Pith Number

pith:UWVEVCHM

pith:2026:UWVEVCHMVIVXQJDTWRAR5HAMGB

not attested not anchored not stored refs resolved

Asymmetric Generative Recommendation via Multi-Expert Projection and Multi-Faceted Hierarchical Quantization

Bin Huang, Haijie Gu, Junwei Pan, Shudong Huang, Wenwu Zhu, Xin Wang, Yifeng Zhou, Yongqi Zhou, Zhixiang Feng

An asymmetric continuous-discrete framework removes dual information bottlenecks in generative recommendation and improves accuracy by 15.8 percent on average.

arxiv:2605.14512 v1 · 2026-05-14 · cs.IR · 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{UWVEVCHMVIVXQJDTWRAR5HAMGB}

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

AsymRec consistently outperforms state-of-the-art generative recommenders by an average of 15.8 %.

C2weakest assumption

That the identified input and output bottlenecks are the dominant limitations of prior symmetric GenRec models and that MSP plus MHQ mitigate them without new trade-offs, as supported only by the reported aggregate improvement.

C3one line summary

AsymRec decouples input and output representations in generative recommendation via multi-expert semantic projection and multi-faceted hierarchical quantization, outperforming prior models by 15.8% on average.

References

37 extracted · 37 resolved · 7 Pith anchors

[1] Pinrec: Outcome-conditioned, multi-token generative retrieval for industry-scale recommendation systems 2025 · doi:10.48550/arxiv.2504.10507

[2] Gordon V Cormack, Charles LA Clarke, and Stefan Buettcher. 2009. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32nd international ACM SIGIR c 2009

[3] OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment 2025 · doi:10.48550/arxiv.2502.18965

[4] Robert Gray. 1984. Vector quantization.IEEE Assp Magazine1, 2 (1984), 4–29 1984

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

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-17T23:39:06.180700Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a5aa4a88ecaa2b782473b4411e9c0c30692ec85a898c86c04b4475ff9d02850e

Aliases

arxiv: 2605.14512 · arxiv_version: 2605.14512v1 · doi: 10.48550/arxiv.2605.14512 · pith_short_12: UWVEVCHMVIVX · pith_short_16: UWVEVCHMVIVXQJDT · pith_short_8: UWVEVCHM

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/UWVEVCHMVIVXQJDTWRAR5HAMGB \
  | 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: a5aa4a88ecaa2b782473b4411e9c0c30692ec85a898c86c04b4475ff9d02850e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2655837b3dcc9048eb4416b456e7652112e3623b77357dd1147b39cd3dbe70d1",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-14T07:55:43Z",
    "title_canon_sha256": "c88571897c4b76698fceda4899d4d84b8146f2107e57b86f91fc1cb57359c549"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14512",
    "kind": "arxiv",
    "version": 1
  }
}