{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RH2CCTWLJ7TGUQBJ6VFHFHZVSW","short_pith_number":"pith:RH2CCTWL","schema_version":"1.0","canonical_sha256":"89f4214ecb4fe66a4029f54a729f359591bde0069875f8a2f08a128cad865408","source":{"kind":"arxiv","id":"2608.10700","version":1},"attestation_state":"computed","paper":{"title":"Deciding When to Rely on Visual Information: Gated Multimodal Fusion in Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Danica Kragic, Martin Tegner, Natalija Glisovic","submitted_at":"2026-08-11T09:21:20Z","abstract_excerpt":"Multimodal sequential recommender systems commonly fuse visual and collaborative signals uniformly, treating visual features as generically informative regardless of item or user context. We argue that visual utility, defined as the contribution of visual signals to recommendation quality, is a latent contextual variable that depends on both the item and the user's interaction history rather than a fixed item property. To model this variability, we introduce VisGate, a framework that makes adaptive item-level fusion decisions conditioned on item embeddings and the user's current sequence conte"},"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":"2608.10700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-11T09:21:20Z","cross_cats_sorted":[],"title_canon_sha256":"38f91d1823bb70de1b42acec348ab2fc6c2c9a02fb387f1006eb19c3b435ca46","abstract_canon_sha256":"183419b068d1bf963f7b4ff48997d5b41f68ea15d26a5801bd1b6a8f9f18c481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:23:05.193477Z","signature_b64":"zDfIvql5+EOexQwyQ8Pe1EVatTddujno81gohhJkkdtZn+hd9DOw5b0lyVMglUZ6vvCRmww/Cphz3jhq3sk6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89f4214ecb4fe66a4029f54a729f359591bde0069875f8a2f08a128cad865408","last_reissued_at":"2026-08-12T01:23:05.191799Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:23:05.191799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deciding When to Rely on Visual Information: Gated Multimodal Fusion in Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Danica Kragic, Martin Tegner, Natalija Glisovic","submitted_at":"2026-08-11T09:21:20Z","abstract_excerpt":"Multimodal sequential recommender systems commonly fuse visual and collaborative signals uniformly, treating visual features as generically informative regardless of item or user context. We argue that visual utility, defined as the contribution of visual signals to recommendation quality, is a latent contextual variable that depends on both the item and the user's interaction history rather than a fixed item property. To model this variability, we introduce VisGate, a framework that makes adaptive item-level fusion decisions conditioned on item embeddings and the user's current sequence conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10700","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/2608.10700/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":"2608.10700","created_at":"2026-08-12T01:23:05.195636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10700v1","created_at":"2026-08-12T01:23:05.195636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10700","created_at":"2026-08-12T01:23:05.195636+00:00"},{"alias_kind":"pith_short_12","alias_value":"RH2CCTWLJ7TG","created_at":"2026-08-12T01:23:05.195636+00:00"},{"alias_kind":"pith_short_16","alias_value":"RH2CCTWLJ7TGUQBJ","created_at":"2026-08-12T01:23:05.195636+00:00"},{"alias_kind":"pith_short_8","alias_value":"RH2CCTWL","created_at":"2026-08-12T01:23:05.195636+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/RH2CCTWLJ7TGUQBJ6VFHFHZVSW","json":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW.json","graph_json":"https://pith.science/api/pith-number/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/graph.json","events_json":"https://pith.science/api/pith-number/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/events.json","paper":"https://pith.science/paper/RH2CCTWL"},"agent_actions":{"view_html":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW","download_json":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW.json","view_paper":"https://pith.science/paper/RH2CCTWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10700&json=true","fetch_graph":"https://pith.science/api/pith-number/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/graph.json","fetch_events":"https://pith.science/api/pith-number/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/action/storage_attestation","attest_author":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/action/author_attestation","sign_citation":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/action/citation_signature","submit_replication":"https://pith.science/pith/RH2CCTWLJ7TGUQBJ6VFHFHZVSW/action/replication_record"}},"created_at":"2026-08-12T01:23:05.195636+00:00","updated_at":"2026-08-12T01:23:05.195636+00:00"}