Pith Number

pith:LBD7VJZ3

pith:2020:LBD7VJZ3AAMW6R3HYSZ4D7GTV7

not attested not anchored not stored refs pending

Training Production Language Models without Memorizing User Data

Fran\c{c}oise Beaufays, Galen Andrew, H. Brendan McMahan, Om Thakkar, Rajiv Mathews, Swaroop Ramaswamy

arxiv:2009.10031 v1 · 2020-09-21 · cs.LG · cs.CR · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LBD7VJZ3AAMW6R3HYSZ4D7GTV7}

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

Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning

Quantifying Memorization Across Neural Language Models

Ethical and social risks of harm from Language Models

Receipt and verification

First computed	2026-07-05T01:36:55.636311Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5847faa73b00196f4767c4b3c1fcd3aff47d65e6538c01b2989e6530be633784

Aliases

arxiv: 2009.10031 · arxiv_version: 2009.10031v1 · doi: 10.48550/arxiv.2009.10031 · pith_short_12: LBD7VJZ3AAMW · pith_short_16: LBD7VJZ3AAMW6R3H · pith_short_8: LBD7VJZ3

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/LBD7VJZ3AAMW6R3HYSZ4D7GTV7 \
  | 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: 5847faa73b00196f4767c4b3c1fcd3aff47d65e6538c01b2989e6530be633784

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3188143dc9b18d33423c4d759a0c6dff158eb076c37489b7d0bfed3a99c43319",
    "cross_cats_sorted": [
      "cs.CR",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2020-09-21T17:12:33Z",
    "title_canon_sha256": "0ba685b00919662f21b0e903c5d9aa9463983340c599a895a71095c147bd7db8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2009.10031",
    "kind": "arxiv",
    "version": 1
  }
}