{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:XVJTRATGUMRZMUMNGQKTUXF3IR","short_pith_number":"pith:XVJTRATG","canonical_record":{"source":{"id":"1507.00677","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-02T18:01:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7d1e528b1b88b79337627cd04ddb86be707ba1a6641b7da1f09d976e573b334","abstract_canon_sha256":"16f977f57823d3957daec5fc2ccfc76beefad897974f3d4c1a1e51b2e70092ac"},"schema_version":"1.0"},"canonical_sha256":"bd53388266a32396518d34153a5cbb444ce195ca4b55f89e0300344dac49c1bb","source":{"kind":"arxiv","id":"1507.00677","version":9},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.00677","created_at":"2026-05-18T01:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"1507.00677v9","created_at":"2026-05-18T01:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00677","created_at":"2026-05-18T01:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"XVJTRATGUMRZ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XVJTRATGUMRZMUMN","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XVJTRATG","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:XVJTRATGUMRZMUMNGQKTUXF3IR","target":"record","payload":{"canonical_record":{"source":{"id":"1507.00677","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-02T18:01:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7d1e528b1b88b79337627cd04ddb86be707ba1a6641b7da1f09d976e573b334","abstract_canon_sha256":"16f977f57823d3957daec5fc2ccfc76beefad897974f3d4c1a1e51b2e70092ac"},"schema_version":"1.0"},"canonical_sha256":"bd53388266a32396518d34153a5cbb444ce195ca4b55f89e0300344dac49c1bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:36.252356Z","signature_b64":"VCXf/WrWzY+IGy+b8wWpDTRw1nclOh1uk2eisVnBoW6oqUm/Irgn7zDqwSqEsszUwjwBcY/ucdMVPTqvq2YJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd53388266a32396518d34153a5cbb444ce195ca4b55f89e0300344dac49c1bb","last_reissued_at":"2026-05-18T01:12:36.251733Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:36.251733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.00677","source_version":9,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GQ71xONMqsoQzbzoXg3PUmmvY04S70r2pVr1c1FNU9xG+we+zWRrSONWbiS2fvXt6pVBrPlDbnVAdy5LpVjmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:32:28.964094Z"},"content_sha256":"034495d2396b345536108bbefbf07b9ffd4b0bda8f330be350e6a3411fef9669","schema_version":"1.0","event_id":"sha256:034495d2396b345536108bbefbf07b9ffd4b0bda8f330be350e6a3411fef9669"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:XVJTRATGUMRZMUMNGQKTUXF3IR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributional Smoothing with Virtual Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ken Nakae, Masanori Koyama, Shin-ichi Maeda, Shin Ishii, Takeru Miyato","submitted_at":"2015-07-02T18:01:23Z","abstract_excerpt":"We propose local distributional smoothness (LDS), a new notion of smoothness for statistical model that can be used as a regularization term to promote the smoothness of the model distribution. We named the LDS based regularization as virtual adversarial training (VAT). The LDS of a model at an input datapoint is defined as the KL-divergence based robustness of the model distribution against local perturbation around the datapoint. VAT resembles adversarial training, but distinguishes itself in that it determines the adversarial direction from the model distribution alone without using the lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00677","kind":"arxiv","version":9},"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":"2026-05-18T01:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OpwgAKO+ETjfZDpd6r4V+Qw0lAHknvxyJGBsE9E4eg6o2If0LQyEL3mIbCivTKaH8GnuZc9L2jpn/06VhO2qBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:32:28.964754Z"},"content_sha256":"1b434c694d13b2138218d0c437102006010ed1dcabbb7b9f976aac432b90d58f","schema_version":"1.0","event_id":"sha256:1b434c694d13b2138218d0c437102006010ed1dcabbb7b9f976aac432b90d58f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVJTRATGUMRZMUMNGQKTUXF3IR/bundle.json","state_url":"https://pith.science/pith/XVJTRATGUMRZMUMNGQKTUXF3IR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVJTRATGUMRZMUMNGQKTUXF3IR/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":"2026-05-26T07:32:28Z","links":{"resolver":"https://pith.science/pith/XVJTRATGUMRZMUMNGQKTUXF3IR","bundle":"https://pith.science/pith/XVJTRATGUMRZMUMNGQKTUXF3IR/bundle.json","state":"https://pith.science/pith/XVJTRATGUMRZMUMNGQKTUXF3IR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVJTRATGUMRZMUMNGQKTUXF3IR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:XVJTRATGUMRZMUMNGQKTUXF3IR","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":"16f977f57823d3957daec5fc2ccfc76beefad897974f3d4c1a1e51b2e70092ac","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-02T18:01:23Z","title_canon_sha256":"d7d1e528b1b88b79337627cd04ddb86be707ba1a6641b7da1f09d976e573b334"},"schema_version":"1.0","source":{"id":"1507.00677","kind":"arxiv","version":9}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.00677","created_at":"2026-05-18T01:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"1507.00677v9","created_at":"2026-05-18T01:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00677","created_at":"2026-05-18T01:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"XVJTRATGUMRZ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XVJTRATGUMRZMUMN","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XVJTRATG","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:1b434c694d13b2138218d0c437102006010ed1dcabbb7b9f976aac432b90d58f","target":"graph","created_at":"2026-05-18T01:12:36Z","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 local distributional smoothness (LDS), a new notion of smoothness for statistical model that can be used as a regularization term to promote the smoothness of the model distribution. We named the LDS based regularization as virtual adversarial training (VAT). The LDS of a model at an input datapoint is defined as the KL-divergence based robustness of the model distribution against local perturbation around the datapoint. VAT resembles adversarial training, but distinguishes itself in that it determines the adversarial direction from the model distribution alone without using the lab","authors_text":"Ken Nakae, 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":"2015-07-02T18:01:23Z","title":"Distributional Smoothing with Virtual Adversarial Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00677","kind":"arxiv","version":9},"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":"sha256:034495d2396b345536108bbefbf07b9ffd4b0bda8f330be350e6a3411fef9669","target":"record","created_at":"2026-05-18T01:12:36Z","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":"16f977f57823d3957daec5fc2ccfc76beefad897974f3d4c1a1e51b2e70092ac","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-02T18:01:23Z","title_canon_sha256":"d7d1e528b1b88b79337627cd04ddb86be707ba1a6641b7da1f09d976e573b334"},"schema_version":"1.0","source":{"id":"1507.00677","kind":"arxiv","version":9}},"canonical_sha256":"bd53388266a32396518d34153a5cbb444ce195ca4b55f89e0300344dac49c1bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd53388266a32396518d34153a5cbb444ce195ca4b55f89e0300344dac49c1bb","first_computed_at":"2026-05-18T01:12:36.251733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:36.251733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VCXf/WrWzY+IGy+b8wWpDTRw1nclOh1uk2eisVnBoW6oqUm/Irgn7zDqwSqEsszUwjwBcY/ucdMVPTqvq2YJDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:36.252356Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.00677","source_kind":"arxiv","source_version":9}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:034495d2396b345536108bbefbf07b9ffd4b0bda8f330be350e6a3411fef9669","sha256:1b434c694d13b2138218d0c437102006010ed1dcabbb7b9f976aac432b90d58f"],"state_sha256":"51d72048e232175a5d29871f95077606d17ee2e57f7f4c7fa12fdab89d983e31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GMVetNBb5APyEzAtRgCKeMW/80hRR8yfOj6ZNJlk4wzfReeTOaxdB6htpiNKVcVZdpigATawWw7j6Yz2jjAnCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:32:28.968202Z","bundle_sha256":"2eda17e80afaf0a426df23445786be4f3212a0e6f23fe6210cd0ed324ddd2434"}}