mlsanityData to 14 Oct 2026

SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation

arXiv 2608.18779 ↗First posted 19 Aug 2026cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Semantic ID tokenizers assign code sequences to catalog items, which generative recommenders predict and resolve back to items. Reusing a released mapping requires checking its code organization, item resolution, and compatibility with an existing model after a refresh. SIDScope provides these checks through source traced adapters, mapping diagnostics, candidate retrieval tests, and generated trace analysis. Its inventory contains nine exports from seven tokenizer families across Amazon and Yelp, including eight executable routes and one auditable snapshot. The analyses establish three distinctions. First, code allocation and item addressability differ: in GRID, tail items occupy 95.7 distinct codes per 100 items, yet only 82.2 percent have globally unique codes. Second, prefix alignment calibrates retrieval operations that use prefixes. With fixed candidate budgets and ranking, original assignments on Beauty and Instruments expose more targets than controls preserving code capacity and coarse popularity. Resolving identical generated paths also shows that an explicit item selection rule recovers part of the gap between target path survival and singleton credit. Third, a released refresh repairs missing codes, while model adaptation separately restores new item recall. SIDScope supplies code, diagnostic summaries, and verification tools to compare mappings, evaluate their use in retrieval and generation, and test model reuse after changes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 61 of its 72 references that are in the map. First posted on arXiv 19 Aug 2026.

Builds on

61 of 72 references.

References · 61

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  3. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
  4. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  5. 2023Recommender Systems with Generative Retrievalcited by 198
  6. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  7. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
  8. 2020RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithmscited by 138
  9. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 113
  10. 2022A Neural Corpus Indexer for Document Retrievalcited by 111
  11. 2024Learnable Item Tokenization for Generative Recommendationcited by 110
  12. 2023How to Index Item IDs for Recommendation Foundation Modelscited by 102
38 more
  1. 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 73
  2. 2019A Troubling Analysis of Reproducibility and Progress in Recommender Systems Researchcited by 65
  3. 2024EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaborationcited by 58
  4. 2023Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendationscited by 52
  5. 2024TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendationcited by 35
  6. 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representationscited by 35
  7. 2024Generative Recommender with End-to-End Learnable Item Tokenizationcited by 34
  8. 2021Elliot: a Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluationcited by 28
  9. 2024QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishoucited by 28
  10. 2024CoST: Contrastive Quantization based Semantic Tokenization for Generative Recommendationcited by 26
  11. 2026Differentiable Semantic ID for Generative Recommendationcited by 19
  12. 2025Generative Recommendation with Semantic IDs: A Practitioner's Handbookcited by 18
  13. 2025Semantic IDs for Joint Generative Search and Recommendationcited by 14
  14. 2018LensKit for Python: Next-Generation Software for Recommender System Experimentscited by 13
  15. 2025Multimodal Quantitative Language for Generative Recommendationcited by 12
  16. 2025From IDs to Semantics: A Generative Framework for Cross-Domain Recommendation with Adaptive Semantic Tokenizationcited by 9
  17. 2021Beyond NDCG: behavioral testing of recommender systems with RecListcited by 8
  18. 2025DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendationcited by 8
  19. 2025Universal Item Tokenization for Transferable Generative Recommendationcited by 7
  20. 2026Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Acceleratorscited by 6
  21. 2026Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scalecited by 6
  22. 2026Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfercited by 5
  23. 2026Unleash the Potential of Long Semantic IDs for Generative Recommendationcited by 4
  24. 2026Variable-Length Semantic IDs for Recommender Systemscited by 4
  25. 2026Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendationcited by 4
  26. 2026When Text-as-Vision Meets Semantic IDs in Generative Recommendation: An Empirical Studycited by 3
  27. 2026PIT: A Dynamic Personalized Item Tokenizer for End-to-End Generative Recommendationcited by 3
  28. 2026End-to-End Semantic ID Generation for Generative Advertisement Recommendationcited by 3
  29. 2026CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendationcited by 3
  30. 2026Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMscited by 2
  31. 2026Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choicescited by 2
  32. 2026Mitigating Collaborative Semantic ID Staleness in Generative Retrievalcited by 2
  33. 2026Beyond Static Collision Handling: Adaptive Semantic ID Learning for Multimodal Recommendation at Industrial Scalecited by 2
  34. 2026CARD: Non-Uniform Quantization of Visual Semantic Unit for Generative Recommendationcited by 2
  35. 2026Faithful Evaluation of Semantic-ID Tokenizers for Generative Recommendationcited by 2
  36. 2026Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendationcited by 2
  37. 2026Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commercecited by 2
  38. 2026Can Generative Recommendation Reach Cold Items? A Temporal Perspective on Semantic-ID Generationcited by 2

50 most cited of 61 All 61 (JSON)

Built on by

Not cited yet.