Pith Number

pith:XKG5HDJH

pith:2024:XKG5HDJH2XG2WSHL3JKFOVEGDJ

not attested not anchored not stored refs pending

Soft-TransFormers for Continual Learning

Chang D. Yoo, Haeyong Kang

Task-specific multiplicative masks on attention projections enable continual learning in frozen pre-trained transformers with minimal added parameters.

arxiv:2411.16073 v4 · 2024-11-25 · cs.LG · cs.AI · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{XKG5HDJH2XG2WSHL3JKFOVEGDJ}

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 multiple continual learning benchmarks, Soft-TF achieves state-of-the-art performance, consistently outperforming prompt-based, adapter-based, and LoRA-style baselines while requiring minimal additional parameters.

C2weakest assumption

The central claim depends on the premise that task-specific multiplicative masks applied to the key, query, value, and output projections in self-attention, together with a lightweight dual-prompt mechanism, will enable smooth task adaptation while preserving shared representations in the frozen pre-trained transformer.

C3one line summary

Soft-TF learns task-specific multiplicative masks on transformer self-attention layers combined with dual prompts to achieve SOTA continual learning performance with minimal added parameters.

Receipt and verification

First computed	2026-07-22T01:22:09.600324Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ba8dd38d27d5cdab48ebda545754861a5a6572ea559afa25cb6c370b0853c6b5

Aliases

arxiv: 2411.16073 · arxiv_version: 2411.16073v4 · doi: 10.48550/arxiv.2411.16073 · pith_short_12: XKG5HDJH2XG2 · pith_short_16: XKG5HDJH2XG2WSHL · pith_short_8: XKG5HDJH

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/XKG5HDJH2XG2WSHL3JKFOVEGDJ \
  | 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: ba8dd38d27d5cdab48ebda545754861a5a6572ea559afa25cb6c370b0853c6b5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f31acb0b0abf2d3e5157b18a9effc475e2a54a029e7a1e40a2411717cd0ba219",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-11-25T03:52:47Z",
    "title_canon_sha256": "e7581f2ed6b79d16e25d45d2b3648fc39fdb50e122bf029079f83f9b51c4a499"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2411.16073",
    "kind": "arxiv",
    "version": 4
  }
}