Pith Number

pith:ZL33BJGS

pith:2023:ZL33BJGSXS2UZIDL7XE5A3XWFM

not attested not anchored not stored refs pending

One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention

Arvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma

arxiv:2307.03576 v1 · 2023-07-07 · 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{ZL33BJGSXS2UZIDL7XE5A3XWFM}

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

6 papers in Pith

Transformers Provably Learn to Internalize Chain-of-Thought

Provable Knowledge Acquisition and Extraction in One-Layer Transformers

A Survey on In-context Learning

One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning

Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer

Receipt and verification

First computed	2026-07-05T06:28:44.668635Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

caf7b0a4d2bcb54ca06bfdc9d06ef62b0145c950af173d39c04b622972f1717d

Aliases

arxiv: 2307.03576 · arxiv_version: 2307.03576v1 · doi: 10.48550/arxiv.2307.03576 · pith_short_12: ZL33BJGSXS2U · pith_short_16: ZL33BJGSXS2UZIDL · pith_short_8: ZL33BJGS

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/ZL33BJGSXS2UZIDL7XE5A3XWFM \
  | 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: caf7b0a4d2bcb54ca06bfdc9d06ef62b0145c950af173d39c04b622972f1717d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8cefd9893c974e40c907978a7ae10cff1263b79253e799c92d6c7b2693691ada",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2023-07-07T13:09:18Z",
    "title_canon_sha256": "3cc35278798ce418cc7f2b504ff6c6c8d7df81560bd7f48b1d542af9dde3bd64"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2307.03576",
    "kind": "arxiv",
    "version": 1
  }
}