{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NDFDNML5YVXM36EUGSTLHBCTB","short_pith_number":"pith:6NDFDNML","schema_version":"1.0","canonical_sha256":"f34651b58bee2b766fc4a1a5359c22987f93562d02efbdec571331bdf96bb33d","source":{"kind":"arxiv","id":"2411.19513","version":1},"attestation_state":"computed","paper":{"title":"ContextGNN: Beyond Two-Tower Recommendation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Akihiro Nitta, Alan Krumholz, Bla\\v{z} Stojanovi\\v{c}, Dong Wang, Jan Eric Lenssen, Jure Leskovec, Manan Shah, Matthias Fey, Shenyang Huang, Weihua Hu, Xinwei He, Yiwen Yuan, Zecheng Zhang","submitted_at":"2024-11-29T07:11:42Z","abstract_excerpt":"Recommendation systems predominantly utilize two-tower architectures, which evaluate user-item rankings through the inner product of their respective embeddings. However, one key limitation of two-tower models is that they learn a pair-agnostic representation of users and items. In contrast, pair-wise representations either scale poorly due to their quadratic complexity or are too restrictive on the candidate pairs to rank. To address these issues, we introduce Context-based Graph Neural Networks (ContextGNNs), a novel deep learning architecture for link prediction in recommendation systems. T"},"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":"2411.19513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-29T07:11:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"08de81a70074ef7d7ca377608e5c3a516169f4493aa6d52ed786941915bc9fb8","abstract_canon_sha256":"93a6eb97d3504ee68a6eade2f2844e5b1d7b0daac5586da19bef14b04bac3b70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:03.536769Z","signature_b64":"0eoLIunOD8GlqWMlXBVeqM0PE8TKIwp/F1heU2Fp/3neqO4WOUvE1VAWO6g1F+K1eFdSIAU3GYiTeh11s/36Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f34651b58bee2b766fc4a1a5359c22987f93562d02efbdec571331bdf96bb33d","last_reissued_at":"2026-07-05T09:42:03.536265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:03.536265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ContextGNN: Beyond Two-Tower Recommendation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Akihiro Nitta, Alan Krumholz, Bla\\v{z} Stojanovi\\v{c}, Dong Wang, Jan Eric Lenssen, Jure Leskovec, Manan Shah, Matthias Fey, Shenyang Huang, Weihua Hu, Xinwei He, Yiwen Yuan, Zecheng Zhang","submitted_at":"2024-11-29T07:11:42Z","abstract_excerpt":"Recommendation systems predominantly utilize two-tower architectures, which evaluate user-item rankings through the inner product of their respective embeddings. However, one key limitation of two-tower models is that they learn a pair-agnostic representation of users and items. In contrast, pair-wise representations either scale poorly due to their quadratic complexity or are too restrictive on the candidate pairs to rank. To address these issues, we introduce Context-based Graph Neural Networks (ContextGNNs), a novel deep learning architecture for link prediction in recommendation systems. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19513","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/2411.19513/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":"2411.19513","created_at":"2026-07-05T09:42:03.536334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19513v1","created_at":"2026-07-05T09:42:03.536334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19513","created_at":"2026-07-05T09:42:03.536334+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NDFDNML5YVX","created_at":"2026-07-05T09:42:03.536334+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NDFDNML5YVXM36E","created_at":"2026-07-05T09:42:03.536334+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NDFDNML","created_at":"2026-07-05T09:42:03.536334+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/6NDFDNML5YVXM36EUGSTLHBCTB","json":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB.json","graph_json":"https://pith.science/api/pith-number/6NDFDNML5YVXM36EUGSTLHBCTB/graph.json","events_json":"https://pith.science/api/pith-number/6NDFDNML5YVXM36EUGSTLHBCTB/events.json","paper":"https://pith.science/paper/6NDFDNML"},"agent_actions":{"view_html":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB","download_json":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB.json","view_paper":"https://pith.science/paper/6NDFDNML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19513&json=true","fetch_graph":"https://pith.science/api/pith-number/6NDFDNML5YVXM36EUGSTLHBCTB/graph.json","fetch_events":"https://pith.science/api/pith-number/6NDFDNML5YVXM36EUGSTLHBCTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB/action/storage_attestation","attest_author":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB/action/author_attestation","sign_citation":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB/action/citation_signature","submit_replication":"https://pith.science/pith/6NDFDNML5YVXM36EUGSTLHBCTB/action/replication_record"}},"created_at":"2026-07-05T09:42:03.536334+00:00","updated_at":"2026-07-05T09:42:03.536334+00:00"}