Pith Number

pith:YER45XPB

pith:2026:YER45XPBBQFOA2GSISPGBYIF45

not attested not anchored not stored refs resolved

Differentially Private Motif-Preserving Multi-modal Hashing

Jiahao Sun, Wei Dai, Zehua Cheng

Degree clipping before noisy synthesis lets differentially private multi-modal hashing retain up to 92.5 percent of non-private retrieval accuracy.

arxiv:2605.15460 v1 · 2026-05-14 · cs.IR · 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{YER45XPBBQFOA2GSISPGBYIF45}

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

DMP-MH outperforms private baselines by up to 11.4 mAP points while retaining up to 92.5% of non-private performance on MIRFlickr-25K and NUS-WIDE under a strict inductive protocol.

C2weakest assumption

That deterministically clipping node degrees to a fixed threshold caps the L2-sensitivity of triangle motifs independently of dataset size and still leaves enough structural signal for the downstream hashing loss to recover useful cross-modal alignments.

C3one line summary

DMP-MH clips degrees to control triangle sensitivity, synthesizes an edge-DP graph with Noisy Mirror Descent, and distills it into dual-stream hash networks, beating private baselines by up to 11.4 mAP on MIRFlickr-25K and NUS-WIDE while keeping 92.5% of non-private performance.

References

43 extracted · 43 resolved · 5 Pith anchors

[1] Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. 2016. Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC conference on 2016

[2] Tadas Baltrušaitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multi- modal machine learning: A survey and taxonomy.IEEE transactions on pattern analysis and machine intelligence41, 2 (2018), 2018

[3] Albert-László Barabási and Réka Albert. 1999. Emergence of scaling in random networks.science286, 5439 (1999), 509–512 1999

[4] Austin R Benson, David F Gleich, and Jure Leskovec. 2016. Higher-order organi- zation of complex networks.Science353, 6295 (2016), 163–166 2016

[5] Dimitri P. Bertsekas. 1999.Nonlinear Programming(2 ed.). Athena Scientific 1999

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:59.720643Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c123cedde10c0ae068d2449e60e105e7558572c75a73cc6201f3b070a37e64eb

Aliases

arxiv: 2605.15460 · arxiv_version: 2605.15460v1 · doi: 10.48550/arxiv.2605.15460 · pith_short_12: YER45XPBBQFO · pith_short_16: YER45XPBBQFOA2GS · pith_short_8: YER45XPB

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/YER45XPBBQFOA2GSISPGBYIF45 \
  | 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: c123cedde10c0ae068d2449e60e105e7558572c75a73cc6201f3b070a37e64eb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "62263ae63dafad58291d982776f6e1a16bea20e2c13717e7f870bce567e892be",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-14T22:43:30Z",
    "title_canon_sha256": "4a18356291197261c8689a35ef5c251e3318b10835fcc221d96182ce65e48f61"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15460",
    "kind": "arxiv",
    "version": 1
  }
}