{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7THLI5VXWRQ22PHGY6L5Q5TOT6","short_pith_number":"pith:7THLI5VX","schema_version":"1.0","canonical_sha256":"fcceb476b7b461ad3ce6c797d8766e9f935b5a842406bd8a6fd3aa046b86977a","source":{"kind":"arxiv","id":"2410.10089","version":1},"attestation_state":"computed","paper":{"title":"PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fei Liu, Le Wu, Shengwei Ji, Xinlu Li, Yujie Tian","submitted_at":"2024-10-14T02:07:02Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out of memory (OOM) errors on mainstream GPUs (e.g., 29GB memory consumption on the Ogbnproducts graph with 5 layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgra"},"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":"2410.10089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T02:07:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd69f72ae0584faea22d1f3923effebf2e3e979c7b529ad3a7055304118a8169","abstract_canon_sha256":"44462f504641f222daf15807cbe48ff91742642f14c8a5823a042f8662c4e108"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:10.968692Z","signature_b64":"Pq2JSB97TnQfz6W4HFlyQ89WgLyd8ia+JOjl4ae5efQE5Lm149x7YRsdfMP4A+aEOcuGE8mWP/QVgh7VaRjOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcceb476b7b461ad3ce6c797d8766e9f935b5a842406bd8a6fd3aa046b86977a","last_reissued_at":"2026-07-05T09:20:10.968237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:10.968237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fei Liu, Le Wu, Shengwei Ji, Xinlu Li, Yujie Tian","submitted_at":"2024-10-14T02:07:02Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out of memory (OOM) errors on mainstream GPUs (e.g., 29GB memory consumption on the Ogbnproducts graph with 5 layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10089","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/2410.10089/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":"2410.10089","created_at":"2026-07-05T09:20:10.968292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10089v1","created_at":"2026-07-05T09:20:10.968292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10089","created_at":"2026-07-05T09:20:10.968292+00:00"},{"alias_kind":"pith_short_12","alias_value":"7THLI5VXWRQ2","created_at":"2026-07-05T09:20:10.968292+00:00"},{"alias_kind":"pith_short_16","alias_value":"7THLI5VXWRQ22PHG","created_at":"2026-07-05T09:20:10.968292+00:00"},{"alias_kind":"pith_short_8","alias_value":"7THLI5VX","created_at":"2026-07-05T09:20:10.968292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00267","citing_title":"Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6","json":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6.json","graph_json":"https://pith.science/api/pith-number/7THLI5VXWRQ22PHGY6L5Q5TOT6/graph.json","events_json":"https://pith.science/api/pith-number/7THLI5VXWRQ22PHGY6L5Q5TOT6/events.json","paper":"https://pith.science/paper/7THLI5VX"},"agent_actions":{"view_html":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6","download_json":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6.json","view_paper":"https://pith.science/paper/7THLI5VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10089&json=true","fetch_graph":"https://pith.science/api/pith-number/7THLI5VXWRQ22PHGY6L5Q5TOT6/graph.json","fetch_events":"https://pith.science/api/pith-number/7THLI5VXWRQ22PHGY6L5Q5TOT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6/action/storage_attestation","attest_author":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6/action/author_attestation","sign_citation":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6/action/citation_signature","submit_replication":"https://pith.science/pith/7THLI5VXWRQ22PHGY6L5Q5TOT6/action/replication_record"}},"created_at":"2026-07-05T09:20:10.968292+00:00","updated_at":"2026-07-05T09:20:10.968292+00:00"}