Pith Number

pith:WK2R4PQT

pith:2026:WK2R4PQTKOWYCBXE7ZX7BLOAPG

not attested not anchored not stored refs resolved

Continual Fine-Tuning of Large Language Models via Program Memory

Hung Le, Svetha Venkatesh

Organizing LoRA adapters into input-retrieved program memory slots improves retention and reduces catastrophic forgetting during sequential fine-tuning of large language models.

arxiv:2605.13162 v1 · 2026-05-13 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WK2R4PQTKOWYCBXE7ZX7BLOAPG}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

Experiments on diverse benchmarks demonstrate improved retention and reduced catastrophic forgetting over other continual LoRA strategies.

C2weakest assumption

That input-conditioned attention can reliably retrieve and consolidate short-term LoRA updates into a stable distributed representation while preserving unused capacity for future tasks, without introducing hidden costs or interference.

C3one line summary

ProCL organizes LoRA adapters into input-conditioned program memory slots that combine with a distributed adapter to improve retention and reduce forgetting in continual LLM fine-tuning.

References

35 extracted · 35 resolved · 3 Pith anchors

[1] Superrag: Beyond rag with layout-aware graph modeling , author=. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Langu 2025

[2] Transactions on Machine Learning Research , year=

[3] Pacific-Asia Conference on Knowledge Discovery and Data Mining , pages= 2025

[4] Proceedings of the AAAI Conference on Artificial Intelligence , volume=

[5] The Thirteenth International Conference on Learning Representations , year=

Receipt and verification

First computed	2026-05-18T03:08:56.834900Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b2b51e3e1353ad8106e4fe6ff0adc079b849695cd66ae99f2e92d65d245fca78

Aliases

arxiv: 2605.13162 · arxiv_version: 2605.13162v1 · doi: 10.48550/arxiv.2605.13162 · pith_short_12: WK2R4PQTKOWY · pith_short_16: WK2R4PQTKOWYCBXE · pith_short_8: WK2R4PQT

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/WK2R4PQTKOWYCBXE7ZX7BLOAPG \
  | 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: b2b51e3e1353ad8106e4fe6ff0adc079b849695cd66ae99f2e92d65d245fca78

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4da11ee8ea1144d415a32efb840f40a16c2ba64462d3c68bef8cbd5c4b31b6ff",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T08:26:37Z",
    "title_canon_sha256": "e03bc4a3a5bb330f2af76e8f58554e665b0a5bd5ca227b50a1fe3ab801eca6b5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13162",
    "kind": "arxiv",
    "version": 1
  }
}