Pith Number

pith:RWT45WHE

pith:2026:RWT45WHEDQ2T77UZTST5ALRBRS

not attested not anchored not stored refs pending

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning

Anirudh Kanchi, Garv Shah, Prakhar Gupta, Satyam Goyal

Sparse Memory Finetuning updates only the most heavily read rows in added key-value layers to gain task performance while preserving general capabilities better than LoRA or full finetuning.

arxiv:2605.03229 v2 · 2026-05-04 · cs.CL · 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{RWT45WHEDQ2T77UZTST5ALRBRS}

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

SMF improves MedMCQA by 2.5 percentage points while keeping both forgetting probes within roughly 1 point of the base model, whereas LoRA and full finetuning achieve larger gains but with clear drift on both.

C2weakest assumption

That selectively updating only the most heavily read memory rows during training is sufficient to acquire new task knowledge without unintended interference in unrelated general capabilities.

C3one line summary

SMF improves MedMCQA accuracy by 2.5 points while keeping WikiText perplexity and TriviaQA accuracy within 1 point of the base model, outperforming LoRA and full finetuning on forgetting metrics.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-06-09T02:08:43.618522Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8da7ced8e41c353ffe999ca7d02e218cb8181a55c59ecfcb1bb850111953d964

Aliases

arxiv: 2605.03229 · arxiv_version: 2605.03229v2 · doi: 10.48550/arxiv.2605.03229 · pith_short_12: RWT45WHEDQ2T · pith_short_16: RWT45WHEDQ2T77UZ · pith_short_8: RWT45WHE

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/RWT45WHEDQ2T77UZTST5ALRBRS \
  | 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: 8da7ced8e41c353ffe999ca7d02e218cb8181a55c59ecfcb1bb850111953d964

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f5f1f66b2cd960f80551f3f7b38a468e1641e83de9f26e9393a906e31f0a5c58",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-04T23:46:40Z",
    "title_canon_sha256": "a9199ad6290c362e71d7ebdeb0f59de454c47aeaa7e76e814a1cd0e7cca22e0a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03229",
    "kind": "arxiv",
    "version": 2
  }
}