{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DBAY2KE7ZG4SN2LVA4W7CJ52ZO","short_pith_number":"pith:DBAY2KE7","canonical_record":{"source":{"id":"1905.11713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T10:01:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90d558f0aad03bce5d57abde31e8a01f9f4d07df1f9fe11dcce2a5b42d107e6d","abstract_canon_sha256":"e4a321bb4945746b18e50d11220f107e92873255b6c8da7745bd32c59805d4e1"},"schema_version":"1.0"},"canonical_sha256":"18418d289fc9b926e975072df127bacbbbbd44ab43c73487732e6be566eed966","source":{"kind":"arxiv","id":"1905.11713","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11713","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11713v1","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11713","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"pith_short_12","alias_value":"DBAY2KE7ZG4S","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DBAY2KE7ZG4SN2LV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DBAY2KE7","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DBAY2KE7ZG4SN2LVA4W7CJ52ZO","target":"record","payload":{"canonical_record":{"source":{"id":"1905.11713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T10:01:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90d558f0aad03bce5d57abde31e8a01f9f4d07df1f9fe11dcce2a5b42d107e6d","abstract_canon_sha256":"e4a321bb4945746b18e50d11220f107e92873255b6c8da7745bd32c59805d4e1"},"schema_version":"1.0"},"canonical_sha256":"18418d289fc9b926e975072df127bacbbbbd44ab43c73487732e6be566eed966","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:52.536565Z","signature_b64":"evzIohigyahztsxTlJZrfXtes0s4+xO1JCSnS/oPI/ilWU5dSqwUvZoR/Y+Nm7QKI7CHavrXzlJHWMIefb9dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18418d289fc9b926e975072df127bacbbbbd44ab43c73487732e6be566eed966","last_reissued_at":"2026-05-17T23:44:52.535900Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:52.535900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.11713","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNLQ74MPFnhU/UXIIni6/uq4DSfBq+7rDN7EXktLnOQyFFRHu0g/dChwO8ImlLytrJdxJQELXN9WDAABFtXlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:40:38.779969Z"},"content_sha256":"3e17301ed28a10638d8a3edb24004ff78499b940c7b1074707975094d5a30155","schema_version":"1.0","event_id":"sha256:3e17301ed28a10638d8a3edb24004ff78499b940c7b1074707975094d5a30155"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DBAY2KE7ZG4SN2LVA4W7CJ52ZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bowen Zhou, Jinfeng Yi, Lijun Zhang, Pengcheng Li","submitted_at":"2019-05-28T10:01:24Z","abstract_excerpt":"Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate Triplet Loss, one of the most popular Distance Metric Learning methods, into the framework of adversarial training. Our proposed algorithm, Adversarial Training with Triplet Loss (AT$^2$L), substitutes the adversarial example against the current model for the anchor of triplet loss to effectively smooth the classification boundary. Furthermore, we propose an ens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11713","kind":"arxiv","version":1},"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":"2026-05-17T23:44:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iIhuyYIplwTJb6fzAbLajngRVB5ws+EI7hx/m+DLbb0vTb+Y5srdTS4f8A31kJwf+9tw3BkzOdyZcyk0XoZ/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:40:38.780648Z"},"content_sha256":"a44e52b8ab748c82b848f8557a2192adb1fd35a8f771bd51fcd536ca386fd60b","schema_version":"1.0","event_id":"sha256:a44e52b8ab748c82b848f8557a2192adb1fd35a8f771bd51fcd536ca386fd60b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBAY2KE7ZG4SN2LVA4W7CJ52ZO/bundle.json","state_url":"https://pith.science/pith/DBAY2KE7ZG4SN2LVA4W7CJ52ZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBAY2KE7ZG4SN2LVA4W7CJ52ZO/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":"2026-05-26T20:40:38Z","links":{"resolver":"https://pith.science/pith/DBAY2KE7ZG4SN2LVA4W7CJ52ZO","bundle":"https://pith.science/pith/DBAY2KE7ZG4SN2LVA4W7CJ52ZO/bundle.json","state":"https://pith.science/pith/DBAY2KE7ZG4SN2LVA4W7CJ52ZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBAY2KE7ZG4SN2LVA4W7CJ52ZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DBAY2KE7ZG4SN2LVA4W7CJ52ZO","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":"e4a321bb4945746b18e50d11220f107e92873255b6c8da7745bd32c59805d4e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T10:01:24Z","title_canon_sha256":"90d558f0aad03bce5d57abde31e8a01f9f4d07df1f9fe11dcce2a5b42d107e6d"},"schema_version":"1.0","source":{"id":"1905.11713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11713","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11713v1","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11713","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"pith_short_12","alias_value":"DBAY2KE7ZG4S","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DBAY2KE7ZG4SN2LV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DBAY2KE7","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:a44e52b8ab748c82b848f8557a2192adb1fd35a8f771bd51fcd536ca386fd60b","target":"graph","created_at":"2026-05-17T23:44:52Z","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":"Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate Triplet Loss, one of the most popular Distance Metric Learning methods, into the framework of adversarial training. Our proposed algorithm, Adversarial Training with Triplet Loss (AT$^2$L), substitutes the adversarial example against the current model for the anchor of triplet loss to effectively smooth the classification boundary. Furthermore, we propose an ens","authors_text":"Bowen Zhou, Jinfeng Yi, Lijun Zhang, Pengcheng Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T10:01:24Z","title":"Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11713","kind":"arxiv","version":1},"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":"sha256:3e17301ed28a10638d8a3edb24004ff78499b940c7b1074707975094d5a30155","target":"record","created_at":"2026-05-17T23:44:52Z","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":"e4a321bb4945746b18e50d11220f107e92873255b6c8da7745bd32c59805d4e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T10:01:24Z","title_canon_sha256":"90d558f0aad03bce5d57abde31e8a01f9f4d07df1f9fe11dcce2a5b42d107e6d"},"schema_version":"1.0","source":{"id":"1905.11713","kind":"arxiv","version":1}},"canonical_sha256":"18418d289fc9b926e975072df127bacbbbbd44ab43c73487732e6be566eed966","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18418d289fc9b926e975072df127bacbbbbd44ab43c73487732e6be566eed966","first_computed_at":"2026-05-17T23:44:52.535900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:52.535900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"evzIohigyahztsxTlJZrfXtes0s4+xO1JCSnS/oPI/ilWU5dSqwUvZoR/Y+Nm7QKI7CHavrXzlJHWMIefb9dAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:52.536565Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e17301ed28a10638d8a3edb24004ff78499b940c7b1074707975094d5a30155","sha256:a44e52b8ab748c82b848f8557a2192adb1fd35a8f771bd51fcd536ca386fd60b"],"state_sha256":"6e13ef9cdc112328cc6e684811530121595d731943ab1e9d5e7671f953fa1c42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afwGdiDKWZy1k/tY1ZYPYQCH1R7wibAhP1Rbn/7hdGJ/s132lpvdAuvrXe/QnBivKc3WtLn2TMp9GmWQHiu0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:40:38.784350Z","bundle_sha256":"716df05fdd3996f42a98912b29c1bc37ceb13a1e5d28184c751894bfc20f788d"}}