{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DPPP53JZJZ4OMHIAPPF6S23WZL","short_pith_number":"pith:DPPP53JZ","schema_version":"1.0","canonical_sha256":"1bdefeed394e78e61d007bcbe96b76cafb733ecc2739dc9e2f318ca01c6345e2","source":{"kind":"arxiv","id":"1802.02896","version":2},"attestation_state":"computed","paper":{"title":"Learning Role-based Graph Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI","stat.AP"],"primary_cat":"stat.ML","authors_text":"Hoda Eldardiry, John Boaz Lee, Nesreen K. Ahmed, Rong Zhou, Ryan Rossi, Theodore L. Willke, Xiangnan Kong","submitted_at":"2018-02-07T00:29:44Z","abstract_excerpt":"Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce the Role2Vec framework which uses the flexible notion of attributed random walks, and serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applic"},"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":"1802.02896","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-07T00:29:44Z","cross_cats_sorted":["cs.AI","cs.SI","stat.AP"],"title_canon_sha256":"ebff2da9f6a6a352902e278f37e167dfaedfd39b40fe0030c252c5be8710b065","abstract_canon_sha256":"38f3115439b2ab2af1368d0d5080de82170ededfe68b3796efbcbf57bfe615da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:49.882611Z","signature_b64":"XFewJSkvs4eQrANVTASUxJfc+7Sg5vv+/GphfzUQ97r/wqQT9tl4U/HMrAARx70NvOlxQ/2OcS4BGW74OV5oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bdefeed394e78e61d007bcbe96b76cafb733ecc2739dc9e2f318ca01c6345e2","last_reissued_at":"2026-05-18T00:11:49.882079Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:49.882079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Role-based Graph Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI","stat.AP"],"primary_cat":"stat.ML","authors_text":"Hoda Eldardiry, John Boaz Lee, Nesreen K. Ahmed, Rong Zhou, Ryan Rossi, Theodore L. Willke, Xiangnan Kong","submitted_at":"2018-02-07T00:29:44Z","abstract_excerpt":"Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce the Role2Vec framework which uses the flexible notion of attributed random walks, and serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02896","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":""},"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":"1802.02896","created_at":"2026-05-18T00:11:49.882158+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02896v2","created_at":"2026-05-18T00:11:49.882158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02896","created_at":"2026-05-18T00:11:49.882158+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPPP53JZJZ4O","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPPP53JZJZ4OMHIA","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPPP53JZ","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11142","citing_title":"Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00716","citing_title":"Aitchison Embeddings for Learning Compositional Graph Representations","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL","json":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL.json","graph_json":"https://pith.science/api/pith-number/DPPP53JZJZ4OMHIAPPF6S23WZL/graph.json","events_json":"https://pith.science/api/pith-number/DPPP53JZJZ4OMHIAPPF6S23WZL/events.json","paper":"https://pith.science/paper/DPPP53JZ"},"agent_actions":{"view_html":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL","download_json":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL.json","view_paper":"https://pith.science/paper/DPPP53JZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02896&json=true","fetch_graph":"https://pith.science/api/pith-number/DPPP53JZJZ4OMHIAPPF6S23WZL/graph.json","fetch_events":"https://pith.science/api/pith-number/DPPP53JZJZ4OMHIAPPF6S23WZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL/action/storage_attestation","attest_author":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL/action/author_attestation","sign_citation":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL/action/citation_signature","submit_replication":"https://pith.science/pith/DPPP53JZJZ4OMHIAPPF6S23WZL/action/replication_record"}},"created_at":"2026-05-18T00:11:49.882158+00:00","updated_at":"2026-05-18T00:11:49.882158+00:00"}