{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:V3AD5R4EAYCOM2SK2VU5SKWT2E","short_pith_number":"pith:V3AD5R4E","schema_version":"1.0","canonical_sha256":"aec03ec7840604e66a4ad569d92ad3d12884ebf8db37b3b5fb9ff0f0a9f002b5","source":{"kind":"arxiv","id":"2210.02946","version":1},"attestation_state":"computed","paper":{"title":"VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"(2) Peking University), Songhao Han (1), Wei Huang (1), Xiaotian Luan (2) ((1) Beihang University","submitted_at":"2022-10-06T14:27:37Z","abstract_excerpt":"News representation and user-oriented modeling are both essential for news recommendation. Most existing methods are based on textual information but ignore the visual information and users' dynamic interests. However, compared to textual only content, multimodal semantics is beneficial for enhancing the comprehension of users' temporal and long-lasting interests. In our work, we propose a vision-linguistics coordinate time sequence news recommendation. Firstly, a pretrained multimodal encoder is applied to embed images and texts into the same feature space. Then the self-attention network is "},"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":"2210.02946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-10-06T14:27:37Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"daaae0d2f558502b393688a684642ffbea373fccba5d1f1d8a514ee2ed4f4d73","abstract_canon_sha256":"c208250a0b29f0799d9b9b40151bbc283334b903712dc41e7c2f4c2bcebc313a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:05.576054Z","signature_b64":"cANcJCgLvInhAPPq7b0YYQuZPzulpkFAsSXXVpVoHnzU18leY1SWHV7TVlB641UtwiiYYeyQwawcaPIN1pg5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aec03ec7840604e66a4ad569d92ad3d12884ebf8db37b3b5fb9ff0f0a9f002b5","last_reissued_at":"2026-07-05T05:04:05.575654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:05.575654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"(2) Peking University), Songhao Han (1), Wei Huang (1), Xiaotian Luan (2) ((1) Beihang University","submitted_at":"2022-10-06T14:27:37Z","abstract_excerpt":"News representation and user-oriented modeling are both essential for news recommendation. Most existing methods are based on textual information but ignore the visual information and users' dynamic interests. However, compared to textual only content, multimodal semantics is beneficial for enhancing the comprehension of users' temporal and long-lasting interests. In our work, we propose a vision-linguistics coordinate time sequence news recommendation. Firstly, a pretrained multimodal encoder is applied to embed images and texts into the same feature space. Then the self-attention network is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02946","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/2210.02946/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":"2210.02946","created_at":"2026-07-05T05:04:05.575735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02946v1","created_at":"2026-07-05T05:04:05.575735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02946","created_at":"2026-07-05T05:04:05.575735+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3AD5R4EAYCO","created_at":"2026-07-05T05:04:05.575735+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3AD5R4EAYCOM2SK","created_at":"2026-07-05T05:04:05.575735+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3AD5R4E","created_at":"2026-07-05T05:04:05.575735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15460","citing_title":"Privacy-Preserving Multimodal News Recommendation through Federated Learning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E","json":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E.json","graph_json":"https://pith.science/api/pith-number/V3AD5R4EAYCOM2SK2VU5SKWT2E/graph.json","events_json":"https://pith.science/api/pith-number/V3AD5R4EAYCOM2SK2VU5SKWT2E/events.json","paper":"https://pith.science/paper/V3AD5R4E"},"agent_actions":{"view_html":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E","download_json":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E.json","view_paper":"https://pith.science/paper/V3AD5R4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02946&json=true","fetch_graph":"https://pith.science/api/pith-number/V3AD5R4EAYCOM2SK2VU5SKWT2E/graph.json","fetch_events":"https://pith.science/api/pith-number/V3AD5R4EAYCOM2SK2VU5SKWT2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E/action/storage_attestation","attest_author":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E/action/author_attestation","sign_citation":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E/action/citation_signature","submit_replication":"https://pith.science/pith/V3AD5R4EAYCOM2SK2VU5SKWT2E/action/replication_record"}},"created_at":"2026-07-05T05:04:05.575735+00:00","updated_at":"2026-07-05T05:04:05.575735+00:00"}