Pith Number

pith:T6HXDXI5

pith:2026:T6HXDXI5T6DCCNYEMDWBKLT24O

not attested not anchored not stored refs pending

Class Unlearning via Depth-Aware Removal of Forget-Specific Directions

Arman Hatami, Ilya E. Monosov, Romina Aalishah

By projecting out forget-specific directions layer by layer with depth-aware scaling, a closed-form method achieves class unlearning closer to full retraining than prior approaches.

arxiv:2604.15166 v2 · 2026-04-16 · cs.CV · cs.AI · 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{T6HXDXI5T6DCCNYEMDWBKLT24O}

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

Across MNIST, CIFAR-10, CIFAR-100, and Tiny ImageNet, and across convolutional and transformer architectures, DAMP more closely resembles the retraining gold standard than some of the prior methods, improving selective forgetting while better preserving retain-class performance and reducing residual forget-class structure in deep layers.

C2weakest assumption

That forget directions extracted as residuals relative to retain-class prototypes at each layer accurately isolate the targeted knowledge, and that the parameter-free depth-aware scaling derived from probe separability will preserve utility without introducing new failure modes on retain classes.

C3one line summary

DAMP performs one-shot class unlearning by extracting and projecting out forget-specific residual directions at each network depth using class prototypes and a separability-derived scaling rule.

Cited by

1 paper in Pith

Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation

Receipt and verification

First computed	2026-05-20T02:05:43.203711Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9f8f71dd1d9f8621370460ec152e7ae38ebf59870be78a60f56e61b6503c9373

Aliases

arxiv: 2604.15166 · arxiv_version: 2604.15166v2 · doi: 10.48550/arxiv.2604.15166 · pith_short_12: T6HXDXI5T6DC · pith_short_16: T6HXDXI5T6DCCNYE · pith_short_8: T6HXDXI5

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/T6HXDXI5T6DCCNYEMDWBKLT24O \
  | 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: 9f8f71dd1d9f8621370460ec152e7ae38ebf59870be78a60f56e61b6503c9373

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c0ad3f258483854b11b7e8c6a5cfb15767e9be967efcd7e68a2d2e6a8ac57a69",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-16T15:46:02Z",
    "title_canon_sha256": "9599830383a0f2641a0b445a59d5275738d96d4977a5d3214365f5153c26e668"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.15166",
    "kind": "arxiv",
    "version": 2
  }
}