{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4OFVLZZLOVAQPHVNJWKHMIRTAT","short_pith_number":"pith:4OFVLZZL","schema_version":"1.0","canonical_sha256":"e38b55e72b7541079ead4d9476223304c9ee1416cd7911867544650c80d1d435","source":{"kind":"arxiv","id":"2605.12617","version":1},"attestation_state":"computed","paper":{"title":"MLPs are Efficient Distilled Generative Recommenders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Distilling generative recommenders into MLPs preserves accuracy while speeding up inference by 8.74x","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Clark Mingxuan Ju, Julian McAuley, Neil Shah, Yupeng Hou, Zitian Guo","submitted_at":"2026-05-12T18:05:55Z","abstract_excerpt":"Generative recommendation models employing Semantic IDs (SIDs) exhibit strong potential, yet their practical deployment is bottlenecked by the high inference latency of beam-expanded autoregressive decoding. In this work, we identify that standard attention-heavy Transformer decoders represent a structural overkill for this task: the hierarchical nature of SIDs makes prediction difficulty drops sharply after the first token, rendering repeated attention computations highly redundant. Driven by this insight, we propose SID-MLP, a lightweight MLP-centric distillation framework that fundamentally"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-12T18:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"805391eadae9bcf536e9256d7da1afd222e74a5616b7d54437935f8d2427f49c","abstract_canon_sha256":"90d565358fe1850a6c46e9f614103872ce80bb47f4c6d8f3850473d21558d259"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:00.496445Z","signature_b64":"DI8NoU1FwK/mHPBUYoYDiHtZpsQYHU8GB3JZ7nET2voOZjnnisrRW2pUPZe9HOVQt9RcRjxgWI5A2jUtovSgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e38b55e72b7541079ead4d9476223304c9ee1416cd7911867544650c80d1d435","last_reissued_at":"2026-05-18T03:10:00.495604Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:00.495604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLPs are Efficient Distilled Generative Recommenders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Distilling generative recommenders into MLPs preserves accuracy while speeding up inference by 8.74x","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Clark Mingxuan Ju, Julian McAuley, Neil Shah, Yupeng Hou, Zitian Guo","submitted_at":"2026-05-12T18:05:55Z","abstract_excerpt":"Generative recommendation models employing Semantic IDs (SIDs) exhibit strong potential, yet their practical deployment is bottlenecked by the high inference latency of beam-expanded autoregressive decoding. In this work, we identify that standard attention-heavy Transformer decoders represent a structural overkill for this task: the hierarchical nature of SIDs makes prediction difficulty drops sharply after the first token, rendering repeated attention computations highly redundant. Driven by this insight, we propose SID-MLP, a lightweight MLP-centric distillation framework that fundamentally"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments demonstrate that SID-MLP matches the accuracy of teacher models while accelerating inference by 8.74x. This distillation strategy can serve as a plug-and-play accelerator for different backbones and tokenizer settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The hierarchical nature of SIDs makes prediction difficulty drop sharply after the first token, rendering repeated attention computations highly redundant.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SID-MLP distills autoregressive generative recommenders into efficient position-specific MLP heads for Semantic ID tasks, achieving 8.74x faster inference with matching accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Distilling generative recommenders into MLPs preserves accuracy while speeding up inference by 8.74x","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"07bdc74cc6460efc6a67511efaa3b45150cdb3a996393ffa80da030f0551d571"},"source":{"id":"2605.12617","kind":"arxiv","version":1},"verdict":{"id":"c375d6d3-cc80-41db-bcf6-3aa50bdcf746","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:10:41.001869Z","strongest_claim":"Extensive experiments demonstrate that SID-MLP matches the accuracy of teacher models while accelerating inference by 8.74x. This distillation strategy can serve as a plug-and-play accelerator for different backbones and tokenizer settings.","one_line_summary":"SID-MLP distills autoregressive generative recommenders into efficient position-specific MLP heads for Semantic ID tasks, achieving 8.74x faster inference with matching accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The hierarchical nature of SIDs makes prediction difficulty drop sharply after the first token, rendering repeated attention computations highly redundant.","pith_extraction_headline":"Distilling generative recommenders into MLPs preserves accuracy while speeding up inference by 8.74x"},"references":{"count":77,"sample":[{"doi":"","year":2022,"title":"Transformer memory as a differentiable search index","work_id":"86233c16-b959-4114-9574-a43c62cdee35","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Tran, Jonah Samost, Maciej Kula, Ed H","work_id":"ba5c0f0c-d332-440a-93c5-8606c39de2fc","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Adapting large language models by integrating collaborative semantics for recommenda- tion","work_id":"f51fe37c-a7aa-419f-a196-bf60fb106255","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment","work_id":"d1a07d92-e045-4af2-a79f-c7b0112cf824","ref_index":4,"cited_arxiv_id":"2502.18965","is_internal_anchor":true},{"doi":"","year":2016,"title":"Session-based recommendations with recurrent neural networks","work_id":"52fdec4e-20e0-4895-a662-0d3deb4fbb2c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":77,"snapshot_sha256":"95ab4ab1a560bd6719e2e877be70c7bae451ba16f2f3c5a52fad1cff53927393","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"45ceee976e77c80dc467ccff50a920c0c08e893e6405a463602a79e5c62d41ea"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.12617","created_at":"2026-05-18T03:10:00.495736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12617v1","created_at":"2026-05-18T03:10:00.495736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12617","created_at":"2026-05-18T03:10:00.495736+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OFVLZZLOVAQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OFVLZZLOVAQPHVN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OFVLZZL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT","json":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT.json","graph_json":"https://pith.science/api/pith-number/4OFVLZZLOVAQPHVNJWKHMIRTAT/graph.json","events_json":"https://pith.science/api/pith-number/4OFVLZZLOVAQPHVNJWKHMIRTAT/events.json","paper":"https://pith.science/paper/4OFVLZZL"},"agent_actions":{"view_html":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT","download_json":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT.json","view_paper":"https://pith.science/paper/4OFVLZZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12617&json=true","fetch_graph":"https://pith.science/api/pith-number/4OFVLZZLOVAQPHVNJWKHMIRTAT/graph.json","fetch_events":"https://pith.science/api/pith-number/4OFVLZZLOVAQPHVNJWKHMIRTAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT/action/storage_attestation","attest_author":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT/action/author_attestation","sign_citation":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT/action/citation_signature","submit_replication":"https://pith.science/pith/4OFVLZZLOVAQPHVNJWKHMIRTAT/action/replication_record"}},"created_at":"2026-05-18T03:10:00.495736+00:00","updated_at":"2026-05-18T03:10:00.495736+00:00"}