{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HZRKUZA2ATEZ4ZJI3FBAQTWQXG","short_pith_number":"pith:HZRKUZA2","schema_version":"1.0","canonical_sha256":"3e62aa641a04c99e6528d942084ed0b98dda2ead5efe82d68d23876e9d42bb6c","source":{"kind":"arxiv","id":"2202.08391","version":2},"attestation_state":"computed","paper":{"title":"Graph Masked Autoencoders with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Guandong Xu, Haoran Yang, Hongxu Chen, Philip S. Yu, Sixiao Zhang, Xiangguo Sun","submitted_at":"2022-02-17T01:04:32Z","abstract_excerpt":"Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train from scratch and the quadratic memory consumption w.r.t. the number of nodes. In this paper, we propose Graph Masked Autoencoders (GMAEs), a self-supervised transformer-based model for learning graph representations. To address the above two challenges, we adopt the masking mechanism and the asymmetric encoder-decoder design. Specifically, GMAE takes partial"},"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":"2202.08391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-17T01:04:32Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"24bad73f89f60049fe4b176a426b7fa5b11d82b0119e7c6b195d9d46254876a8","abstract_canon_sha256":"0ae853421fdc6f40fc95e12ae705ceeb1887fc1976919c2c647cfc82ea0d7af1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:40.601530Z","signature_b64":"9qD9+Sx3P87a06OO8c7NuVNaKjpzmWR4MfCCFqfrF8TYIxMAQ0wgl3fFRcNDWHaeBj4uN3T3Bu3T7KuUQEqcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e62aa641a04c99e6528d942084ed0b98dda2ead5efe82d68d23876e9d42bb6c","last_reissued_at":"2026-07-05T04:22:40.601074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:40.601074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Masked Autoencoders with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Guandong Xu, Haoran Yang, Hongxu Chen, Philip S. Yu, Sixiao Zhang, Xiangguo Sun","submitted_at":"2022-02-17T01:04:32Z","abstract_excerpt":"Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train from scratch and the quadratic memory consumption w.r.t. the number of nodes. In this paper, we propose Graph Masked Autoencoders (GMAEs), a self-supervised transformer-based model for learning graph representations. To address the above two challenges, we adopt the masking mechanism and the asymmetric encoder-decoder design. Specifically, GMAE takes partial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08391","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/2202.08391/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":"2202.08391","created_at":"2026-07-05T04:22:40.601132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.08391v2","created_at":"2026-07-05T04:22:40.601132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08391","created_at":"2026-07-05T04:22:40.601132+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZRKUZA2ATEZ","created_at":"2026-07-05T04:22:40.601132+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZRKUZA2ATEZ4ZJI","created_at":"2026-07-05T04:22:40.601132+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZRKUZA2","created_at":"2026-07-05T04:22:40.601132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09065","citing_title":"Display Content, Display Methods and Evaluation Methods of the HCI in Explainable Recommender Systems: A Survey","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG","json":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG.json","graph_json":"https://pith.science/api/pith-number/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/graph.json","events_json":"https://pith.science/api/pith-number/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/events.json","paper":"https://pith.science/paper/HZRKUZA2"},"agent_actions":{"view_html":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG","download_json":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG.json","view_paper":"https://pith.science/paper/HZRKUZA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.08391&json=true","fetch_graph":"https://pith.science/api/pith-number/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/graph.json","fetch_events":"https://pith.science/api/pith-number/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/action/storage_attestation","attest_author":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/action/author_attestation","sign_citation":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/action/citation_signature","submit_replication":"https://pith.science/pith/HZRKUZA2ATEZ4ZJI3FBAQTWQXG/action/replication_record"}},"created_at":"2026-07-05T04:22:40.601132+00:00","updated_at":"2026-07-05T04:22:40.601132+00:00"}