{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IAR42EWGBDROKAVGQGFL7K3S7G","short_pith_number":"pith:IAR42EWG","schema_version":"1.0","canonical_sha256":"4023cd12c608e2e502a6818abfab72f9942f59747b38a917c1effce40ed0ec68","source":{"kind":"arxiv","id":"2205.10803","version":3},"attestation_state":"computed","paper":{"title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunjie Wang, Hongxia Yang, Jie Tang, Xiao Liu, Yukuo Cen, Yuxiao Dong, Zhenyu Hou","submitted_at":"2022-05-22T11:57:08Z","abstract_excerpt":"Self-supervised learning (SSL) has been extensively explored in recent years. Particularly, generative SSL has seen emerging success in natural language processing and other AI fields, such as the wide adoption of BERT and GPT. Despite this, contrastive learning-which heavily relies on structural data augmentation and complicated training strategies-has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields. In this paper, we identify and examine the issues"},"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":"2205.10803","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-22T11:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"8eb3631f79531507ce2949df5d570e39d9ad656eb444208ad4b5ab424ba44746","abstract_canon_sha256":"e4fffe2b7b296ff33570fb63c2c23a4db4d8ca1aaef8487b7b2a9e45adb1f74a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:01.709286Z","signature_b64":"shnHY3H0BhsVK0HrPYGwr54CjlrcDJndYfxMYHfEri0jDF95OJRKxXC8AQFTA/yqkYXygZSPk3IP+W9dDUubBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4023cd12c608e2e502a6818abfab72f9942f59747b38a917c1effce40ed0ec68","last_reissued_at":"2026-07-05T04:40:01.708809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:01.708809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunjie Wang, Hongxia Yang, Jie Tang, Xiao Liu, Yukuo Cen, Yuxiao Dong, Zhenyu Hou","submitted_at":"2022-05-22T11:57:08Z","abstract_excerpt":"Self-supervised learning (SSL) has been extensively explored in recent years. Particularly, generative SSL has seen emerging success in natural language processing and other AI fields, such as the wide adoption of BERT and GPT. Despite this, contrastive learning-which heavily relies on structural data augmentation and complicated training strategies-has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields. In this paper, we identify and examine the issues"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10803","kind":"arxiv","version":3},"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/2205.10803/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":"2205.10803","created_at":"2026-07-05T04:40:01.708872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10803v3","created_at":"2026-07-05T04:40:01.708872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10803","created_at":"2026-07-05T04:40:01.708872+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAR42EWGBDRO","created_at":"2026-07-05T04:40:01.708872+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAR42EWGBDROKAVG","created_at":"2026-07-05T04:40:01.708872+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAR42EWG","created_at":"2026-07-05T04:40:01.708872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17667","citing_title":"Handling Feature Heterogeneity with Learnable Graph Patches","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16416","citing_title":"SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08689","citing_title":"Structure-Centric Graph Foundation Model via Geometric Bases","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07037","citing_title":"Towards foundation-style models for energy-frontier heterogeneous neutrino detectors via self-supervised pre-training","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G","json":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G.json","graph_json":"https://pith.science/api/pith-number/IAR42EWGBDROKAVGQGFL7K3S7G/graph.json","events_json":"https://pith.science/api/pith-number/IAR42EWGBDROKAVGQGFL7K3S7G/events.json","paper":"https://pith.science/paper/IAR42EWG"},"agent_actions":{"view_html":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G","download_json":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G.json","view_paper":"https://pith.science/paper/IAR42EWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10803&json=true","fetch_graph":"https://pith.science/api/pith-number/IAR42EWGBDROKAVGQGFL7K3S7G/graph.json","fetch_events":"https://pith.science/api/pith-number/IAR42EWGBDROKAVGQGFL7K3S7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G/action/storage_attestation","attest_author":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G/action/author_attestation","sign_citation":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G/action/citation_signature","submit_replication":"https://pith.science/pith/IAR42EWGBDROKAVGQGFL7K3S7G/action/replication_record"}},"created_at":"2026-07-05T04:40:01.708872+00:00","updated_at":"2026-07-05T04:40:01.708872+00:00"}