as uncited traversal context and graph structure also affect results, requiring evaluation of the full retrieval trajectory.

References

12 extracted · 12 resolved · 1 Pith anchors

[1] L. Huang, W. Yu, W. Ma, W. Zhong, Z. Feng, H. Wang, Q. Chen, W. Peng, X. Feng, B. Qin, et al., A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions, 2025
[2] A. T. Kalai, O. Nachum, S. S. Vempala, E. Zhang, Evaluating large language models for accuracy incentivizes hallucinations, Nature (2026). URL: https://doi.org/10.1038/s41586-026-10549-w. doi:10.1038/ 2026 · doi:10.1038/s41586-026-10549-w
[3] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, S. Riedel, D. Kiela, Retrieval-augmented generation for knowledge-intensive nlp task 2020
[4] B. Peng, Y. Zhu, Y. Liu, X. Bo, H. Shi, C. Hong, Y. Zhang, S. Tang, Graph retrieval-augmented generation: A survey, ACM Transactions on Information Systems 44 (2025) 1–52 2025
[5] Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions.Artificial Intelligence Review, 59(11) 2025 · doi:10.1007/s10462-025-11422-4
Receipt and verification
First computed 2026-05-17T21:40:25.756355Z
Last reissued 2026-05-17T21:57:19.086859Z
Builder pith-number-builder-2026-05-17-v1
Signature unsigned_v0
Schema pith-number/v1.0

Canonical hash

7089dd4db0d55db6c70b275854603cd6b89eb0e7c8e7ca88f1eeb3487d64666f

Aliases

arxiv: 2605.15109 · arxiv_version: 2605.15109v1 · pith_short_12: OCE52TNQ2VO3 · pith_short_16: OCE52TNQ2VO3NRYL · pith_short_8: OCE52TNQ
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/OCE52TNQ2VO3NRYLE5MFIYB422 \
  | 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: 7089dd4db0d55db6c70b275854603cd6b89eb0e7c8e7ca88f1eeb3487d64666f
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "bd93ea7898bb9030aab9d1f510a5c23a698d870f6490b8b2164188228093100f",
    "cross_cats_sorted": [
      "cs.IR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T17:25:20Z",
    "title_canon_sha256": "342a1aaff5ff97c4cce40545f89f31e17ac775241ec97c5c13be933ab23d36cd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15109",
    "kind": "arxiv",
    "version": 1
  }
}