Pith Number

pith:PPMBUTRR

pith:2026:PPMBUTRRQXVWHMAIVDMHFJNOSZ

not attested not anchored not stored refs pending

Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent

Emir Poyraz, Karthik Ramgopal, Praveen Kumar Bodigutla, Shangjin Zhang, Xiaofeng Wang, Xiaoyang Gu, Xie Lu, Ye Jin, Yvonne Li, Zhentao Xu

A schema-aligned hierarchical memory tree lets LLM agents store and retrieve long-term semantic knowledge with over 10% gains in correctness and retrieval quality.

arxiv:2604.26197 v2 · 2026-04-29 · cs.IR · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PPMBUTRRQXVWHMAIVDMHFJNOSZ}

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

HLTM improves answer correctness and retrieval F1 significantly by more than 10%, while significantly advancing the Pareto frontier between query and indexing latency. HLTM has been deployed in LinkedIn's Hiring Assistant to power core personalization features in production hiring workflows.

C2weakest assumption

That the schema-aligned memory tree and adaptation mechanism generalize across diverse use cases and that the claimed >10% gains on LinkedIn's internal Hiring Assistant data reflect real-world improvements without undisclosed data selection or baseline choices.

C3one line summary

HLTM builds a hierarchical memory tree from longitudinal data to enable scalable, private, low-latency retrieval, delivering over 10% gains in answer correctness and retrieval F1 for LinkedIn's Hiring Assistant while improving the query-indexing latency tradeoff.

Receipt and verification

First computed	2026-05-27T01:04:58.454743Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7bd81a4e3185eb63b008a8d872a5ae965cb427d5db58613061b21926e33c34fe

Aliases

arxiv: 2604.26197 · arxiv_version: 2604.26197v2 · doi: 10.48550/arxiv.2604.26197 · pith_short_12: PPMBUTRRQXVW · pith_short_16: PPMBUTRRQXVWHMAI · pith_short_8: PPMBUTRR

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/PPMBUTRRQXVWHMAIVDMHFJNOSZ \
  | 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: 7bd81a4e3185eb63b008a8d872a5ae965cb427d5db58613061b21926e33c34fe

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a48c99cadd423f56bef2122474501a2d36a47fbeff05a60f7b2665dd9823e8d1",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-04-29T00:53:52Z",
    "title_canon_sha256": "c5d9d2e3b8f601d8c88eccf1b704453dedc27189d4afbe2778015c9686e652ba"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.26197",
    "kind": "arxiv",
    "version": 2
  }
}