Pith Number

pith:U5ZII53P

pith:2026:U5ZII53PUDBI3ZPHQWNR4376YF

not attested not anchored not stored refs pending

C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs

Morteza Ziyadi, Rui Gao, Swastik Roy, Xiang 'Anthony' Chen, Youngseung Jeon

Reinforcement learning post-training with group-based optimization and non-linear rewards aligns LLMs to optimize molecules across multiple competing properties.

arxiv:2604.23061 v2 · 2026-04-24 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{U5ZII53PUDBI3ZPHQWNR4376YF}

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

Experiments on the C-MuMOInstruct benchmark show that C-Moral consistently outperforms state-of-the-art models across both in-domain and out-of-domain settings, achieving the best Success Optimized Rate (SOR) of 48.9% on IND tasks and 39.5% on OOD tasks, while largely preserving scaffold similarity.

C2weakest assumption

That the reported performance gains on the C-MuMOInstruct benchmark are attributable to the proposed components (group-based relative optimization, property score alignment, and continuous non-linear reward aggregation) rather than implementation details or benchmark-specific artifacts, and that these gains generalize to practical drug design.

C3one line summary

C-MORAL applies reinforcement learning post-training with group-based optimization and non-linear reward aggregation to align LLMs for controllable multi-objective molecular optimization, achieving 48.9% SOR on in-domain and 39.5% on out-of-domain benchmark tasks.

Receipt and verification

First computed	2026-05-28T01:04:08.586605Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a77284776fa0c28de5e7859b1e6ffec142b4c702f1634c29a92b4b09d8da9e09

Aliases

arxiv: 2604.23061 · arxiv_version: 2604.23061v2 · doi: 10.48550/arxiv.2604.23061 · pith_short_12: U5ZII53PUDBI · pith_short_16: U5ZII53PUDBI3ZPH · pith_short_8: U5ZII53P

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/U5ZII53PUDBI3ZPHQWNR4376YF \
  | 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: a77284776fa0c28de5e7859b1e6ffec142b4c702f1634c29a92b4b09d8da9e09

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f672d682a77307538cd790975e1ceeb9b292fdfdf0b6e93ac9090019acd7d1a0",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-24T23:11:44Z",
    "title_canon_sha256": "26fe96969ff62fbc8062cc7d547f2bc67ec548d8cb116d88c4db89722698a604"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.23061",
    "kind": "arxiv",
    "version": 2
  }
}