{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YAO2ONLTWIT5MXZ2GZJNDTC42R","short_pith_number":"pith:YAO2ONLT","schema_version":"1.0","canonical_sha256":"c01da73573b227d65f3a3652d1cc5cd47ad6ec69085b6b0520673ea187ae1363","source":{"kind":"arxiv","id":"2304.01507","version":2},"attestation_state":"computed","paper":{"title":"RARE: Robust Masked Graph Autoencoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuan Ma, Qing Liao, Sihang Zhou, Wenxuan Tu, Xin Peng, Xinwang Liu, Zhe Liu, Zhiping Cai","submitted_at":"2023-04-04T03:35:29Z","abstract_excerpt":"Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important non-Euclidean property of graph data. As a result, the highly unstable local connection structures largely increase the uncertainty in inferring masked data and decrease the reliability of the exploited self-supervision signals, leading to inferio"},"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":"2304.01507","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-04T03:35:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7857437d6039db1d0a5316140d5bfcde558d72c82ecc2c6835516f4ece5d0dd","abstract_canon_sha256":"6677d1fcd37bbca6a3be95af12c405f3e71060e01a217f56939eb67d069c255a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:42.028609Z","signature_b64":"7JBknGcYOFxEISv+198NlyC1uRdKtSaBrGt1TZVGscBo8UxZksZRsfWDiwn24d0iydoqto6+yxND6xsrem/RBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c01da73573b227d65f3a3652d1cc5cd47ad6ec69085b6b0520673ea187ae1363","last_reissued_at":"2026-07-05T05:58:42.028165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:42.028165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RARE: Robust Masked Graph Autoencoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuan Ma, Qing Liao, Sihang Zhou, Wenxuan Tu, Xin Peng, Xinwang Liu, Zhe Liu, Zhiping Cai","submitted_at":"2023-04-04T03:35:29Z","abstract_excerpt":"Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important non-Euclidean property of graph data. As a result, the highly unstable local connection structures largely increase the uncertainty in inferring masked data and decrease the reliability of the exploited self-supervision signals, leading to inferio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01507","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/2304.01507/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":"2304.01507","created_at":"2026-07-05T05:58:42.028225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01507v2","created_at":"2026-07-05T05:58:42.028225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01507","created_at":"2026-07-05T05:58:42.028225+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAO2ONLTWIT5","created_at":"2026-07-05T05:58:42.028225+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAO2ONLTWIT5MXZ2","created_at":"2026-07-05T05:58:42.028225+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAO2ONLT","created_at":"2026-07-05T05:58:42.028225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.13471","citing_title":"Disentangled Generative Graph Representation Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R","json":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R.json","graph_json":"https://pith.science/api/pith-number/YAO2ONLTWIT5MXZ2GZJNDTC42R/graph.json","events_json":"https://pith.science/api/pith-number/YAO2ONLTWIT5MXZ2GZJNDTC42R/events.json","paper":"https://pith.science/paper/YAO2ONLT"},"agent_actions":{"view_html":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R","download_json":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R.json","view_paper":"https://pith.science/paper/YAO2ONLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01507&json=true","fetch_graph":"https://pith.science/api/pith-number/YAO2ONLTWIT5MXZ2GZJNDTC42R/graph.json","fetch_events":"https://pith.science/api/pith-number/YAO2ONLTWIT5MXZ2GZJNDTC42R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R/action/storage_attestation","attest_author":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R/action/author_attestation","sign_citation":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R/action/citation_signature","submit_replication":"https://pith.science/pith/YAO2ONLTWIT5MXZ2GZJNDTC42R/action/replication_record"}},"created_at":"2026-07-05T05:58:42.028225+00:00","updated_at":"2026-07-05T05:58:42.028225+00:00"}