{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:477WLUV5ANVOGYGIYROWBTOOW2","short_pith_number":"pith:477WLUV5","schema_version":"1.0","canonical_sha256":"e7ff65d2bd036ae360c8c45d60cdceb69965a466eff14fc06eb3b0e6b7628881","source":{"kind":"arxiv","id":"2202.09025","version":1},"attestation_state":"computed","paper":{"title":"Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Carl Yang, Mingyue Tang, Pan Li","submitted_at":"2022-02-18T05:08:04Z","abstract_excerpt":"Graph neural networks (GNNs) have drawn significant research attention recently, mostly under the setting of semi-supervised learning. When task-agnostic representations are preferred or supervision is simply unavailable, the auto-encoder framework comes in handy with a natural graph reconstruction objective for unsupervised GNN training. However, existing graph auto-encoders are designed to reconstruct the direct links, so GNNs trained in this way are only optimized towards proximity-oriented graph mining tasks, and will fall short when the topological structures matter. In this work, we revi"},"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":"2202.09025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-18T05:08:04Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"ff7fafed8c481da5ee68319b6f326b36dfbabe3ce1bef631f8c2b4590d001086","abstract_canon_sha256":"cb84d73c7dee648351fd69f3be3c8f26375e355a2f2898650f219587872d250e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:08.964820Z","signature_b64":"hfhAWJIKx6R7hFrtslUWU1EJ/GZfQ7tumPWeIK9lnvqGteNJpqMilCDc+EHY1m0TvklKw0N1ud6ai8bdKmFuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7ff65d2bd036ae360c8c45d60cdceb69965a466eff14fc06eb3b0e6b7628881","last_reissued_at":"2026-07-05T03:58:08.964459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:08.964459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Carl Yang, Mingyue Tang, Pan Li","submitted_at":"2022-02-18T05:08:04Z","abstract_excerpt":"Graph neural networks (GNNs) have drawn significant research attention recently, mostly under the setting of semi-supervised learning. When task-agnostic representations are preferred or supervision is simply unavailable, the auto-encoder framework comes in handy with a natural graph reconstruction objective for unsupervised GNN training. However, existing graph auto-encoders are designed to reconstruct the direct links, so GNNs trained in this way are only optimized towards proximity-oriented graph mining tasks, and will fall short when the topological structures matter. In this work, we revi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09025","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/2202.09025/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":"2202.09025","created_at":"2026-07-05T03:58:08.964521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09025v1","created_at":"2026-07-05T03:58:08.964521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09025","created_at":"2026-07-05T03:58:08.964521+00:00"},{"alias_kind":"pith_short_12","alias_value":"477WLUV5ANVO","created_at":"2026-07-05T03:58:08.964521+00:00"},{"alias_kind":"pith_short_16","alias_value":"477WLUV5ANVOGYGI","created_at":"2026-07-05T03:58:08.964521+00:00"},{"alias_kind":"pith_short_8","alias_value":"477WLUV5","created_at":"2026-07-05T03:58:08.964521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19750","citing_title":"A Unified Framework for Interactive Visual Graph Matching via Attribute-Structure Synchronization","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2","json":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2.json","graph_json":"https://pith.science/api/pith-number/477WLUV5ANVOGYGIYROWBTOOW2/graph.json","events_json":"https://pith.science/api/pith-number/477WLUV5ANVOGYGIYROWBTOOW2/events.json","paper":"https://pith.science/paper/477WLUV5"},"agent_actions":{"view_html":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2","download_json":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2.json","view_paper":"https://pith.science/paper/477WLUV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09025&json=true","fetch_graph":"https://pith.science/api/pith-number/477WLUV5ANVOGYGIYROWBTOOW2/graph.json","fetch_events":"https://pith.science/api/pith-number/477WLUV5ANVOGYGIYROWBTOOW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2/action/storage_attestation","attest_author":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2/action/author_attestation","sign_citation":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2/action/citation_signature","submit_replication":"https://pith.science/pith/477WLUV5ANVOGYGIYROWBTOOW2/action/replication_record"}},"created_at":"2026-07-05T03:58:08.964521+00:00","updated_at":"2026-07-05T03:58:08.964521+00:00"}