{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M6UAXGXA5TJ6HN3ROYCYB772QT","short_pith_number":"pith:M6UAXGXA","schema_version":"1.0","canonical_sha256":"67a80b9ae0ecd3e3b771760580fffa84d6f6afc19f0ccfbb6443ef1bff65ea1e","source":{"kind":"arxiv","id":"2503.02960","version":1},"attestation_state":"computed","paper":{"title":"Deal: Distributed End-to-End GNN Inference for All Nodes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Hang Liu, Shiyang Chen, Vasiloudis Theodore, Xiang Song","submitted_at":"2025-03-04T19:35:41Z","abstract_excerpt":"Graph Neural Networks (GNNs) are a new research frontier with various applications and successes. The end-to-end inference for all nodes, is common for GNN embedding models, which are widely adopted in applications like recommendation and advertising. While sharing opportunities arise in GNN tasks (i.e., inference for a few nodes and training), the potential for sharing in full graph end-to-end inference is largely underutilized because traditional efforts fail to fully extract sharing benefits due to overwhelming overheads or excessive memory usage.\n  This paper introduces Deal, a distributed"},"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":"2503.02960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-03-04T19:35:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3652dfc6350015010fc6753595a885d01b27ff4b6d2ecfd77cdb591294ea4a4a","abstract_canon_sha256":"c1816e07bac2276e25131e504a08c1efe908049c051c3045c9364484ba41f1b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:35.825555Z","signature_b64":"NBnFybtKU3fj7gCh7ts0/BTCIkvT6vEH7bCM+R4d3DNAIcGcOpF75UobfD7id0FPTwWx2UZbwgsmIdmur07tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67a80b9ae0ecd3e3b771760580fffa84d6f6afc19f0ccfbb6443ef1bff65ea1e","last_reissued_at":"2026-07-05T10:24:35.824912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:35.824912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deal: Distributed End-to-End GNN Inference for All Nodes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Hang Liu, Shiyang Chen, Vasiloudis Theodore, Xiang Song","submitted_at":"2025-03-04T19:35:41Z","abstract_excerpt":"Graph Neural Networks (GNNs) are a new research frontier with various applications and successes. The end-to-end inference for all nodes, is common for GNN embedding models, which are widely adopted in applications like recommendation and advertising. While sharing opportunities arise in GNN tasks (i.e., inference for a few nodes and training), the potential for sharing in full graph end-to-end inference is largely underutilized because traditional efforts fail to fully extract sharing benefits due to overwhelming overheads or excessive memory usage.\n  This paper introduces Deal, a distributed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02960","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/2503.02960/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":"2503.02960","created_at":"2026-07-05T10:24:35.824988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02960v1","created_at":"2026-07-05T10:24:35.824988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02960","created_at":"2026-07-05T10:24:35.824988+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6UAXGXA5TJ6","created_at":"2026-07-05T10:24:35.824988+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6UAXGXA5TJ6HN3R","created_at":"2026-07-05T10:24:35.824988+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6UAXGXA","created_at":"2026-07-05T10:24:35.824988+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09402","citing_title":"ATLAS: Efficient Out-of-Core Inference for Billion-Scale Graph Neural Networks","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT","json":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT.json","graph_json":"https://pith.science/api/pith-number/M6UAXGXA5TJ6HN3ROYCYB772QT/graph.json","events_json":"https://pith.science/api/pith-number/M6UAXGXA5TJ6HN3ROYCYB772QT/events.json","paper":"https://pith.science/paper/M6UAXGXA"},"agent_actions":{"view_html":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT","download_json":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT.json","view_paper":"https://pith.science/paper/M6UAXGXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02960&json=true","fetch_graph":"https://pith.science/api/pith-number/M6UAXGXA5TJ6HN3ROYCYB772QT/graph.json","fetch_events":"https://pith.science/api/pith-number/M6UAXGXA5TJ6HN3ROYCYB772QT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT/action/storage_attestation","attest_author":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT/action/author_attestation","sign_citation":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT/action/citation_signature","submit_replication":"https://pith.science/pith/M6UAXGXA5TJ6HN3ROYCYB772QT/action/replication_record"}},"created_at":"2026-07-05T10:24:35.824988+00:00","updated_at":"2026-07-05T10:24:35.824988+00:00"}