{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:B76JOX7XXX6EETPA6L5OCBDWMZ","short_pith_number":"pith:B76JOX7X","schema_version":"1.0","canonical_sha256":"0ffc975ff7bdfc424de0f2fae10476667aea293401ce45e68da53e93856da55d","source":{"kind":"arxiv","id":"2205.10053","version":2},"attestation_state":"computed","paper":{"title":"What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhua Meng, Jintang Li, Liang Chen, Liang Zhu, Ruofan Wu, Sheng Tian, Wangbin Sun, Weiqiang Wang, Zibin Zheng","submitted_at":"2022-05-20T09:45:57Z","abstract_excerpt":"The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph autoencoders (GAEs). In this work, we present masked graph autoencoder (MaskGAE), a self-supervised learning framework for graph-structured data. Different from standard GAEs, MaskGAE adopts masked graph modeling (MGM) as a principled pretext task - masking a portion of edges and attempting to reconstruct the missing part with partially visible, unmasked graph structure. To underst"},"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":"2205.10053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T09:45:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64ff9f90e99995b3187930aae0e0ced62bb46600b219b8175dea2e746766986b","abstract_canon_sha256":"b72cbbf1b9ea84690dafe1e485122a01261831cc9541193a9f778d7eda1c9303"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:34.785334Z","signature_b64":"iRlCvcSjfqjphHE9BKUo7zoxkKik4ltCuikAMaFtfB+GIj7nL5wq+j4mTdZaqKEZa6U6R2ug7ZhZf9ODZzH6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ffc975ff7bdfc424de0f2fae10476667aea293401ce45e68da53e93856da55d","last_reissued_at":"2026-07-05T06:14:34.784781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:34.784781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhua Meng, Jintang Li, Liang Chen, Liang Zhu, Ruofan Wu, Sheng Tian, Wangbin Sun, Weiqiang Wang, Zibin Zheng","submitted_at":"2022-05-20T09:45:57Z","abstract_excerpt":"The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph autoencoders (GAEs). In this work, we present masked graph autoencoder (MaskGAE), a self-supervised learning framework for graph-structured data. Different from standard GAEs, MaskGAE adopts masked graph modeling (MGM) as a principled pretext task - masking a portion of edges and attempting to reconstruct the missing part with partially visible, unmasked graph structure. To underst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10053","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/2205.10053/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":"2205.10053","created_at":"2026-07-05T06:14:34.784840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10053v2","created_at":"2026-07-05T06:14:34.784840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10053","created_at":"2026-07-05T06:14:34.784840+00:00"},{"alias_kind":"pith_short_12","alias_value":"B76JOX7XXX6E","created_at":"2026-07-05T06:14:34.784840+00:00"},{"alias_kind":"pith_short_16","alias_value":"B76JOX7XXX6EETPA","created_at":"2026-07-05T06:14:34.784840+00:00"},{"alias_kind":"pith_short_8","alias_value":"B76JOX7X","created_at":"2026-07-05T06:14:34.784840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ","json":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ.json","graph_json":"https://pith.science/api/pith-number/B76JOX7XXX6EETPA6L5OCBDWMZ/graph.json","events_json":"https://pith.science/api/pith-number/B76JOX7XXX6EETPA6L5OCBDWMZ/events.json","paper":"https://pith.science/paper/B76JOX7X"},"agent_actions":{"view_html":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ","download_json":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ.json","view_paper":"https://pith.science/paper/B76JOX7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10053&json=true","fetch_graph":"https://pith.science/api/pith-number/B76JOX7XXX6EETPA6L5OCBDWMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/B76JOX7XXX6EETPA6L5OCBDWMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ/action/storage_attestation","attest_author":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ/action/author_attestation","sign_citation":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ/action/citation_signature","submit_replication":"https://pith.science/pith/B76JOX7XXX6EETPA6L5OCBDWMZ/action/replication_record"}},"created_at":"2026-07-05T06:14:34.784840+00:00","updated_at":"2026-07-05T06:14:34.784840+00:00"}