{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:53KSBEAEL7RGIEOVOCJAMNNSTL","short_pith_number":"pith:53KSBEAE","canonical_record":{"source":{"id":"1808.06088","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-18T14:30:57Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3223a79c0daa3b97fd079ae74123499c91c8fe24a64bd8de517a2c8544f5bcbc","abstract_canon_sha256":"2ce6193d5c762d8ae7df8e693ee3b0fd43633d71d1037eabaf1e67a864812415"},"schema_version":"1.0"},"canonical_sha256":"eed52090045fe26411d570920635b29ace8c2d85f3b4a666934ed42cc5987eab","source":{"kind":"arxiv","id":"1808.06088","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.06088","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"1808.06088v3","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06088","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"53KSBEAEL7RG","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"53KSBEAEL7RGIEOV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"53KSBEAE","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:53KSBEAEL7RGIEOVOCJAMNNSTL","target":"record","payload":{"canonical_record":{"source":{"id":"1808.06088","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-18T14:30:57Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3223a79c0daa3b97fd079ae74123499c91c8fe24a64bd8de517a2c8544f5bcbc","abstract_canon_sha256":"2ce6193d5c762d8ae7df8e693ee3b0fd43633d71d1037eabaf1e67a864812415"},"schema_version":"1.0"},"canonical_sha256":"eed52090045fe26411d570920635b29ace8c2d85f3b4a666934ed42cc5987eab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:24.242362Z","signature_b64":"MV8LeK0MbxHo1ygUD2+ZL5qi1bk+nJC24MJR2UWn4Z0abFBTD1Q9DJM0y+rLpb5Jz+G/l+ht/ZLOJ4exWlHABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eed52090045fe26411d570920635b29ace8c2d85f3b4a666934ed42cc5987eab","last_reissued_at":"2026-05-17T23:52:24.241733Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:24.241733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.06088","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iVWSYZTyn5OtTbDe9s0JB5A9HfJ03rrJfeNGt1khB/QNExWlOUU6IIGWVmQNHdaxs7brkKN5vPHCZxOs40o0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:04:53.531329Z"},"content_sha256":"ddf145b835bfb77e2d01e17f7b993e69023d321727ab529df0f1e702a35c7aa3","schema_version":"1.0","event_id":"sha256:ddf145b835bfb77e2d01e17f7b993e69023d321727ab529df0f1e702a35c7aa3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:53KSBEAEL7RGIEOVOCJAMNNSTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tangent-Normal Adversarial Regularization for Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bing Yu, Jingfeng Wu, Jinwen Ma, Zhanxing Zhu","submitted_at":"2018-08-18T14:30:57Z","abstract_excerpt":"Compared with standard supervised learning, the key difficulty in semi-supervised learning is how to make full use of the unlabeled data. A recently proposed method, virtual adversarial training (VAT), smartly performs adversarial training without label information to impose a local smoothness on the classifier, which is especially beneficial to semi-supervised learning. In this work, we propose tangent-normal adversarial regularization (TNAR) as an extension of VAT by taking the data manifold into consideration. The proposed TNAR is composed by two complementary parts, the tangent adversarial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06088","kind":"arxiv","version":3},"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":"2026-05-17T23:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MAOnS4wAYk+ZfsdGiQY4XmuULrNcqe7errOIfbE8UE6Shu4abRwNq+HiEnSSdlFKSAZU9Fls49kDuDkMXKG/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:04:53.531683Z"},"content_sha256":"95e88675ab93461eb8ac2bf2ce70eab81ac5828056d43d41f97f623ee2f7abbe","schema_version":"1.0","event_id":"sha256:95e88675ab93461eb8ac2bf2ce70eab81ac5828056d43d41f97f623ee2f7abbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53KSBEAEL7RGIEOVOCJAMNNSTL/bundle.json","state_url":"https://pith.science/pith/53KSBEAEL7RGIEOVOCJAMNNSTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53KSBEAEL7RGIEOVOCJAMNNSTL/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":"2026-06-02T22:04:53Z","links":{"resolver":"https://pith.science/pith/53KSBEAEL7RGIEOVOCJAMNNSTL","bundle":"https://pith.science/pith/53KSBEAEL7RGIEOVOCJAMNNSTL/bundle.json","state":"https://pith.science/pith/53KSBEAEL7RGIEOVOCJAMNNSTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53KSBEAEL7RGIEOVOCJAMNNSTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:53KSBEAEL7RGIEOVOCJAMNNSTL","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":"2ce6193d5c762d8ae7df8e693ee3b0fd43633d71d1037eabaf1e67a864812415","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-18T14:30:57Z","title_canon_sha256":"3223a79c0daa3b97fd079ae74123499c91c8fe24a64bd8de517a2c8544f5bcbc"},"schema_version":"1.0","source":{"id":"1808.06088","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.06088","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"1808.06088v3","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06088","created_at":"2026-05-17T23:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"53KSBEAEL7RG","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"53KSBEAEL7RGIEOV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"53KSBEAE","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:95e88675ab93461eb8ac2bf2ce70eab81ac5828056d43d41f97f623ee2f7abbe","target":"graph","created_at":"2026-05-17T23:52:24Z","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":"Compared with standard supervised learning, the key difficulty in semi-supervised learning is how to make full use of the unlabeled data. A recently proposed method, virtual adversarial training (VAT), smartly performs adversarial training without label information to impose a local smoothness on the classifier, which is especially beneficial to semi-supervised learning. In this work, we propose tangent-normal adversarial regularization (TNAR) as an extension of VAT by taking the data manifold into consideration. The proposed TNAR is composed by two complementary parts, the tangent adversarial","authors_text":"Bing Yu, Jingfeng Wu, Jinwen Ma, Zhanxing Zhu","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-18T14:30:57Z","title":"Tangent-Normal Adversarial Regularization for Semi-supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06088","kind":"arxiv","version":3},"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:ddf145b835bfb77e2d01e17f7b993e69023d321727ab529df0f1e702a35c7aa3","target":"record","created_at":"2026-05-17T23:52:24Z","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":"2ce6193d5c762d8ae7df8e693ee3b0fd43633d71d1037eabaf1e67a864812415","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-18T14:30:57Z","title_canon_sha256":"3223a79c0daa3b97fd079ae74123499c91c8fe24a64bd8de517a2c8544f5bcbc"},"schema_version":"1.0","source":{"id":"1808.06088","kind":"arxiv","version":3}},"canonical_sha256":"eed52090045fe26411d570920635b29ace8c2d85f3b4a666934ed42cc5987eab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eed52090045fe26411d570920635b29ace8c2d85f3b4a666934ed42cc5987eab","first_computed_at":"2026-05-17T23:52:24.241733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:24.241733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MV8LeK0MbxHo1ygUD2+ZL5qi1bk+nJC24MJR2UWn4Z0abFBTD1Q9DJM0y+rLpb5Jz+G/l+ht/ZLOJ4exWlHABw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:24.242362Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.06088","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddf145b835bfb77e2d01e17f7b993e69023d321727ab529df0f1e702a35c7aa3","sha256:95e88675ab93461eb8ac2bf2ce70eab81ac5828056d43d41f97f623ee2f7abbe"],"state_sha256":"78b4f2a35ec5c3de53143862d3fff5f59bbd595bfb4031204b6c70e5133d338d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eOoZrXVYq1wbQYVJGKJCyrYObx4EIQLtlIQspSh0WTrfbpNH67zfi0DjaCm5wdPbTFofeU/Uc4aYFTccwPhTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:04:53.533755Z","bundle_sha256":"5332988a1fde8f078d3d0a1eae730382827abebdde313d8d16d55b5c809e680a"}}