{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P4MNXX6PGNOIRX4SAWEOP5HEJM","short_pith_number":"pith:P4MNXX6P","schema_version":"1.0","canonical_sha256":"7f18dbdfcf335c88df920588e7f4e44b3aca8d96e0a4bd0f876c8647eebea451","source":{"kind":"arxiv","id":"2504.10541","version":2},"attestation_state":"computed","paper":{"title":"Multi-Modal Hypergraph Enhanced LLM Learning for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chenxu Wang, Fuyun Wang, Tong Zhang, Xiaoya Zhang, Xin Liu, Xudong Wang, Xu Guo, Yuanzhi Wang, Zhen Cui","submitted_at":"2025-04-13T09:12:35Z","abstract_excerpt":"The burgeoning presence of Large Language Models (LLM) is propelling the development of personalized recommender systems. Most existing LLM-based methods fail to sufficiently explore the multi-view graph structure correlations inherent in recommendation scenarios. To this end, we propose a novel framework, Hypergraph Enhanced LLM Learning for multimodal Recommendation (HeLLM), designed to equip LLMs with the capability to capture intricate higher-order semantic correlations by fusing graph-level contextual signals with sequence-level behavioral patterns. In the recommender pre-training phase, "},"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":"2504.10541","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-13T09:12:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"353169958fdf70c1cd5ad67d1bb0844bd8cf7209f06ace04d5b3495a16c3588d","abstract_canon_sha256":"1700f2a50ceb165a0057c95485a6215dd5ac706ddbcc88358787f1f86b96bfd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:47.847586Z","signature_b64":"oVQkJrufSQEg09aDpgldmnPXAgfhrZdqp4M/BzFr4tYqNfB6whAMMpq1Hr5/VrM6KUa7Alzvo22cBBrKnRUDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f18dbdfcf335c88df920588e7f4e44b3aca8d96e0a4bd0f876c8647eebea451","last_reissued_at":"2026-07-05T11:44:47.847082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:47.847082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Hypergraph Enhanced LLM Learning for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chenxu Wang, Fuyun Wang, Tong Zhang, Xiaoya Zhang, Xin Liu, Xudong Wang, Xu Guo, Yuanzhi Wang, Zhen Cui","submitted_at":"2025-04-13T09:12:35Z","abstract_excerpt":"The burgeoning presence of Large Language Models (LLM) is propelling the development of personalized recommender systems. Most existing LLM-based methods fail to sufficiently explore the multi-view graph structure correlations inherent in recommendation scenarios. To this end, we propose a novel framework, Hypergraph Enhanced LLM Learning for multimodal Recommendation (HeLLM), designed to equip LLMs with the capability to capture intricate higher-order semantic correlations by fusing graph-level contextual signals with sequence-level behavioral patterns. In the recommender pre-training phase, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10541","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/2504.10541/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":"2504.10541","created_at":"2026-07-05T11:44:47.847140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10541v2","created_at":"2026-07-05T11:44:47.847140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10541","created_at":"2026-07-05T11:44:47.847140+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4MNXX6PGNOI","created_at":"2026-07-05T11:44:47.847140+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4MNXX6PGNOIRX4S","created_at":"2026-07-05T11:44:47.847140+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4MNXX6P","created_at":"2026-07-05T11:44:47.847140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20554","citing_title":"Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21858","citing_title":"Hypergraph as Language","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM","json":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM.json","graph_json":"https://pith.science/api/pith-number/P4MNXX6PGNOIRX4SAWEOP5HEJM/graph.json","events_json":"https://pith.science/api/pith-number/P4MNXX6PGNOIRX4SAWEOP5HEJM/events.json","paper":"https://pith.science/paper/P4MNXX6P"},"agent_actions":{"view_html":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM","download_json":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM.json","view_paper":"https://pith.science/paper/P4MNXX6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10541&json=true","fetch_graph":"https://pith.science/api/pith-number/P4MNXX6PGNOIRX4SAWEOP5HEJM/graph.json","fetch_events":"https://pith.science/api/pith-number/P4MNXX6PGNOIRX4SAWEOP5HEJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM/action/storage_attestation","attest_author":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM/action/author_attestation","sign_citation":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM/action/citation_signature","submit_replication":"https://pith.science/pith/P4MNXX6PGNOIRX4SAWEOP5HEJM/action/replication_record"}},"created_at":"2026-07-05T11:44:47.847140+00:00","updated_at":"2026-07-05T11:44:47.847140+00:00"}