Pith Number

pith:WKCT3GBS

pith:2026:WKCT3GBS3JAHZSL2DVVIBP6QLS

not attested not anchored not stored refs resolved

A Cascaded Generative Approach for e-Commerce Recommendations

Guanghua Shu, Hamidreza Shahidi, Moein Hasani, Tejaswi Tenneti, Trace Levinson, Vinesh Gudla, Yuan Zhong

Cascaded generative models for themes and keywords deliver 2.7% higher cart adds in e-commerce storefronts.

arxiv:2605.11118 v2 · 2026-05-11 · cs.AI · cs.IR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WKCT3GBS3JAHZSL2DVVIBP6QLS}

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

In online experiments, this framework yields an estimated +2.7% lift in cart adds per page view over a strong baseline.

C2weakest assumption

The teacher-student fine-tuned generative models can reliably produce high-quality, safe, and semantically cohesive themes and keywords that integrate effectively with traditional ranking models under production latency and cost limits.

C3one line summary

A cascaded generative merchandising framework with placement theme generation, constrained keyword generation, and teacher-student fine-tuning achieves a 2.7% lift in cart adds per page view over a strong baseline in online e-commerce experiments.

References

19 extracted · 19 resolved · 10 Pith anchors

[1] Francesco Fabbri, Gustavo Penha, Edoardo D’Amico, Alice Wang, Marco De Nadai, Jackie Doremus, Paul Gigioli, Andreas Damianou, Oskar Stål, and Mounia Lalmas. 2025. Evaluating Podcast Recommendations wi 2025

[2] Retrieval-Augmented Generation for Large Language Models: A Survey 2024 · arXiv:2312.10997

[3] The Llama 3 Herd of Models 2024 · arXiv:2407.21783

[4] DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing 2021 · arXiv:2111.09543

[5] Distilling the Knowledge in a Neural Network 2015 · arXiv:1503.02531

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:42.714029Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b2853d9832da407cc97a1d6a80bfd05ca382a98cc9e340e670c5465dad4454bf

Aliases

arxiv: 2605.11118 · arxiv_version: 2605.11118v2 · doi: 10.48550/arxiv.2605.11118 · pith_short_12: WKCT3GBS3JAH · pith_short_16: WKCT3GBS3JAHZSL2 · pith_short_8: WKCT3GBS

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/WKCT3GBS3JAHZSL2DVVIBP6QLS \
  | 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: b2853d9832da407cc97a1d6a80bfd05ca382a98cc9e340e670c5465dad4454bf

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "363756637a276fe9fee8a5e0db69b2c61a5a6928d063f2d18d0b54797983ce46",
    "cross_cats_sorted": [
      "cs.IR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-11T18:27:08Z",
    "title_canon_sha256": "903e6aa7d1c7938c6eabff486b75a022336673c2726f20d4de0e8df31ae1b4b2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11118",
    "kind": "arxiv",
    "version": 2
  }
}