{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:D77A4XCT25RMFHLO7X3SOZKEQZ","short_pith_number":"pith:D77A4XCT","schema_version":"1.0","canonical_sha256":"1ffe0e5c53d762c29d6efdf72765448654d11e59f7cad66fbb5e663a44ca1432","source":{"kind":"arxiv","id":"2106.10866","version":4},"attestation_state":"computed","paper":{"title":"Customizing Graph Neural Networks using Path Reweighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bitan Hou, Jianpeng Chen, Ming Zeng, Ole J. Mengshoel, Yazhou Ren, Yujing Wang, Yunhai Tong, Zongyi Xiang","submitted_at":"2021-06-21T05:38:26Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not always effective. Intuitively, paths in a graph imply different semantics for different downstream tasks. Inspired by this, we design a novel GNN solution, namely Customized Graph Neural Network with Path Reweighting (CustomGNN for short). Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks"},"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":"2106.10866","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T05:38:26Z","cross_cats_sorted":[],"title_canon_sha256":"4b1b5fdfd28556439153b5cb420cd7c6c3cbd21ae7fe74d954409753d8de04b5","abstract_canon_sha256":"31a7a121c148bba21419308f506af4031d0fd76f36f90d10d67cade074e9d251"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:44.384879Z","signature_b64":"GWRr1+mM/yT/ijSEW1owUS1MTtPied1MbsnVctCevGJ0UFyTn7v/n0RqyteAEr2ljVE9pT44uH+cnDgNsdMdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ffe0e5c53d762c29d6efdf72765448654d11e59f7cad66fbb5e663a44ca1432","last_reissued_at":"2026-07-05T09:08:44.384310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:44.384310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Customizing Graph Neural Networks using Path Reweighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bitan Hou, Jianpeng Chen, Ming Zeng, Ole J. Mengshoel, Yazhou Ren, Yujing Wang, Yunhai Tong, Zongyi Xiang","submitted_at":"2021-06-21T05:38:26Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not always effective. Intuitively, paths in a graph imply different semantics for different downstream tasks. Inspired by this, we design a novel GNN solution, namely Customized Graph Neural Network with Path Reweighting (CustomGNN for short). Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10866","kind":"arxiv","version":4},"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/2106.10866/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":"2106.10866","created_at":"2026-07-05T09:08:44.384386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.10866v4","created_at":"2026-07-05T09:08:44.384386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10866","created_at":"2026-07-05T09:08:44.384386+00:00"},{"alias_kind":"pith_short_12","alias_value":"D77A4XCT25RM","created_at":"2026-07-05T09:08:44.384386+00:00"},{"alias_kind":"pith_short_16","alias_value":"D77A4XCT25RMFHLO","created_at":"2026-07-05T09:08:44.384386+00:00"},{"alias_kind":"pith_short_8","alias_value":"D77A4XCT","created_at":"2026-07-05T09:08:44.384386+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/D77A4XCT25RMFHLO7X3SOZKEQZ","json":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ.json","graph_json":"https://pith.science/api/pith-number/D77A4XCT25RMFHLO7X3SOZKEQZ/graph.json","events_json":"https://pith.science/api/pith-number/D77A4XCT25RMFHLO7X3SOZKEQZ/events.json","paper":"https://pith.science/paper/D77A4XCT"},"agent_actions":{"view_html":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ","download_json":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ.json","view_paper":"https://pith.science/paper/D77A4XCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.10866&json=true","fetch_graph":"https://pith.science/api/pith-number/D77A4XCT25RMFHLO7X3SOZKEQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/D77A4XCT25RMFHLO7X3SOZKEQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ/action/storage_attestation","attest_author":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ/action/author_attestation","sign_citation":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ/action/citation_signature","submit_replication":"https://pith.science/pith/D77A4XCT25RMFHLO7X3SOZKEQZ/action/replication_record"}},"created_at":"2026-07-05T09:08:44.384386+00:00","updated_at":"2026-07-05T09:08:44.384386+00:00"}