Pith Number

pith:SWUJDETK

pith:2025:SWUJDETKRTVIUSPEBLADWKT3SZ

not attested not anchored not stored refs resolved

Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization

Jianxun Lian, Laks V. S. Lakshmanan, Shanlin Zhou, Xiaoyuan Yi, Xinpeng Wang, Yongtao Hao, Zhenghao Liu

Formalizing Chinese short-form creative tasks as joint optimization of constraints and explanation reliability produces more trustworthy personalized outputs.

arxiv:2511.15408 v2 · 2025-11-19 · cs.CL · cs.AI · cs.IR · cs.MA · cs.NE

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

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 Chinese Baby Naming, a challenging benchmark, demonstrate that MAGIC-HMO significantly outperforms six strong baselines across various LLM backbones.

C2weakest assumption

That iterative multi-agent generation and verification can reliably reduce hallucination, incompleteness, and ambiguity in explanations under complex personalized constraints without introducing new failure modes.

C3one line summary

MAGIC-HMO is a multi-agent framework that treats Chinese short-form creative NLG as heterogeneous multi-objective optimization over personalized constraints plus explanation reliability and outperforms baselines on a baby-naming benchmark.

References

88 extracted · 88 resolved · 13 Pith anchors

[1] OpenAI, “Hello gpt-4o,” https://openai.com/index/hello-gpt-4o/, 2024, accessed: 2025-01-29 2024

[2] ——, “Introducing openai o1,” https://openai.com/o1/, 2024, accessed: 2024-10-28 2024

[3] Gemini: A Family of Highly Capable Multimodal Models 2024 · arXiv:2312.11805

[4] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 2025 · arXiv:2501.12948

[5] MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark 2024 · arXiv:2406.01574

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:17.106096Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

95a891926a8cea8a49e40ac03b2a7b96553049d6750f1bdee797d05d0e54b9a5

Aliases

arxiv: 2511.15408 · arxiv_version: 2511.15408v2 · doi: 10.48550/arxiv.2511.15408 · pith_short_12: SWUJDETKRTVI · pith_short_16: SWUJDETKRTVIUSPE · pith_short_8: SWUJDETK

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/SWUJDETKRTVIUSPEBLADWKT3SZ \
  | 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: 95a891926a8cea8a49e40ac03b2a7b96553049d6750f1bdee797d05d0e54b9a5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f56c0bf41ff7240ea2cc7c2c41067fc0c00b3689a95f755a6fdc67af9bac7ad3",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.IR",
      "cs.MA",
      "cs.NE"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-11-19T13:05:25Z",
    "title_canon_sha256": "2471b8a72b7a915b4e6cb11f695d72dd66c61e78fafe5af31df46d558b845f7a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.15408",
    "kind": "arxiv",
    "version": 2
  }
}