{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4HG5NAJV6M6OTJB4PUDNKMCYNF","short_pith_number":"pith:4HG5NAJV","canonical_record":{"source":{"id":"1704.03976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-13T02:45:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19e3dbf29d3e12c6074938e5998ff2e2d729db57c51c432371c888ed08391783","abstract_canon_sha256":"c921b62d4b5914f0f565b6c72b1f351cfbf0c52448edd88b101698bff43c042a"},"schema_version":"1.0"},"canonical_sha256":"e1cdd68135f33ce9a43c7d06d5305869617cf8a59000d0f631408d5a59292ed1","source":{"kind":"arxiv","id":"1704.03976","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03976","created_at":"2026-05-18T00:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03976v2","created_at":"2026-05-18T00:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03976","created_at":"2026-05-18T00:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"4HG5NAJV6M6O","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4HG5NAJV6M6OTJB4","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4HG5NAJV","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4HG5NAJV6M6OTJB4PUDNKMCYNF","target":"record","payload":{"canonical_record":{"source":{"id":"1704.03976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-13T02:45:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19e3dbf29d3e12c6074938e5998ff2e2d729db57c51c432371c888ed08391783","abstract_canon_sha256":"c921b62d4b5914f0f565b6c72b1f351cfbf0c52448edd88b101698bff43c042a"},"schema_version":"1.0"},"canonical_sha256":"e1cdd68135f33ce9a43c7d06d5305869617cf8a59000d0f631408d5a59292ed1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:14.327379Z","signature_b64":"gQ6hULWk8KtZcVfKbgrE3rU2qudlEsCEcG5MgXSWCYWwkNg0R2DyiDECXG37EV84hMuxXgghfIhjkcnBE4zhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1cdd68135f33ce9a43c7d06d5305869617cf8a59000d0f631408d5a59292ed1","last_reissued_at":"2026-05-18T00:12:14.326852Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:14.326852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.03976","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":"2026-05-18T00:12:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6NZH74RE9i+OR3sFcStQoB7dZ9E3dr3Bwl5U2NuMJmsPyYv95of1k504wI9bKcPRAUxM6Il1rNauLDfnzeImAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:44:54.631502Z"},"content_sha256":"23ad8f5b74c95b28d74cd67059760f3e53b90efe83159012876e77cc6a93731f","schema_version":"1.0","event_id":"sha256:23ad8f5b74c95b28d74cd67059760f3e53b90efe83159012876e77cc6a93731f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4HG5NAJV6M6OTJB4PUDNKMCYNF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Masanori Koyama, Shin-ichi Maeda, Shin Ishii, Takeru Miyato","submitted_at":"2017-04-13T02:45:27Z","abstract_excerpt":"We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adversarial training, our method defines the adversarial direction without label information and is hence applicable to semi-supervised learning. Because the directions in which we smooth the model are only \"virtually\" adversarial, we call our method virtual adversarial training (VAT)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03976","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":"2026-05-18T00:12:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IAfXCmaNIs/BlHJODfFSRVp5KdR/BZSgN6Ujtd9cjvluHxEBY8LAUzbgG4p8AOBcLLUM1z93gVDbNePinIMSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:44:54.632229Z"},"content_sha256":"f56b58c48d5a13dac15607b70497cf1d07429974998390b31c4c3c206333f91f","schema_version":"1.0","event_id":"sha256:f56b58c48d5a13dac15607b70497cf1d07429974998390b31c4c3c206333f91f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HG5NAJV6M6OTJB4PUDNKMCYNF/bundle.json","state_url":"https://pith.science/pith/4HG5NAJV6M6OTJB4PUDNKMCYNF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HG5NAJV6M6OTJB4PUDNKMCYNF/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":"2026-05-25T20:44:54Z","links":{"resolver":"https://pith.science/pith/4HG5NAJV6M6OTJB4PUDNKMCYNF","bundle":"https://pith.science/pith/4HG5NAJV6M6OTJB4PUDNKMCYNF/bundle.json","state":"https://pith.science/pith/4HG5NAJV6M6OTJB4PUDNKMCYNF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HG5NAJV6M6OTJB4PUDNKMCYNF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4HG5NAJV6M6OTJB4PUDNKMCYNF","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":"c921b62d4b5914f0f565b6c72b1f351cfbf0c52448edd88b101698bff43c042a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-13T02:45:27Z","title_canon_sha256":"19e3dbf29d3e12c6074938e5998ff2e2d729db57c51c432371c888ed08391783"},"schema_version":"1.0","source":{"id":"1704.03976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03976","created_at":"2026-05-18T00:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03976v2","created_at":"2026-05-18T00:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03976","created_at":"2026-05-18T00:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"4HG5NAJV6M6O","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4HG5NAJV6M6OTJB4","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4HG5NAJV","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:f56b58c48d5a13dac15607b70497cf1d07429974998390b31c4c3c206333f91f","target":"graph","created_at":"2026-05-18T00:12:14Z","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 propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adversarial training, our method defines the adversarial direction without label information and is hence applicable to semi-supervised learning. Because the directions in which we smooth the model are only \"virtually\" adversarial, we call our method virtual adversarial training (VAT)","authors_text":"Masanori Koyama, Shin-ichi Maeda, Shin Ishii, Takeru Miyato","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-13T02:45:27Z","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03976","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":"sha256:23ad8f5b74c95b28d74cd67059760f3e53b90efe83159012876e77cc6a93731f","target":"record","created_at":"2026-05-18T00:12:14Z","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":"c921b62d4b5914f0f565b6c72b1f351cfbf0c52448edd88b101698bff43c042a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-13T02:45:27Z","title_canon_sha256":"19e3dbf29d3e12c6074938e5998ff2e2d729db57c51c432371c888ed08391783"},"schema_version":"1.0","source":{"id":"1704.03976","kind":"arxiv","version":2}},"canonical_sha256":"e1cdd68135f33ce9a43c7d06d5305869617cf8a59000d0f631408d5a59292ed1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1cdd68135f33ce9a43c7d06d5305869617cf8a59000d0f631408d5a59292ed1","first_computed_at":"2026-05-18T00:12:14.326852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:14.326852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gQ6hULWk8KtZcVfKbgrE3rU2qudlEsCEcG5MgXSWCYWwkNg0R2DyiDECXG37EV84hMuxXgghfIhjkcnBE4zhDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:14.327379Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.03976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23ad8f5b74c95b28d74cd67059760f3e53b90efe83159012876e77cc6a93731f","sha256:f56b58c48d5a13dac15607b70497cf1d07429974998390b31c4c3c206333f91f"],"state_sha256":"ce46bebd86a14bbcbcdd5bebd9bb524753534e993bef3f58e225bd86f7638177"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UXyuR/gFTUTJRFvmMMSJadR/itkQXgbCgwqC60vPgVTXH89QweOEv4FlsFebktZJ/WpKklB9bsv/j+b1HthKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:44:54.636049Z","bundle_sha256":"d624a2eb48e7f61bdde883d12f6371c6261a505ce6ad52efc4b7c3b653227801"}}