Pith Number

pith:37R33OJP

pith:2022:37R33OJPIO4376FPMRBNAZAPXV

not attested not anchored not stored refs pending

Multi-Vector Retrieval as Sparse Alignment

Iftekhar Naim, Jinhyuk Lee, Sai Meher Karthik Duddu, Siddhartha Brahma, Tao Lei, Vincent Y. Zhao, Yujie Qian, Zhuyun Dai

arxiv:2211.01267 v1 · 2022-11-02 · cs.CL · cs.IR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{37R33OJPIO4376FPMRBNAZAPXV}

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.

Cited by

3 papers in Pith

Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings

A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval

Receipt and verification

First computed	2026-07-05T05:12:45.522708Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

dfe3bdb92f43b9bff8af6442d0640fbd5c6f33da25c41f928cb3ebb1452e0b2f

Aliases

arxiv: 2211.01267 · arxiv_version: 2211.01267v1 · doi: 10.48550/arxiv.2211.01267 · pith_short_12: 37R33OJPIO43 · pith_short_16: 37R33OJPIO4376FP · pith_short_8: 37R33OJP

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/37R33OJPIO4376FPMRBNAZAPXV \
  | 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: dfe3bdb92f43b9bff8af6442d0640fbd5c6f33da25c41f928cb3ebb1452e0b2f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "48a2269548f66e5b0e0c1a8f91fab59166866b7620e5092cbefbe2ad8880cedd",
    "cross_cats_sorted": [
      "cs.IR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2022-11-02T16:49:58Z",
    "title_canon_sha256": "e7e3c264d655527f97e4d87ba84eb72b0d045dffcf166a57f2b7e1692ce77a80"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2211.01267",
    "kind": "arxiv",
    "version": 1
  }
}