Pith Number

pith:5TZU32T3

pith:2026:5TZU32T3LGNTIZFNTLZ5BC63IM

not attested not anchored not stored refs pending

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning

Alexander Panchenko, Andrey Savchenko, Anna Borisiuk, Elena Tutubalina

An SFT step on data to forget produces smoother unlearning and 10-50% higher retention than direct unlearning on pretrained models.

arxiv:2602.19612 v5 · 2026-02-23 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5TZU32T3LGNTIZFNTLZ5BC63IM}

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

An SFT step on the forget data yields smoother forgetting, more stable tuning, and 10-50% higher retention, while direct unlearning on pretrained models remains unstable and prone to relearning or catastrophic forgetting.

C2weakest assumption

That differences in unlearning behavior are caused primarily by the presence or absence of an SFT stage rather than by other uncontrolled factors such as model scale, exact unlearning algorithm, or how salience scores correlate with actual memorization.

C3one line summary

SFT models forget facts more stably than pretrained models, with 10-50% higher retention of unrelated knowledge when using the DUET benchmark of 28.6k Wikidata triplets.

Receipt and verification

First computed	2026-06-02T01:03:44.008905Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ecf34dea7b599b3464ad9af3d08bdb43350e9dac9c9d80af0b07c898c1874796

Aliases

arxiv: 2602.19612 · arxiv_version: 2602.19612v5 · doi: 10.48550/arxiv.2602.19612 · pith_short_12: 5TZU32T3LGNT · pith_short_16: 5TZU32T3LGNTIZFN · pith_short_8: 5TZU32T3

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/5TZU32T3LGNTIZFNTLZ5BC63IM \
  | 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: ecf34dea7b599b3464ad9af3d08bdb43350e9dac9c9d80af0b07c898c1874796

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7e9828fa6ed3d49f86bf0bafd1df172b82b768bb42d79c5a882f47f1577302aa",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-02-23T08:58:48Z",
    "title_canon_sha256": "118cd29d8427b7c8a773293d846cdc0b8a3244082c953df518bcdd424bc4149a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.19612",
    "kind": "arxiv",
    "version": 5
  }
}