{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XY7QGPHIYZ7PRYRM66SLLD6NMS","short_pith_number":"pith:XY7QGPHI","canonical_record":{"source":{"id":"1807.05832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T13:01:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b9587c51757dd73c3e4ee72aabc0cf0f8cb9100e0f75144b1841cf3b59eb4c5c","abstract_canon_sha256":"3d53a9eea057cd50800ab12ff98104da6d0f05bf342c5184815233696df1d5ea"},"schema_version":"1.0"},"canonical_sha256":"be3f033ce8c67ef8e22cf7a4b58fcd64b08b8e8a5f1d3c3eb5b067adeb53c534","source":{"kind":"arxiv","id":"1807.05832","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05832","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05832v2","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05832","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"XY7QGPHIYZ7P","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"XY7QGPHIYZ7PRYRM","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"XY7QGPHI","created_at":"2026-07-05T00:19:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XY7QGPHIYZ7PRYRM66SLLD6NMS","target":"record","payload":{"canonical_record":{"source":{"id":"1807.05832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T13:01:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b9587c51757dd73c3e4ee72aabc0cf0f8cb9100e0f75144b1841cf3b59eb4c5c","abstract_canon_sha256":"3d53a9eea057cd50800ab12ff98104da6d0f05bf342c5184815233696df1d5ea"},"schema_version":"1.0"},"canonical_sha256":"be3f033ce8c67ef8e22cf7a4b58fcd64b08b8e8a5f1d3c3eb5b067adeb53c534","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:06.071896Z","signature_b64":"CnObqiILaFOWiuDuO9Zg6VQEIpIiIVW+AVrhRc8tT4lwwKeh4zaDWSu+/JZlThcZdiFu7aCG01UaGB6znLRbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be3f033ce8c67ef8e22cf7a4b58fcd64b08b8e8a5f1d3c3eb5b067adeb53c534","last_reissued_at":"2026-07-05T00:19:06.071530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:06.071530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.05832","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":"2026-07-05T00:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7wtSayGASag6czzNGL5Lx9Y4yrKgMyEYRI62fSe+MyQ2M2AtjPHYrq2KtC/Ef8J/OBdQXO78y5puS1m8YfdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:39:48.920468Z"},"content_sha256":"b33dad0b04a2bdda4926ff05aef115abca9c11b8d0470a578685273dcbd0018c","schema_version":"1.0","event_id":"sha256:b33dad0b04a2bdda4926ff05aef115abca9c11b8d0470a578685273dcbd0018c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XY7QGPHIYZ7PRYRM66SLLD6NMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Manifold Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianke Zhu, Kaizhu Huang, Shufei Zhang, Yang Liu","submitted_at":"2018-07-16T13:01:41Z","abstract_excerpt":"Recently proposed adversarial training methods show the robustness to both adversarial and original examples and achieve state-of-the-art results in supervised and semi-supervised learning. All the existing adversarial training methods consider only how the worst perturbed examples (i.e., adversarial examples) could affect the model output. Despite their success, we argue that such setting may be in lack of generalization, since the output space (or label space) is apparently less informative.In this paper, we propose a novel method, called Manifold Adversarial Training (MAT). MAT manages to b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05832","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1807.05832/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJN41oCPHWeHz68SZNF1+tYMXEtBL69VeiDiA79b5hH/tnYYfHmAuHPJzVWQaNA8wdyAgycKhViyeAoLnUXGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:39:48.920843Z"},"content_sha256":"d49881c1a47d0e36545d2069321183646fc40aa6c26ec46d5aa978cff549cb9d","schema_version":"1.0","event_id":"sha256:d49881c1a47d0e36545d2069321183646fc40aa6c26ec46d5aa978cff549cb9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XY7QGPHIYZ7PRYRM66SLLD6NMS/bundle.json","state_url":"https://pith.science/pith/XY7QGPHIYZ7PRYRM66SLLD6NMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XY7QGPHIYZ7PRYRM66SLLD6NMS/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":"2026-07-07T14:39:48Z","links":{"resolver":"https://pith.science/pith/XY7QGPHIYZ7PRYRM66SLLD6NMS","bundle":"https://pith.science/pith/XY7QGPHIYZ7PRYRM66SLLD6NMS/bundle.json","state":"https://pith.science/pith/XY7QGPHIYZ7PRYRM66SLLD6NMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XY7QGPHIYZ7PRYRM66SLLD6NMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XY7QGPHIYZ7PRYRM66SLLD6NMS","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":"3d53a9eea057cd50800ab12ff98104da6d0f05bf342c5184815233696df1d5ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T13:01:41Z","title_canon_sha256":"b9587c51757dd73c3e4ee72aabc0cf0f8cb9100e0f75144b1841cf3b59eb4c5c"},"schema_version":"1.0","source":{"id":"1807.05832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05832","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05832v2","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05832","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"XY7QGPHIYZ7P","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"XY7QGPHIYZ7PRYRM","created_at":"2026-07-05T00:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"XY7QGPHI","created_at":"2026-07-05T00:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:d49881c1a47d0e36545d2069321183646fc40aa6c26ec46d5aa978cff549cb9d","target":"graph","created_at":"2026-07-05T00:19:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1807.05832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently proposed adversarial training methods show the robustness to both adversarial and original examples and achieve state-of-the-art results in supervised and semi-supervised learning. All the existing adversarial training methods consider only how the worst perturbed examples (i.e., adversarial examples) could affect the model output. Despite their success, we argue that such setting may be in lack of generalization, since the output space (or label space) is apparently less informative.In this paper, we propose a novel method, called Manifold Adversarial Training (MAT). MAT manages to b","authors_text":"Jianke Zhu, Kaizhu Huang, Shufei Zhang, Yang Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T13:01:41Z","title":"Manifold Adversarial Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05832","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:b33dad0b04a2bdda4926ff05aef115abca9c11b8d0470a578685273dcbd0018c","target":"record","created_at":"2026-07-05T00:19:06Z","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":"3d53a9eea057cd50800ab12ff98104da6d0f05bf342c5184815233696df1d5ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T13:01:41Z","title_canon_sha256":"b9587c51757dd73c3e4ee72aabc0cf0f8cb9100e0f75144b1841cf3b59eb4c5c"},"schema_version":"1.0","source":{"id":"1807.05832","kind":"arxiv","version":2}},"canonical_sha256":"be3f033ce8c67ef8e22cf7a4b58fcd64b08b8e8a5f1d3c3eb5b067adeb53c534","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be3f033ce8c67ef8e22cf7a4b58fcd64b08b8e8a5f1d3c3eb5b067adeb53c534","first_computed_at":"2026-07-05T00:19:06.071530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:19:06.071530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CnObqiILaFOWiuDuO9Zg6VQEIpIiIVW+AVrhRc8tT4lwwKeh4zaDWSu+/JZlThcZdiFu7aCG01UaGB6znLRbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:19:06.071896Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b33dad0b04a2bdda4926ff05aef115abca9c11b8d0470a578685273dcbd0018c","sha256:d49881c1a47d0e36545d2069321183646fc40aa6c26ec46d5aa978cff549cb9d"],"state_sha256":"cfd7c547e537c4115be00cce80acc90c7e0eb4dc5976872280a6e8dd431d30af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r8gO+uI8eMZtdRuaTGkM4/o5izdEDgzZvFoCxPQEVBLOTX5bIS6KEmFGG532j+dZqHe4ftC6Kopp+JQY7QsADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:39:48.922742Z","bundle_sha256":"36fa01db56cba90ef495cfea0e4787b54919e2517d250bb29973ad8e75e3c8c0"}}