{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TVCKG5HH4A6ILZHQCYPD4SRVK4","short_pith_number":"pith:TVCKG5HH","schema_version":"1.0","canonical_sha256":"9d44a374e7e03c85e4f0161e3e4a355728abe2aed3999d10ddd765ce2e441ae6","source":{"kind":"arxiv","id":"2203.14082","version":1},"attestation_state":"computed","paper":{"title":"Metropolis-Hastings Data Augmentation for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyeonjin Park, Hyunwoo J. Kim, Jinyoung Park, Jisu Jeong, Jung-Woo Ha, Kyung-Min Kim, Seunghun Lee, Sihyeon Kim","submitted_at":"2022-03-26T14:00:11Z","abstract_excerpt":"Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a prevalent remedy to improve the generalization ability of models in many domains. However, due to the non-Euclidean nature of data space and the dependencies between samples, designing effective augmentation on graphs is challenging. In this paper, we propose a novel framework Metropolis-Hastings Data Augmentation (MH-Aug) that draws augmented graphs from an explicit target distribution for semi-supervised learning."},"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":"2203.14082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-26T14:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"b101bc790740b14499134a070ed249de83fc83ae02de0fccbdcb85f240bbf864","abstract_canon_sha256":"8004d59c3340ec9395d5ed8d72c5be685b211c875d0875a201b77bdd574532d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:46.772361Z","signature_b64":"CTUiYDI93aomx7x7+wqfEHCKXFPnhiyvCPAb79Kz8uYCABzXKiPUmFopQChUxHLkhLtaHgzrrT+YG1rvXxV2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d44a374e7e03c85e4f0161e3e4a355728abe2aed3999d10ddd765ce2e441ae6","last_reissued_at":"2026-07-05T04:08:46.771919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:46.771919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metropolis-Hastings Data Augmentation for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyeonjin Park, Hyunwoo J. Kim, Jinyoung Park, Jisu Jeong, Jung-Woo Ha, Kyung-Min Kim, Seunghun Lee, Sihyeon Kim","submitted_at":"2022-03-26T14:00:11Z","abstract_excerpt":"Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a prevalent remedy to improve the generalization ability of models in many domains. However, due to the non-Euclidean nature of data space and the dependencies between samples, designing effective augmentation on graphs is challenging. In this paper, we propose a novel framework Metropolis-Hastings Data Augmentation (MH-Aug) that draws augmented graphs from an explicit target distribution for semi-supervised learning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14082","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/2203.14082/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":"2203.14082","created_at":"2026-07-05T04:08:46.771986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14082v1","created_at":"2026-07-05T04:08:46.771986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14082","created_at":"2026-07-05T04:08:46.771986+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVCKG5HH4A6I","created_at":"2026-07-05T04:08:46.771986+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVCKG5HH4A6ILZHQ","created_at":"2026-07-05T04:08:46.771986+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVCKG5HH","created_at":"2026-07-05T04:08:46.771986+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/TVCKG5HH4A6ILZHQCYPD4SRVK4","json":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4.json","graph_json":"https://pith.science/api/pith-number/TVCKG5HH4A6ILZHQCYPD4SRVK4/graph.json","events_json":"https://pith.science/api/pith-number/TVCKG5HH4A6ILZHQCYPD4SRVK4/events.json","paper":"https://pith.science/paper/TVCKG5HH"},"agent_actions":{"view_html":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4","download_json":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4.json","view_paper":"https://pith.science/paper/TVCKG5HH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14082&json=true","fetch_graph":"https://pith.science/api/pith-number/TVCKG5HH4A6ILZHQCYPD4SRVK4/graph.json","fetch_events":"https://pith.science/api/pith-number/TVCKG5HH4A6ILZHQCYPD4SRVK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4/action/storage_attestation","attest_author":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4/action/author_attestation","sign_citation":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4/action/citation_signature","submit_replication":"https://pith.science/pith/TVCKG5HH4A6ILZHQCYPD4SRVK4/action/replication_record"}},"created_at":"2026-07-05T04:08:46.771986+00:00","updated_at":"2026-07-05T04:08:46.771986+00:00"}