Pith Number

pith:DWA4HPO5

pith:2026:DWA4HPO55GPCEBJ4FGL62TDYBX

not attested not anchored not stored refs resolved

GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering

Junjie Hu, Ramya Korlakai Vinayak, Stockton Jenkins

GRASP achieves top accuracy on multi-hop QA benchmarks while using 40 to 50 percent fewer tokens through hierarchical graph search.

arxiv:2605.16598 v1 · 2026-05-15 · cs.MA · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DWA4HPO55GPCEBJ4FGL62TDYBX}

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

GRASP achieves the highest QA accuracy in the open retrieval setting on MuSiQue and 2Wiki while using 40-50 percent fewer tokens than IRCoT+HippoRAG2, and leads on EM and F1 across all three datasets in the LongBench setting while using 30 percent fewer tokens than the next most accurate method.

C2weakest assumption

The paper assumes that the novel three-layer hierarchical graph of entities, propositions, and passages can be built and traversed at index and inference time without introducing prohibitive construction costs or retrieval noise that would erase the reported token savings.

C3one line summary

GRASP introduces a hierarchical graph-based agentic retrieval method that achieves top accuracy on MuSiQue, 2WikiMultihopQA, and HotpotQA while using 30-50% fewer tokens than strong baselines.

References

39 extracted · 39 resolved · 3 Pith anchors

[1] Understanding Dataset Design Choices for Multi-hop Reasoning 1904 · doi:10.18653/v1/2023.findings-acl.565

[2] Lost in the Middle: How Language Models Use Long Contexts 2025 · doi:10.1162/tacl

[3] Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions 2023 · arXiv:2212.10509

[4] Write arational plan--- a 1--3 sentence outline of the reasoning chain and key facts needed

[5] Each will be answered by a research agent searching the knowledge graph

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:02:31.833520Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1d81c3bddde99e22053c2997ed4c780dd66ad77d2a59c6749a871c9dee74d00d

Aliases

arxiv: 2605.16598 · arxiv_version: 2605.16598v1 · doi: 10.48550/arxiv.2605.16598 · pith_short_12: DWA4HPO55GPC · pith_short_16: DWA4HPO55GPCEBJ4 · pith_short_8: DWA4HPO5

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/DWA4HPO55GPCEBJ4FGL62TDYBX \
  | 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: 1d81c3bddde99e22053c2997ed4c780dd66ad77d2a59c6749a871c9dee74d00d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1831d9b3d02a69af3812db20e6f0c03792bd11c7b3ee7a1f535ff41598727ef7",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.MA",
    "submitted_at": "2026-05-15T19:59:35Z",
    "title_canon_sha256": "6a675f605aec9879c6309d02a584fcd235c7ce793ea5105999ba43284abfee11"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16598",
    "kind": "arxiv",
    "version": 1
  }
}