{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7UGKF73CJBSGFYZUXK4GQVNW47","short_pith_number":"pith:7UGKF73C","schema_version":"1.0","canonical_sha256":"fd0ca2ff62486462e334bab86855b6e7c431a510609d4aa9efb37f9a0a033ac6","source":{"kind":"arxiv","id":"2508.05377","version":1},"attestation_state":"computed","paper":{"title":"Does Multimodality Improve Recommender Systems as Expected? A Critical Analysis and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Hongyu Zhou, Yinan Zhang, Zhiqi Shen","submitted_at":"2025-08-07T13:21:00Z","abstract_excerpt":"Multimodal recommendation systems are increasingly popular for their potential to improve performance by integrating diverse data types. However, the actual benefits of this integration remain unclear, raising questions about when and how it truly enhances recommendations. In this paper, we propose a structured evaluation framework to systematically assess multimodal recommendations across four dimensions: Comparative Efficiency, Recommendation Tasks, Recommendation Stages, and Multimodal Data Integration. We benchmark a set of reproducible multimodal models against strong traditional baseline"},"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":"2508.05377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-07T13:21:00Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"0cd995d7eb691a70dc572fb5e1f8f595d2f67ef97894ee9d683e4d3b542e7b7f","abstract_canon_sha256":"eee793593fd2abb4226070ac7f561a16fb1da0434605b48a012b3e4641984a4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:11.747371Z","signature_b64":"mL2xK7RxXrs11dL6Z8THgogb1sL51knL2PfOF1f2Cv7Qk3qh0nNDuAkSli4c5cAbxpbqfQrApVcsuRTtAHpHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd0ca2ff62486462e334bab86855b6e7c431a510609d4aa9efb37f9a0a033ac6","last_reissued_at":"2026-07-05T11:50:11.746747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:11.746747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Multimodality Improve Recommender Systems as Expected? A Critical Analysis and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Hongyu Zhou, Yinan Zhang, Zhiqi Shen","submitted_at":"2025-08-07T13:21:00Z","abstract_excerpt":"Multimodal recommendation systems are increasingly popular for their potential to improve performance by integrating diverse data types. However, the actual benefits of this integration remain unclear, raising questions about when and how it truly enhances recommendations. In this paper, we propose a structured evaluation framework to systematically assess multimodal recommendations across four dimensions: Comparative Efficiency, Recommendation Tasks, Recommendation Stages, and Multimodal Data Integration. We benchmark a set of reproducible multimodal models against strong traditional baseline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05377","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/2508.05377/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":"2508.05377","created_at":"2026-07-05T11:50:11.746820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05377v1","created_at":"2026-07-05T11:50:11.746820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05377","created_at":"2026-07-05T11:50:11.746820+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UGKF73CJBSG","created_at":"2026-07-05T11:50:11.746820+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UGKF73CJBSGFYZU","created_at":"2026-07-05T11:50:11.746820+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UGKF73C","created_at":"2026-07-05T11:50:11.746820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09082","citing_title":"Teach Multimodal Recommendation Model to See via Personalized Visual Extraction and Adaptive Learning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23077","citing_title":"Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47","json":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47.json","graph_json":"https://pith.science/api/pith-number/7UGKF73CJBSGFYZUXK4GQVNW47/graph.json","events_json":"https://pith.science/api/pith-number/7UGKF73CJBSGFYZUXK4GQVNW47/events.json","paper":"https://pith.science/paper/7UGKF73C"},"agent_actions":{"view_html":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47","download_json":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47.json","view_paper":"https://pith.science/paper/7UGKF73C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05377&json=true","fetch_graph":"https://pith.science/api/pith-number/7UGKF73CJBSGFYZUXK4GQVNW47/graph.json","fetch_events":"https://pith.science/api/pith-number/7UGKF73CJBSGFYZUXK4GQVNW47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47/action/storage_attestation","attest_author":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47/action/author_attestation","sign_citation":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47/action/citation_signature","submit_replication":"https://pith.science/pith/7UGKF73CJBSGFYZUXK4GQVNW47/action/replication_record"}},"created_at":"2026-07-05T11:50:11.746820+00:00","updated_at":"2026-07-05T11:50:11.746820+00:00"}