{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VMQAJCJG6IY2EYL25T6MEU5VQR","short_pith_number":"pith:VMQAJCJG","schema_version":"1.0","canonical_sha256":"ab20048926f231a2617aecfcc253b5845a1679bb27073445953a10d60b7b0d3b","source":{"kind":"arxiv","id":"2201.02534","version":1},"attestation_state":"computed","paper":{"title":"MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.SI"],"primary_cat":"cs.LG","authors_text":"Ninghao Liu, Qiaoyu Tan, Rui Chen, Soo-Hyun Choi, Xia Hu, Xiao Huang","submitted_at":"2022-01-07T16:48:07Z","abstract_excerpt":"We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these missing edges during training. MGAE has two core designs. First, we find that masking a high ratio of the input graph structure, e.g., $70\\%$, yields a nontrivial and meaningful self-supervisory task that benefits downstream applications. Second, we employ a graph neural network (GNN) as an encoder to perform message propagation on the partially-masked graph."},"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":"2201.02534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T16:48:07Z","cross_cats_sorted":["cs.IR","cs.SI"],"title_canon_sha256":"b94dbee5608198b0e007b978c193591fe0baf12b36c17e133df0a853320c4da1","abstract_canon_sha256":"cc080aa2d857946e04887c79252d1dc7c150e97091be26a45fe718ce7e2f5b4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:41.992322Z","signature_b64":"jjMqu4IvsAGwJQmEPUFpV3Lg9GibYrhxW/QdXG7gvltEkt4G/haC+g2q3VMjmJC/HgaCRsbehmJ9VzrYraDzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab20048926f231a2617aecfcc253b5845a1679bb27073445953a10d60b7b0d3b","last_reissued_at":"2026-07-05T03:46:41.991889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:41.991889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.SI"],"primary_cat":"cs.LG","authors_text":"Ninghao Liu, Qiaoyu Tan, Rui Chen, Soo-Hyun Choi, Xia Hu, Xiao Huang","submitted_at":"2022-01-07T16:48:07Z","abstract_excerpt":"We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these missing edges during training. MGAE has two core designs. First, we find that masking a high ratio of the input graph structure, e.g., $70\\%$, yields a nontrivial and meaningful self-supervisory task that benefits downstream applications. Second, we employ a graph neural network (GNN) as an encoder to perform message propagation on the partially-masked graph."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02534","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/2201.02534/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":"2201.02534","created_at":"2026-07-05T03:46:41.991946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02534v1","created_at":"2026-07-05T03:46:41.991946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02534","created_at":"2026-07-05T03:46:41.991946+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMQAJCJG6IY2","created_at":"2026-07-05T03:46:41.991946+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMQAJCJG6IY2EYL2","created_at":"2026-07-05T03:46:41.991946+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMQAJCJG","created_at":"2026-07-05T03:46:41.991946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.13471","citing_title":"Disentangled Generative Graph Representation Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01542","citing_title":"Mesh Based Simulations with Spatial and Temporal awareness","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR","json":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR.json","graph_json":"https://pith.science/api/pith-number/VMQAJCJG6IY2EYL25T6MEU5VQR/graph.json","events_json":"https://pith.science/api/pith-number/VMQAJCJG6IY2EYL25T6MEU5VQR/events.json","paper":"https://pith.science/paper/VMQAJCJG"},"agent_actions":{"view_html":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR","download_json":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR.json","view_paper":"https://pith.science/paper/VMQAJCJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02534&json=true","fetch_graph":"https://pith.science/api/pith-number/VMQAJCJG6IY2EYL25T6MEU5VQR/graph.json","fetch_events":"https://pith.science/api/pith-number/VMQAJCJG6IY2EYL25T6MEU5VQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR/action/storage_attestation","attest_author":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR/action/author_attestation","sign_citation":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR/action/citation_signature","submit_replication":"https://pith.science/pith/VMQAJCJG6IY2EYL25T6MEU5VQR/action/replication_record"}},"created_at":"2026-07-05T03:46:41.991946+00:00","updated_at":"2026-07-05T03:46:41.991946+00:00"}