{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S2O6O2IYQVV22MF2OXB3KMBWJS","short_pith_number":"pith:S2O6O2IY","schema_version":"1.0","canonical_sha256":"969de76918856bad30ba75c3b530364cba4035c48d64402878511f399c456376","source":{"kind":"arxiv","id":"2403.11408","version":1},"attestation_state":"computed","paper":{"title":"Layer-diverse Negative Sampling for Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Lu, Junyu Xuan, Wei Duan, Yu Guang Wang","submitted_at":"2024-03-18T01:48:50Z","abstract_excerpt":"Graph neural networks (GNNs) are a powerful solution for various structure learning applications due to their strong representation capabilities for graph data. However, traditional GNNs, relying on message-passing mechanisms that gather information exclusively from first-order neighbours (known as positive samples), can lead to issues such as over-smoothing and over-squashing. To mitigate these issues, we propose a layer-diverse negative sampling method for message-passing propagation. This method employs a sampling matrix within a determinantal point process, which transforms the candidate s"},"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":"2403.11408","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T01:48:50Z","cross_cats_sorted":[],"title_canon_sha256":"0a54088d4355139b3a732b3cda069373bdb93df9377a828cf0aff6356a87b494","abstract_canon_sha256":"9e5d0ce8c843eb1b7fff879208493a8fdf525b57c592cb378f13496ad571fc17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:15.837151Z","signature_b64":"AZxT/kcDBTq3tjxK1ePSWut4H2lCh2YNZkgEL5R+kOLZii/LEU6VlO5TmyjtPgz702KgSOmtVEJ+vjXaX7jPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"969de76918856bad30ba75c3b530364cba4035c48d64402878511f399c456376","last_reissued_at":"2026-07-05T07:57:15.836721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:15.836721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-diverse Negative Sampling for Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Lu, Junyu Xuan, Wei Duan, Yu Guang Wang","submitted_at":"2024-03-18T01:48:50Z","abstract_excerpt":"Graph neural networks (GNNs) are a powerful solution for various structure learning applications due to their strong representation capabilities for graph data. However, traditional GNNs, relying on message-passing mechanisms that gather information exclusively from first-order neighbours (known as positive samples), can lead to issues such as over-smoothing and over-squashing. To mitigate these issues, we propose a layer-diverse negative sampling method for message-passing propagation. This method employs a sampling matrix within a determinantal point process, which transforms the candidate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11408","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/2403.11408/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":"2403.11408","created_at":"2026-07-05T07:57:15.836782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11408v1","created_at":"2026-07-05T07:57:15.836782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11408","created_at":"2026-07-05T07:57:15.836782+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2O6O2IYQVV2","created_at":"2026-07-05T07:57:15.836782+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2O6O2IYQVV22MF2","created_at":"2026-07-05T07:57:15.836782+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2O6O2IY","created_at":"2026-07-05T07:57:15.836782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12169","citing_title":"SVGS-DSGAT: An IoT-Enabled Innovation in Underwater Robotic Object Detection Technology","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS","json":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS.json","graph_json":"https://pith.science/api/pith-number/S2O6O2IYQVV22MF2OXB3KMBWJS/graph.json","events_json":"https://pith.science/api/pith-number/S2O6O2IYQVV22MF2OXB3KMBWJS/events.json","paper":"https://pith.science/paper/S2O6O2IY"},"agent_actions":{"view_html":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS","download_json":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS.json","view_paper":"https://pith.science/paper/S2O6O2IY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11408&json=true","fetch_graph":"https://pith.science/api/pith-number/S2O6O2IYQVV22MF2OXB3KMBWJS/graph.json","fetch_events":"https://pith.science/api/pith-number/S2O6O2IYQVV22MF2OXB3KMBWJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS/action/storage_attestation","attest_author":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS/action/author_attestation","sign_citation":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS/action/citation_signature","submit_replication":"https://pith.science/pith/S2O6O2IYQVV22MF2OXB3KMBWJS/action/replication_record"}},"created_at":"2026-07-05T07:57:15.836782+00:00","updated_at":"2026-07-05T07:57:15.836782+00:00"}