{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UR6WF6GMPHCOADR7CRB3GKKURH","short_pith_number":"pith:UR6WF6GM","schema_version":"1.0","canonical_sha256":"a47d62f8cc79c4e00e3f1443b3295489fe699168958e21809ede2f953b0d59db","source":{"kind":"arxiv","id":"2606.17276","version":2},"attestation_state":"computed","paper":{"title":"On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bhuvesh Kumar, Clark Mingxuan Ju, Donald Loveland, Kijung Shin, Liam Collins, Neil Shah, Sunkyung Lee, Sunwoo Kim","submitted_at":"2026-06-15T20:34:49Z","abstract_excerpt":"Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recently, large language models (LLMs) have been increasingly adopted for GR, as their rich pretrained knowledge is expected to help them generalize beyond common user behavior patterns that traditional memorization-oriented baselines can capture. However, existing LLM-based GR works largely ignore LLMs' well-known tendency to memorize, which, if present in LLMs fine-tuned for GR, would restrict their utilization of pretrained knowledge. In this work, we investigate this concern by examining one-hop me"},"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":"2606.17276","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-15T20:34:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec987ada56a04b9fe94654c18522eae04455301efcbddad79bf653826b3d07b3","abstract_canon_sha256":"75fbd4f362c59d605049b16172eca5e1bbc59fa959aa4045b70c3fcbfae4ecff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:06.599601Z","signature_b64":"Lua+rS25j/d1BJ3QQRQXYchvBYtmPWYZrfyWyWvCyo3baAKrcymDi6CXqTld4Wicb6+QwiHAcr6vizE15UMFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47d62f8cc79c4e00e3f1443b3295489fe699168958e21809ede2f953b0d59db","last_reissued_at":"2026-06-19T16:12:06.599247Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:06.599247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bhuvesh Kumar, Clark Mingxuan Ju, Donald Loveland, Kijung Shin, Liam Collins, Neil Shah, Sunkyung Lee, Sunwoo Kim","submitted_at":"2026-06-15T20:34:49Z","abstract_excerpt":"Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recently, large language models (LLMs) have been increasingly adopted for GR, as their rich pretrained knowledge is expected to help them generalize beyond common user behavior patterns that traditional memorization-oriented baselines can capture. However, existing LLM-based GR works largely ignore LLMs' well-known tendency to memorize, which, if present in LLMs fine-tuned for GR, would restrict their utilization of pretrained knowledge. In this work, we investigate this concern by examining one-hop me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17276","kind":"arxiv","version":2},"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/2606.17276/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":"2606.17276","created_at":"2026-06-19T16:12:06.599303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17276v2","created_at":"2026-06-19T16:12:06.599303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17276","created_at":"2026-06-19T16:12:06.599303+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR6WF6GMPHCO","created_at":"2026-06-19T16:12:06.599303+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR6WF6GMPHCOADR7","created_at":"2026-06-19T16:12:06.599303+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR6WF6GM","created_at":"2026-06-19T16:12:06.599303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH","json":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH.json","graph_json":"https://pith.science/api/pith-number/UR6WF6GMPHCOADR7CRB3GKKURH/graph.json","events_json":"https://pith.science/api/pith-number/UR6WF6GMPHCOADR7CRB3GKKURH/events.json","paper":"https://pith.science/paper/UR6WF6GM"},"agent_actions":{"view_html":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH","download_json":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH.json","view_paper":"https://pith.science/paper/UR6WF6GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17276&json=true","fetch_graph":"https://pith.science/api/pith-number/UR6WF6GMPHCOADR7CRB3GKKURH/graph.json","fetch_events":"https://pith.science/api/pith-number/UR6WF6GMPHCOADR7CRB3GKKURH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH/action/storage_attestation","attest_author":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH/action/author_attestation","sign_citation":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH/action/citation_signature","submit_replication":"https://pith.science/pith/UR6WF6GMPHCOADR7CRB3GKKURH/action/replication_record"}},"created_at":"2026-06-19T16:12:06.599303+00:00","updated_at":"2026-06-19T16:12:06.599303+00:00"}