{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A2ELE2N54S7GBXNJ7H5CJHYS2O","short_pith_number":"pith:A2ELE2N5","schema_version":"1.0","canonical_sha256":"0688b269bde4be60dda9f9fa249f12d3906ffb7ed97083546b43eb5d58704d31","source":{"kind":"arxiv","id":"2104.07407","version":2},"attestation_state":"computed","paper":{"title":"MM-Rec: Multimodal News Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang","submitted_at":"2021-04-15T12:11:50Z","abstract_excerpt":"Accurate news representation is critical for news recommendation. Most of existing news representation methods learn news representations only from news texts while ignore the visual information in news like images. In fact, users may click news not only because of the interest in news titles but also due to the attraction of news images. Thus, images are useful for representing news and predicting user behaviors. In this paper, we propose a multimodal news recommendation method, which can incorporate both textual and visual information of news to learn multimodal news representations. We firs"},"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":"2104.07407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-15T12:11:50Z","cross_cats_sorted":[],"title_canon_sha256":"8a4ea479f6ebb30f2426eacdc9c3715afa43df1e1cd7eb8d820e06a6882b8f17","abstract_canon_sha256":"5fe63cc81ba0216f327e1079ef67e6bd6e0be7327596da66538336eee7b64bfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:38.773301Z","signature_b64":"wJm9kZbnnM3t0OKTwRtTUBYlulrgBjLe62semMBwtFlDvDKwXLYZ/+yCZMCCMnFXRLYkDblhnd4pbvdKSs2qBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0688b269bde4be60dda9f9fa249f12d3906ffb7ed97083546b43eb5d58704d31","last_reissued_at":"2026-07-05T04:07:38.772835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:38.772835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Rec: Multimodal News Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang","submitted_at":"2021-04-15T12:11:50Z","abstract_excerpt":"Accurate news representation is critical for news recommendation. Most of existing news representation methods learn news representations only from news texts while ignore the visual information in news like images. In fact, users may click news not only because of the interest in news titles but also due to the attraction of news images. Thus, images are useful for representing news and predicting user behaviors. In this paper, we propose a multimodal news recommendation method, which can incorporate both textual and visual information of news to learn multimodal news representations. We firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07407","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/2104.07407/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":"2104.07407","created_at":"2026-07-05T04:07:38.772891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.07407v2","created_at":"2026-07-05T04:07:38.772891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07407","created_at":"2026-07-05T04:07:38.772891+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2ELE2N54S7G","created_at":"2026-07-05T04:07:38.772891+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2ELE2N54S7GBXNJ","created_at":"2026-07-05T04:07:38.772891+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2ELE2N5","created_at":"2026-07-05T04:07:38.772891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26941","citing_title":"The 2nd EReL@MIR Workshop on Efficient Representation Learning for Multimodal Information Retrieval","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O","json":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O.json","graph_json":"https://pith.science/api/pith-number/A2ELE2N54S7GBXNJ7H5CJHYS2O/graph.json","events_json":"https://pith.science/api/pith-number/A2ELE2N54S7GBXNJ7H5CJHYS2O/events.json","paper":"https://pith.science/paper/A2ELE2N5"},"agent_actions":{"view_html":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O","download_json":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O.json","view_paper":"https://pith.science/paper/A2ELE2N5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.07407&json=true","fetch_graph":"https://pith.science/api/pith-number/A2ELE2N54S7GBXNJ7H5CJHYS2O/graph.json","fetch_events":"https://pith.science/api/pith-number/A2ELE2N54S7GBXNJ7H5CJHYS2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O/action/storage_attestation","attest_author":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O/action/author_attestation","sign_citation":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O/action/citation_signature","submit_replication":"https://pith.science/pith/A2ELE2N54S7GBXNJ7H5CJHYS2O/action/replication_record"}},"created_at":"2026-07-05T04:07:38.772891+00:00","updated_at":"2026-07-05T04:07:38.772891+00:00"}