{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GFPTSHWWYCIY465O2RWGNGMHES","short_pith_number":"pith:GFPTSHWW","schema_version":"1.0","canonical_sha256":"315f391ed6c0918e7baed46c669987249080be301c2ec677841ad43de2690793","source":{"kind":"arxiv","id":"2206.00583","version":2},"attestation_state":"computed","paper":{"title":"Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Di Jin, Dilek Hakkani-Tur, Ruoqing Zhu, Tianning Xu, Yifan Chen, Yun Yang","submitted_at":"2022-06-01T15:52:06Z","abstract_excerpt":"Multiple sampling-based methods have been developed for approximating and accelerating node embedding aggregation in graph convolutional networks (GCNs) training. Among them, a layer-wise approach recursively performs importance sampling to select neighbors jointly for existing nodes in each layer. This paper revisits the approach from a matrix approximation perspective, and identifies two issues in the existing layer-wise sampling methods: suboptimal sampling probabilities and estimation biases induced by sampling without replacement. To address these issues, we accordingly propose two remedi"},"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":"2206.00583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T15:52:06Z","cross_cats_sorted":[],"title_canon_sha256":"0d72cb725f868241274d5a7978597ac8ad39ba768dfa6903d8980a49e6214469","abstract_canon_sha256":"83c5b8eab0405ea1f6f10831b67928d92b71105f7856bdd55eeaace601a9e9b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:12.898582Z","signature_b64":"Wa8YmrotQWOJc0R9OI7jy2TLAJw0lLpUIcjs7qHjzEbWNP/Z6OeIITca2FKzrYcZKNRab9kannJbiFAhWg8PDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"315f391ed6c0918e7baed46c669987249080be301c2ec677841ad43de2690793","last_reissued_at":"2026-07-05T06:21:12.898164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:12.898164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Di Jin, Dilek Hakkani-Tur, Ruoqing Zhu, Tianning Xu, Yifan Chen, Yun Yang","submitted_at":"2022-06-01T15:52:06Z","abstract_excerpt":"Multiple sampling-based methods have been developed for approximating and accelerating node embedding aggregation in graph convolutional networks (GCNs) training. Among them, a layer-wise approach recursively performs importance sampling to select neighbors jointly for existing nodes in each layer. This paper revisits the approach from a matrix approximation perspective, and identifies two issues in the existing layer-wise sampling methods: suboptimal sampling probabilities and estimation biases induced by sampling without replacement. To address these issues, we accordingly propose two remedi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00583","kind":"arxiv","version":2},"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/2206.00583/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":"2206.00583","created_at":"2026-07-05T06:21:12.898237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00583v2","created_at":"2026-07-05T06:21:12.898237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00583","created_at":"2026-07-05T06:21:12.898237+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFPTSHWWYCIY","created_at":"2026-07-05T06:21:12.898237+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFPTSHWWYCIY465O","created_at":"2026-07-05T06:21:12.898237+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFPTSHWW","created_at":"2026-07-05T06:21:12.898237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08845","citing_title":"DAFOS: Dynamic Adaptive Fanout Optimization Sampler","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES","json":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES.json","graph_json":"https://pith.science/api/pith-number/GFPTSHWWYCIY465O2RWGNGMHES/graph.json","events_json":"https://pith.science/api/pith-number/GFPTSHWWYCIY465O2RWGNGMHES/events.json","paper":"https://pith.science/paper/GFPTSHWW"},"agent_actions":{"view_html":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES","download_json":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES.json","view_paper":"https://pith.science/paper/GFPTSHWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00583&json=true","fetch_graph":"https://pith.science/api/pith-number/GFPTSHWWYCIY465O2RWGNGMHES/graph.json","fetch_events":"https://pith.science/api/pith-number/GFPTSHWWYCIY465O2RWGNGMHES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES/action/storage_attestation","attest_author":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES/action/author_attestation","sign_citation":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES/action/citation_signature","submit_replication":"https://pith.science/pith/GFPTSHWWYCIY465O2RWGNGMHES/action/replication_record"}},"created_at":"2026-07-05T06:21:12.898237+00:00","updated_at":"2026-07-05T06:21:12.898237+00:00"}