Pith Number

pith:VDYYBT3S

pith:2025:VDYYBT3SBDQBV5VV2JDK3UNEUE

not attested not anchored not stored refs pending

Overtrained Language Models Are Harder to Fine-Tune

Aditi Raghunathan, Graham Neubig, Jacob Mitchell Springer, Kaiyue Wen, Sachin Goyal, Sadhika Malladi, Tanishq Kumar, Xiang Yue

arxiv:2503.19206 v2 · 2025-03-24 · cs.CL · 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{VDYYBT3SBDQBV5VV2JDK3UNEUE}

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

7 papers in Pith

Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors

Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay

LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning

Receipt and verification

First computed	2026-07-05T10:40:41.361873Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a8f180cf7208e01af6b5d246add1a4a10646fd5e5473cd07eeb087be3ab31c4c

Aliases

arxiv: 2503.19206 · arxiv_version: 2503.19206v2 · doi: 10.48550/arxiv.2503.19206 · pith_short_12: VDYYBT3SBDQB · pith_short_16: VDYYBT3SBDQBV5VV · pith_short_8: VDYYBT3S

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/VDYYBT3SBDQBV5VV2JDK3UNEUE \
  | 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: a8f180cf7208e01af6b5d246add1a4a10646fd5e5473cd07eeb087be3ab31c4c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5effa2240fbf278bd8a87bd10c3122ba1ff9d301b2d2251742582809469a9839",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-03-24T23:11:56Z",
    "title_canon_sha256": "1eca5615d4254a6068f7376be394a53e8f3594a60b4a065e9c79c6e05e7ef40e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.19206",
    "kind": "arxiv",
    "version": 2
  }
}