Pith Number

pith:2MYR2HSV

pith:2026:2MYR2HSV7CYX4VNAN26R6X3IYE

not attested not anchored not stored refs resolved

Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning

Arthur S. Bianchessi, Christian Mattjie, Joana Pasquali, Jo\~ao Vitor Boer Abitante, Lucas S. Kupssinsk\"u, Ot\'avio Parraga, Rafaela Cappelari Ravazio, Ramiro N. Barros, Rodrigo C. Barros, Vin\'icius Conte Turani

SLICE initializes LoRA adapters by projecting current and replay gradients then applying truncated SVD to reduce catastrophic forgetting in continual learning.

arxiv:2605.12752 v1 · 2026-05-12 · 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{2MYR2HSV7CYX4VNAN26R6X3IYE}

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

Compared to vanilla LoRA, LoRA-GA, and LoRAM, SLICE consistently achieves a better stability-plasticity trade-off, improving Average Performance, Final Performance and Forgetting metrics while preserving General Performance and In Context Performance across both standard and adversarial continual learning sequences.

C2weakest assumption

That the projection operator applied to accumulated current-task and replay gradients, followed by truncated SVD, reliably channels updates into subspaces that avoid overwriting previously learned directions without introducing new interference or instability.

C3one line summary

SLICE applies gradient surgery via projection and truncated SVD to initialize LoRA adapters, yielding better stability-plasticity trade-offs on continual learning benchmarks including adversarial task sequences.

References

41 extracted · 41 resolved · 0 Pith anchors

[1] and Hajishirzi, Hannaneh and Khashabi, Daniel , booktitle = 2022 · doi:10.18653/v1/2022.emnlp-main.340

[2] TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models , author=. 2023 , eprint= 2023

[3] The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=

[4] Nature Machine Intelligence , volume= 2025

[5] Chenlong Zhang and Zhuoran Jin and Hongbang Yuan and Jiaheng Wei and Tong Zhou and Kang Liu and Jun Zhao and Yubo Chen , booktitle=. 2025 , url= 2025

Receipt and verification

First computed	2026-05-18T03:09:48.735110Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d3311d1e55f8b17e55a06ebd1f5f68c1025160fb359a75d8e4b80029c8ccd10d

Aliases

arxiv: 2605.12752 · arxiv_version: 2605.12752v1 · doi: 10.48550/arxiv.2605.12752 · pith_short_12: 2MYR2HSV7CYX · pith_short_16: 2MYR2HSV7CYX4VNA · pith_short_8: 2MYR2HSV

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/2MYR2HSV7CYX4VNAN26R6X3IYE \
  | 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: d3311d1e55f8b17e55a06ebd1f5f68c1025160fb359a75d8e4b80029c8ccd10d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ece6f9960e995c19791123bd6a4d83755bd7db56e1331e3ac7c533225a36ecdb",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T21:06:03Z",
    "title_canon_sha256": "3e47e494325e05d37d6dd634f0e63dabbb1709d60463e7d92c67df390f757553"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12752",
    "kind": "arxiv",
    "version": 1
  }
}