{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LYYZQCDKNTYQEM2NCCEQFJVD26","short_pith_number":"pith:LYYZQCDK","schema_version":"1.0","canonical_sha256":"5e3198086a6cf102334d108902a6a3d789798a0d2e23ccda38a7861601a8dfde","source":{"kind":"arxiv","id":"2505.09777","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Large Language Models in Multimodal Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Alejo Lopez-Avila, Jinhua Du","submitted_at":"2025-05-14T20:15:52Z","abstract_excerpt":"Multimodal recommender systems (MRS) integrate heterogeneous user and item data, such as text, images, and structured information, to enhance recommendation performance. The emergence of large language models (LLMs) introduces new opportunities for MRS by enabling semantic reasoning, in-context learning, and dynamic input handling. Compared to earlier pre-trained language models (PLMs), LLMs offer greater flexibility and generalisation capabilities but also introduce challenges related to scalability and model accessibility. This survey presents a comprehensive review of recent work at the int"},"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":"2505.09777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-14T20:15:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dee48099b376ce4ef8da8e58d597869e6df7417bf50b83454d693789e80a2302","abstract_canon_sha256":"d676f1e91cc35c97a8a33d63640e4f8971308fee2bad85c9beb0f96f1efa18f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:28.270933Z","signature_b64":"1V/C+NMweC185d0dWvigwqDOh0696V9lTordMw6SuEcZQUEL+X4NeOmgHFZgfOMei/nPK3OJvnySPo40aYOJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e3198086a6cf102334d108902a6a3d789798a0d2e23ccda38a7861601a8dfde","last_reissued_at":"2026-07-05T11:03:28.270497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:28.270497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Large Language Models in Multimodal Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Alejo Lopez-Avila, Jinhua Du","submitted_at":"2025-05-14T20:15:52Z","abstract_excerpt":"Multimodal recommender systems (MRS) integrate heterogeneous user and item data, such as text, images, and structured information, to enhance recommendation performance. The emergence of large language models (LLMs) introduces new opportunities for MRS by enabling semantic reasoning, in-context learning, and dynamic input handling. Compared to earlier pre-trained language models (PLMs), LLMs offer greater flexibility and generalisation capabilities but also introduce challenges related to scalability and model accessibility. This survey presents a comprehensive review of recent work at the int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09777","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/2505.09777/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":"2505.09777","created_at":"2026-07-05T11:03:28.270551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09777v1","created_at":"2026-07-05T11:03:28.270551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09777","created_at":"2026-07-05T11:03:28.270551+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYYZQCDKNTYQ","created_at":"2026-07-05T11:03:28.270551+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYYZQCDKNTYQEM2N","created_at":"2026-07-05T11:03:28.270551+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYYZQCDK","created_at":"2026-07-05T11:03:28.270551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25726","citing_title":"SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26","json":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26.json","graph_json":"https://pith.science/api/pith-number/LYYZQCDKNTYQEM2NCCEQFJVD26/graph.json","events_json":"https://pith.science/api/pith-number/LYYZQCDKNTYQEM2NCCEQFJVD26/events.json","paper":"https://pith.science/paper/LYYZQCDK"},"agent_actions":{"view_html":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26","download_json":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26.json","view_paper":"https://pith.science/paper/LYYZQCDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09777&json=true","fetch_graph":"https://pith.science/api/pith-number/LYYZQCDKNTYQEM2NCCEQFJVD26/graph.json","fetch_events":"https://pith.science/api/pith-number/LYYZQCDKNTYQEM2NCCEQFJVD26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26/action/storage_attestation","attest_author":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26/action/author_attestation","sign_citation":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26/action/citation_signature","submit_replication":"https://pith.science/pith/LYYZQCDKNTYQEM2NCCEQFJVD26/action/replication_record"}},"created_at":"2026-07-05T11:03:28.270551+00:00","updated_at":"2026-07-05T11:03:28.270551+00:00"}