{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IKWTGGIDCQ5L2IPDIZ57VPH6YU","short_pith_number":"pith:IKWTGGID","schema_version":"1.0","canonical_sha256":"42ad331903143abd21e3467bfabcfec53f4b088e9cd2dba9ba3cb5f7d5204b5d","source":{"kind":"arxiv","id":"2503.23333","version":1},"attestation_state":"computed","paper":{"title":"Beyond Unimodal Boundaries: Generative Recommendation with Multimodal Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Danai Koutra, Jing Zhu, Mingxuan Ju, Neil Shah, Tong Zhao, Yozen Liu","submitted_at":"2025-03-30T06:24:43Z","abstract_excerpt":"Generative recommendation (GR) has become a powerful paradigm in recommendation systems that implicitly links modality and semantics to item representation, in contrast to previous methods that relied on non-semantic item identifiers in autoregressive models. However, previous research has predominantly treated modalities in isolation, typically assuming item content is unimodal (usually text). We argue that this is a significant limitation given the rich, multimodal nature of real-world data and the potential sensitivity of GR models to modality choices and usage. Our work aims to explore the"},"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":"2503.23333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-03-30T06:24:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"3eca10819e3089bcc7ffbccae3f09c1f457e28ab271cc62275250e222d225bb3","abstract_canon_sha256":"6da7734a134da255fc27da894cbe4133bb328abc0daf69f90ab5650ec42f735f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:34.666796Z","signature_b64":"cvSkQhu2JQSwu1kUfBvbH5Tg1d6EvQCz5kM01cnxznr+iquxnwUf4GDB0+4jNwFCr6axAB++X5ZLJYkeYrp6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ad331903143abd21e3467bfabcfec53f4b088e9cd2dba9ba3cb5f7d5204b5d","last_reissued_at":"2026-07-05T10:41:34.666330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:34.666330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Unimodal Boundaries: Generative Recommendation with Multimodal Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Danai Koutra, Jing Zhu, Mingxuan Ju, Neil Shah, Tong Zhao, Yozen Liu","submitted_at":"2025-03-30T06:24:43Z","abstract_excerpt":"Generative recommendation (GR) has become a powerful paradigm in recommendation systems that implicitly links modality and semantics to item representation, in contrast to previous methods that relied on non-semantic item identifiers in autoregressive models. However, previous research has predominantly treated modalities in isolation, typically assuming item content is unimodal (usually text). We argue that this is a significant limitation given the rich, multimodal nature of real-world data and the potential sensitivity of GR models to modality choices and usage. Our work aims to explore the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23333","kind":"arxiv","version":1},"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/2503.23333/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":"2503.23333","created_at":"2026-07-05T10:41:34.666386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23333v1","created_at":"2026-07-05T10:41:34.666386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23333","created_at":"2026-07-05T10:41:34.666386+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKWTGGIDCQ5L","created_at":"2026-07-05T10:41:34.666386+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKWTGGIDCQ5L2IPD","created_at":"2026-07-05T10:41:34.666386+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKWTGGID","created_at":"2026-07-05T10:41:34.666386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18920","citing_title":"SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12617","citing_title":"MLPs are Efficient Distilled Generative Recommenders","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06331","citing_title":"Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU","json":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU.json","graph_json":"https://pith.science/api/pith-number/IKWTGGIDCQ5L2IPDIZ57VPH6YU/graph.json","events_json":"https://pith.science/api/pith-number/IKWTGGIDCQ5L2IPDIZ57VPH6YU/events.json","paper":"https://pith.science/paper/IKWTGGID"},"agent_actions":{"view_html":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU","download_json":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU.json","view_paper":"https://pith.science/paper/IKWTGGID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23333&json=true","fetch_graph":"https://pith.science/api/pith-number/IKWTGGIDCQ5L2IPDIZ57VPH6YU/graph.json","fetch_events":"https://pith.science/api/pith-number/IKWTGGIDCQ5L2IPDIZ57VPH6YU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU/action/storage_attestation","attest_author":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU/action/author_attestation","sign_citation":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU/action/citation_signature","submit_replication":"https://pith.science/pith/IKWTGGIDCQ5L2IPDIZ57VPH6YU/action/replication_record"}},"created_at":"2026-07-05T10:41:34.666386+00:00","updated_at":"2026-07-05T10:41:34.666386+00:00"}