Pith Number

pith:PK5JOMRF

pith:2026:PK5JOMRFAOBHPK5XN33DHDLAJW

not attested not anchored not stored refs pending

Investigation into In-Context Learning Capabilities of Transformers

Arya Mazumdar, Leo Bangayan, Rushil Chandrupatla, Sebastian Leng

Transformers succeed at in-context binary classification on Gaussian mixtures under specific alignments of dimension, example count, and task diversity.

arxiv:2604.25858 v2 · 2026-04-28 · cs.LG · 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{PK5JOMRFAOBHPK5XN33DHDLAJW}

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

Through extensive sweeps across dimensionality, sequence length, task diversity, and signal-to-noise regimes, we identify the parameter regions in which benign overfitting arises and characterize how it depends on data geometry and training exposure.

C2weakest assumption

The linear in-context classifier formulation and controlled synthetic Gaussian-mixture setup isolate the geometric conditions under which models successfully infer task structure from context alone.

C3one line summary

Systematic sweeps show in-context test accuracy for Gaussian-mixture classification depends on input dimension, number of examples, and pre-training task count, with benign overfitting appearing in specific geometry and noise regimes.

Receipt and verification

First computed	2026-05-20T00:03:12.683711Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7aba973225038277abb76ef6338d604db00dd237970f188ca7c44d00324e0c7e

Aliases

arxiv: 2604.25858 · arxiv_version: 2604.25858v2 · doi: 10.48550/arxiv.2604.25858 · pith_short_12: PK5JOMRFAOBH · pith_short_16: PK5JOMRFAOBHPK5X · pith_short_8: PK5JOMRF

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/PK5JOMRFAOBHPK5XN33DHDLAJW \
  | 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: 7aba973225038277abb76ef6338d604db00dd237970f188ca7c44d00324e0c7e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "57b615f3453ed68939921552785edee228e347a89ddf50646e177f7f74c0c846",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-28T16:57:55Z",
    "title_canon_sha256": "363aab4bae13ae5b327633d5b6d58a0c036a091a60c5d37ab622334b33173134"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.25858",
    "kind": "arxiv",
    "version": 2
  }
}