{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RTBCYOUVX6E5NXD6CZ6ZVZQMUJ","short_pith_number":"pith:RTBCYOUV","schema_version":"1.0","canonical_sha256":"8cc22c3a95bf89d6dc7e167d9ae60ca26b18d3fae490014caa3f5dfbc595faa0","source":{"kind":"arxiv","id":"2509.25522","version":3},"attestation_state":"computed","paper":{"title":"Understanding Generative Recommendation with Semantic IDs from a Model-scaling View","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Clark Mingxuan Ju, Jiliang Tang, Jingzhe Liu, Liam Collins, Neil Shah, Tong Zhao","submitted_at":"2025-09-29T21:24:17Z","abstract_excerpt":"Recent advancements in generative models have allowed the emergence of a promising paradigm for recommender systems (RS), known as Generative Recommendation (GR), which tries to unify rich item semantics and collaborative filtering signals. One popular modern approach is to use semantic IDs (SIDs), which are discrete codes quantized from the embeddings of modality encoders (e.g., large language or vision models), to represent items in an autoregressive user interaction sequence modeling setup (henceforth, SID-based GR). While generative models in other domains exhibit well-established scaling "},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.25522","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-29T21:24:17Z","cross_cats_sorted":[],"title_canon_sha256":"fa00d0488377f8816a0765124cfb934bfb8bba9ee769c9a543cdfbad6dc7b6c5","abstract_canon_sha256":"4159240d7435d8fe181b94053ee8ec61180b7d4f5d773e9476755330e7737086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:48.920257Z","signature_b64":"UQOKF4y0LvyI9nmWqdEF27Ri8VE9YJxwRi6Zge7xgl5rLg4f9Zxut8iRU29Yd8PZ2h77ygADwocSQgKGHZE1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cc22c3a95bf89d6dc7e167d9ae60ca26b18d3fae490014caa3f5dfbc595faa0","last_reissued_at":"2026-06-08T01:03:48.919340Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:48.919340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Generative Recommendation with Semantic IDs from a Model-scaling View","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Clark Mingxuan Ju, Jiliang Tang, Jingzhe Liu, Liam Collins, Neil Shah, Tong Zhao","submitted_at":"2025-09-29T21:24:17Z","abstract_excerpt":"Recent advancements in generative models have allowed the emergence of a promising paradigm for recommender systems (RS), known as Generative Recommendation (GR), which tries to unify rich item semantics and collaborative filtering signals. One popular modern approach is to use semantic IDs (SIDs), which are discrete codes quantized from the embeddings of modality encoders (e.g., large language or vision models), to represent items in an autoregressive user interaction sequence modeling setup (henceforth, SID-based GR). While generative models in other domains exhibit well-established scaling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.25522","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.25522/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2509.25522","created_at":"2026-06-08T01:03:48.919463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.25522v3","created_at":"2026-06-08T01:03:48.919463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.25522","created_at":"2026-06-08T01:03:48.919463+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTBCYOUVX6E5","created_at":"2026-06-08T01:03:48.919463+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTBCYOUVX6E5NXD6","created_at":"2026-06-08T01:03:48.919463+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTBCYOUV","created_at":"2026-06-08T01:03:48.919463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.12617","citing_title":"MLPs are Efficient Distilled Generative Recommenders","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06331","citing_title":"Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05329","citing_title":"Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ","json":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ.json","graph_json":"https://pith.science/api/pith-number/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/graph.json","events_json":"https://pith.science/api/pith-number/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/events.json","paper":"https://pith.science/paper/RTBCYOUV"},"agent_actions":{"view_html":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ","download_json":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ.json","view_paper":"https://pith.science/paper/RTBCYOUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.25522&json=true","fetch_graph":"https://pith.science/api/pith-number/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/action/storage_attestation","attest_author":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/action/author_attestation","sign_citation":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/action/citation_signature","submit_replication":"https://pith.science/pith/RTBCYOUVX6E5NXD6CZ6ZVZQMUJ/action/replication_record"}},"created_at":"2026-06-08T01:03:48.919463+00:00","updated_at":"2026-06-08T01:03:48.919463+00:00"}