{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7POQDGZ6VY2D7JQEITUQO32C4L","short_pith_number":"pith:7POQDGZ6","canonical_record":{"source":{"id":"1902.09192","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-25T10:57:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5ca0db5c910fec6bf7900466d7da1af3bd9572b49111c8a399525b4e1c88044d","abstract_canon_sha256":"7367fdc1da41022540653b8035016e54cf11f088987e930e9d924ad894c40a27"},"schema_version":"1.0"},"canonical_sha256":"fbdd019b3eae343fa60444e9076f42e2f2aca28f70fe4758d316b19dea221cbe","source":{"kind":"arxiv","id":"1902.09192","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09192","created_at":"2026-05-17T23:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09192v2","created_at":"2026-05-17T23:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09192","created_at":"2026-05-17T23:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"7POQDGZ6VY2D","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7POQDGZ6VY2D7JQE","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7POQDGZ6","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7POQDGZ6VY2D7JQEITUQO32C4L","target":"record","payload":{"canonical_record":{"source":{"id":"1902.09192","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-25T10:57:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5ca0db5c910fec6bf7900466d7da1af3bd9572b49111c8a399525b4e1c88044d","abstract_canon_sha256":"7367fdc1da41022540653b8035016e54cf11f088987e930e9d924ad894c40a27"},"schema_version":"1.0"},"canonical_sha256":"fbdd019b3eae343fa60444e9076f42e2f2aca28f70fe4758d316b19dea221cbe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:14.810535Z","signature_b64":"aeyYubiM7grlZvjKZ3HeIn6XsC6WggNRfZGe10xOSlMhRlSsJipmcFhv2J838RqNYOmOtSrU+ooxvyNzJILTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbdd019b3eae343fa60444e9076f42e2f2aca28f70fe4758d316b19dea221cbe","last_reissued_at":"2026-05-17T23:45:14.810033Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:14.810033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.09192","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgcHMw/8shzO4MVsGu1/kgtAllq/PsG5SwXOYfbyuGMz6dRCiXA+Q7KDY5L6HAZ8cQw6AbmbBGgJAmwKI4fWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T19:41:33.981995Z"},"content_sha256":"921f5ffb5bb607489933915290d5ca33825878f40f566d5999ac40ecc17e8aa9","schema_version":"1.0","event_id":"sha256:921f5ffb5bb607489933915290d5ca33825878f40f566d5999ac40ecc17e8aa9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7POQDGZ6VY2D7JQEITUQO32C4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Batch Virtual Adversarial Training for Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jun Zhu, Yinpeng Dong, Zhijie Deng","submitted_at":"2019-02-25T10:57:43Z","abstract_excerpt":"We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09192","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1/xg2T4Vig/Zxbp0awury3IcBPG+NvivX1+9b2+pTxl7GbkkFOhcCC/GOlbcnU4kUriyy5ED3c7qyHpjrdMVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T19:41:33.982351Z"},"content_sha256":"151f52ce50a4778bc043bf634f8783aad94fac133f05d9a9451469e321747be5","schema_version":"1.0","event_id":"sha256:151f52ce50a4778bc043bf634f8783aad94fac133f05d9a9451469e321747be5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7POQDGZ6VY2D7JQEITUQO32C4L/bundle.json","state_url":"https://pith.science/pith/7POQDGZ6VY2D7JQEITUQO32C4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7POQDGZ6VY2D7JQEITUQO32C4L/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-23T19:41:33Z","links":{"resolver":"https://pith.science/pith/7POQDGZ6VY2D7JQEITUQO32C4L","bundle":"https://pith.science/pith/7POQDGZ6VY2D7JQEITUQO32C4L/bundle.json","state":"https://pith.science/pith/7POQDGZ6VY2D7JQEITUQO32C4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7POQDGZ6VY2D7JQEITUQO32C4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7POQDGZ6VY2D7JQEITUQO32C4L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7367fdc1da41022540653b8035016e54cf11f088987e930e9d924ad894c40a27","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-25T10:57:43Z","title_canon_sha256":"5ca0db5c910fec6bf7900466d7da1af3bd9572b49111c8a399525b4e1c88044d"},"schema_version":"1.0","source":{"id":"1902.09192","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09192","created_at":"2026-05-17T23:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09192v2","created_at":"2026-05-17T23:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09192","created_at":"2026-05-17T23:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"7POQDGZ6VY2D","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7POQDGZ6VY2D7JQE","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7POQDGZ6","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:151f52ce50a4778bc043bf634f8783aad94fac133f05d9a9451469e321747be5","target":"graph","created_at":"2026-05-17T23:45:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with ","authors_text":"Jun Zhu, Yinpeng Dong, Zhijie Deng","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-25T10:57:43Z","title":"Batch Virtual Adversarial Training for Graph Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09192","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:921f5ffb5bb607489933915290d5ca33825878f40f566d5999ac40ecc17e8aa9","target":"record","created_at":"2026-05-17T23:45:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7367fdc1da41022540653b8035016e54cf11f088987e930e9d924ad894c40a27","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-25T10:57:43Z","title_canon_sha256":"5ca0db5c910fec6bf7900466d7da1af3bd9572b49111c8a399525b4e1c88044d"},"schema_version":"1.0","source":{"id":"1902.09192","kind":"arxiv","version":2}},"canonical_sha256":"fbdd019b3eae343fa60444e9076f42e2f2aca28f70fe4758d316b19dea221cbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbdd019b3eae343fa60444e9076f42e2f2aca28f70fe4758d316b19dea221cbe","first_computed_at":"2026-05-17T23:45:14.810033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:14.810033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aeyYubiM7grlZvjKZ3HeIn6XsC6WggNRfZGe10xOSlMhRlSsJipmcFhv2J838RqNYOmOtSrU+ooxvyNzJILTCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:14.810535Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09192","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:921f5ffb5bb607489933915290d5ca33825878f40f566d5999ac40ecc17e8aa9","sha256:151f52ce50a4778bc043bf634f8783aad94fac133f05d9a9451469e321747be5"],"state_sha256":"dbbb1095324bc8c4aacffbd83e611bd1a670e915e71a504da83288092edd8048"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUbzzrTa9QiVIjJ0Hl2DH1NMq5ii7WkzpsaRfZpleSed1X4ChX7t8Rpp6QPh1Qg+RbfRWgLBMYwvyvBPzkmtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T19:41:33.984282Z","bundle_sha256":"d7f1838c51e7876516fa2aa026d4c0ab26d1057574b88f6b9726070fcad6224c"}}