{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RA2KBT2DDHYYFM3QQ5Y2BCXUUD","short_pith_number":"pith:RA2KBT2D","schema_version":"1.0","canonical_sha256":"8834a0cf4319f182b3708771a08af4a0da93441b0b07b0feb33c08fc76000862","source":{"kind":"arxiv","id":"2508.09664","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Fusion And Sparse Attention-based Alignment Model for Long Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hanmeng Liu, Jian Liu, Shouke Qin, Tao Li, Yongrui Fu, Zonggang Wu","submitted_at":"2025-08-13T09:50:44Z","abstract_excerpt":"Recent advances in multimodal recommendation enable richer item understanding, while modeling users' multi-scale interests across temporal horizons has attracted growing attention. However, effectively exploiting multimodal item sequences and mining multi-grained user interests to substantially bridge the gap between content comprehension and recommendation remain challenging. To address these issues, we propose MUFASA, a MUltimodal Fusion And Sparse Attention-based Alignment model for long sequential recommendation. Our model comprises two core components. First, the Multimodal Fusion Layer ("},"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":"2508.09664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-13T09:50:44Z","cross_cats_sorted":[],"title_canon_sha256":"072b2a40f1b4d62c07173c4c76ba696d56e6086962480254ef8a7bd5869ffae7","abstract_canon_sha256":"9969296d5b192c5fd1517398ff1dd08735862ff330819ec85e48e3cba4845cf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:19.481070Z","signature_b64":"IsDZulP7PL8zWpgcF+8RdWZoy3kC9hPmgkCHcMIO04S1d7O8uGtWgd8q9jcekqNZY3uSlPo32SJYwbF6R6g/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8834a0cf4319f182b3708771a08af4a0da93441b0b07b0feb33c08fc76000862","last_reissued_at":"2026-07-05T11:53:19.480339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:19.480339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Fusion And Sparse Attention-based Alignment Model for Long Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hanmeng Liu, Jian Liu, Shouke Qin, Tao Li, Yongrui Fu, Zonggang Wu","submitted_at":"2025-08-13T09:50:44Z","abstract_excerpt":"Recent advances in multimodal recommendation enable richer item understanding, while modeling users' multi-scale interests across temporal horizons has attracted growing attention. However, effectively exploiting multimodal item sequences and mining multi-grained user interests to substantially bridge the gap between content comprehension and recommendation remain challenging. To address these issues, we propose MUFASA, a MUltimodal Fusion And Sparse Attention-based Alignment model for long sequential recommendation. Our model comprises two core components. First, the Multimodal Fusion Layer ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09664","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/2508.09664/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":"2508.09664","created_at":"2026-07-05T11:53:19.480504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09664v1","created_at":"2026-07-05T11:53:19.480504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09664","created_at":"2026-07-05T11:53:19.480504+00:00"},{"alias_kind":"pith_short_12","alias_value":"RA2KBT2DDHYY","created_at":"2026-07-05T11:53:19.480504+00:00"},{"alias_kind":"pith_short_16","alias_value":"RA2KBT2DDHYYFM3Q","created_at":"2026-07-05T11:53:19.480504+00:00"},{"alias_kind":"pith_short_8","alias_value":"RA2KBT2D","created_at":"2026-07-05T11:53:19.480504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.13368","citing_title":"BlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD","json":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD.json","graph_json":"https://pith.science/api/pith-number/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/graph.json","events_json":"https://pith.science/api/pith-number/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/events.json","paper":"https://pith.science/paper/RA2KBT2D"},"agent_actions":{"view_html":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD","download_json":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD.json","view_paper":"https://pith.science/paper/RA2KBT2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09664&json=true","fetch_graph":"https://pith.science/api/pith-number/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/graph.json","fetch_events":"https://pith.science/api/pith-number/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/action/storage_attestation","attest_author":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/action/author_attestation","sign_citation":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/action/citation_signature","submit_replication":"https://pith.science/pith/RA2KBT2DDHYYFM3QQ5Y2BCXUUD/action/replication_record"}},"created_at":"2026-07-05T11:53:19.480504+00:00","updated_at":"2026-07-05T11:53:19.480504+00:00"}