{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DAFTAA66EXOL5EVDF5KNHAQLQL","short_pith_number":"pith:DAFTAA66","schema_version":"1.0","canonical_sha256":"180b3003de25dcbe92a32f54d3820b82f35bad48a299571f5cf10eb5cb2cce77","source":{"kind":"arxiv","id":"2405.12486","version":1},"attestation_state":"computed","paper":{"title":"Time Matters: Enhancing Pre-trained News Recommendation Models with Robust User Dwell Time Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chuanzhen Li, Hao Jiang, Mingxiao An","submitted_at":"2024-05-21T04:08:07Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized text comprehension, leading to State-of-the-Art (SOTA) news recommendation models that utilize LLMs for in-depth news understanding. Despite this, accurately modeling user preferences remains challenging due to the inherent uncertainty of click behaviors. Techniques like multi-head attention in Transformers seek to alleviate this by capturing interactions among clicks, yet they fall short in integrating explicit feedback signals. User Dwell Time emerges as a powerful indicator, offering the potential to enhance the weak signals emanating from cl"},"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":"2405.12486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-21T04:08:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bf1e1417a2812884c8793e69a94f076b1370302471762ad3589e2ad29b5e4076","abstract_canon_sha256":"51f307965a22c75a56c78b76819e50ae68ca419e59200cd5553971e7c6131019"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:20.781976Z","signature_b64":"AA4XZwxUTMWrWio0VWjS0cSPlItMXckJAxvqa7c2XnUXz+/3Xdjp2ja9J9jz8kT3wHYSfzIPYEbt/bBpoVptBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"180b3003de25dcbe92a32f54d3820b82f35bad48a299571f5cf10eb5cb2cce77","last_reissued_at":"2026-07-05T08:21:20.781574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:20.781574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Matters: Enhancing Pre-trained News Recommendation Models with Robust User Dwell Time Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chuanzhen Li, Hao Jiang, Mingxiao An","submitted_at":"2024-05-21T04:08:07Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized text comprehension, leading to State-of-the-Art (SOTA) news recommendation models that utilize LLMs for in-depth news understanding. Despite this, accurately modeling user preferences remains challenging due to the inherent uncertainty of click behaviors. Techniques like multi-head attention in Transformers seek to alleviate this by capturing interactions among clicks, yet they fall short in integrating explicit feedback signals. User Dwell Time emerges as a powerful indicator, offering the potential to enhance the weak signals emanating from cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12486","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/2405.12486/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":"2405.12486","created_at":"2026-07-05T08:21:20.781628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12486v1","created_at":"2026-07-05T08:21:20.781628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12486","created_at":"2026-07-05T08:21:20.781628+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAFTAA66EXOL","created_at":"2026-07-05T08:21:20.781628+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAFTAA66EXOL5EVD","created_at":"2026-07-05T08:21:20.781628+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAFTAA66","created_at":"2026-07-05T08:21:20.781628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07178","citing_title":"Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL","json":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL.json","graph_json":"https://pith.science/api/pith-number/DAFTAA66EXOL5EVDF5KNHAQLQL/graph.json","events_json":"https://pith.science/api/pith-number/DAFTAA66EXOL5EVDF5KNHAQLQL/events.json","paper":"https://pith.science/paper/DAFTAA66"},"agent_actions":{"view_html":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL","download_json":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL.json","view_paper":"https://pith.science/paper/DAFTAA66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12486&json=true","fetch_graph":"https://pith.science/api/pith-number/DAFTAA66EXOL5EVDF5KNHAQLQL/graph.json","fetch_events":"https://pith.science/api/pith-number/DAFTAA66EXOL5EVDF5KNHAQLQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL/action/storage_attestation","attest_author":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL/action/author_attestation","sign_citation":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL/action/citation_signature","submit_replication":"https://pith.science/pith/DAFTAA66EXOL5EVDF5KNHAQLQL/action/replication_record"}},"created_at":"2026-07-05T08:21:20.781628+00:00","updated_at":"2026-07-05T08:21:20.781628+00:00"}