{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:P5MCRTQ355S7ZI7PG6URQFIVZ6","short_pith_number":"pith:P5MCRTQ3","canonical_record":{"source":{"id":"1710.10571","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-29T07:27:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a8ab52e02b660f0684515be792317bd5123eca95c00ca3c5203abb52237e0843","abstract_canon_sha256":"696d5707c39551c4d4acf8d77f322eafb1ec35d78ad77ba08f695252f72d5047"},"schema_version":"1.0"},"canonical_sha256":"7f5828ce1bef65fca3ef37a9181515cfb987d3ad2b795217b2b3c9a445ccdf63","source":{"kind":"arxiv","id":"1710.10571","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10571","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10571v5","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10571","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"P5MCRTQ355S7","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"pith_short_16","alias_value":"P5MCRTQ355S7ZI7P","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"pith_short_8","alias_value":"P5MCRTQ3","created_at":"2026-07-05T00:59:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:P5MCRTQ355S7ZI7PG6URQFIVZ6","target":"record","payload":{"canonical_record":{"source":{"id":"1710.10571","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-29T07:27:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a8ab52e02b660f0684515be792317bd5123eca95c00ca3c5203abb52237e0843","abstract_canon_sha256":"696d5707c39551c4d4acf8d77f322eafb1ec35d78ad77ba08f695252f72d5047"},"schema_version":"1.0"},"canonical_sha256":"7f5828ce1bef65fca3ef37a9181515cfb987d3ad2b795217b2b3c9a445ccdf63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:32.393258Z","signature_b64":"uBboEpLVVudtlXiHITz8vkx5bwIATP+9ziKogmcBTzQ2zQSfDzWtXqooyU8yq2rvEwyOwbwY1DQcCeJff4a2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f5828ce1bef65fca3ef37a9181515cfb987d3ad2b795217b2b3c9a445ccdf63","last_reissued_at":"2026-07-05T00:59:32.392839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:32.392839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.10571","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxGOegdw4nkdnSBR/FrNW3XJjjr/gZIYI4mS6KD0Beud5wAKaH82DBKM336UfBu4o1bcG396A9OgaTHb0e4vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:28:15.940056Z"},"content_sha256":"1b80278f51f8c71d49cc7f0e422ad9ff1e0a83d04f397a55fac5f2ed84343204","schema_version":"1.0","event_id":"sha256:1b80278f51f8c71d49cc7f0e422ad9ff1e0a83d04f397a55fac5f2ed84343204"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:P5MCRTQ355S7ZI7PG6URQFIVZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Certifying Some Distributional Robustness with Principled Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aman Sinha, Hongseok Namkoong, John Duchi, Riccardo Volpi","submitted_at":"2017-10-29T07:27:57Z","abstract_excerpt":"Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms. We address this problem through the principled lens of distributionally robust optimization, which guarantees performance under adversarial input perturbations. By considering a Lagrangian penalty formulation of perturbing the underlying data distribution in a Wasserstein ball, we provide a training procedure that augments model parameter updates with worst-case perturbations of training data. For smooth losses, our procedure provably achieves moderate levels of ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10571","kind":"arxiv","version":5},"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/1710.10571/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":"2026-07-05T00:59:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jjc0w0vSy6xPpqmLo8ecHvv8Gy+r3v8AxeHTSAhtnKYAxCE+JD6MPa6hOccv305ZBfupzUvOpUelJWD8laZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:28:15.940802Z"},"content_sha256":"3c9cbda0f066ca2f2ef89448007b0ec95d90b27fda5ee2684271db793156cde5","schema_version":"1.0","event_id":"sha256:3c9cbda0f066ca2f2ef89448007b0ec95d90b27fda5ee2684271db793156cde5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5MCRTQ355S7ZI7PG6URQFIVZ6/bundle.json","state_url":"https://pith.science/pith/P5MCRTQ355S7ZI7PG6URQFIVZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5MCRTQ355S7ZI7PG6URQFIVZ6/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":"2026-08-18T14:28:15Z","links":{"resolver":"https://pith.science/pith/P5MCRTQ355S7ZI7PG6URQFIVZ6","bundle":"https://pith.science/pith/P5MCRTQ355S7ZI7PG6URQFIVZ6/bundle.json","state":"https://pith.science/pith/P5MCRTQ355S7ZI7PG6URQFIVZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5MCRTQ355S7ZI7PG6URQFIVZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:P5MCRTQ355S7ZI7PG6URQFIVZ6","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":"696d5707c39551c4d4acf8d77f322eafb1ec35d78ad77ba08f695252f72d5047","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-29T07:27:57Z","title_canon_sha256":"a8ab52e02b660f0684515be792317bd5123eca95c00ca3c5203abb52237e0843"},"schema_version":"1.0","source":{"id":"1710.10571","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10571","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10571v5","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10571","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"P5MCRTQ355S7","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"pith_short_16","alias_value":"P5MCRTQ355S7ZI7P","created_at":"2026-07-05T00:59:32Z"},{"alias_kind":"pith_short_8","alias_value":"P5MCRTQ3","created_at":"2026-07-05T00:59:32Z"}],"graph_snapshots":[{"event_id":"sha256:3c9cbda0f066ca2f2ef89448007b0ec95d90b27fda5ee2684271db793156cde5","target":"graph","created_at":"2026-07-05T00:59:32Z","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/1710.10571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms. We address this problem through the principled lens of distributionally robust optimization, which guarantees performance under adversarial input perturbations. By considering a Lagrangian penalty formulation of perturbing the underlying data distribution in a Wasserstein ball, we provide a training procedure that augments model parameter updates with worst-case perturbations of training data. For smooth losses, our procedure provably achieves moderate levels of ro","authors_text":"Aman Sinha, Hongseok Namkoong, John Duchi, Riccardo Volpi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-29T07:27:57Z","title":"Certifying Some Distributional Robustness with Principled Adversarial Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10571","kind":"arxiv","version":5},"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":"sha256:1b80278f51f8c71d49cc7f0e422ad9ff1e0a83d04f397a55fac5f2ed84343204","target":"record","created_at":"2026-07-05T00:59:32Z","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":"696d5707c39551c4d4acf8d77f322eafb1ec35d78ad77ba08f695252f72d5047","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-29T07:27:57Z","title_canon_sha256":"a8ab52e02b660f0684515be792317bd5123eca95c00ca3c5203abb52237e0843"},"schema_version":"1.0","source":{"id":"1710.10571","kind":"arxiv","version":5}},"canonical_sha256":"7f5828ce1bef65fca3ef37a9181515cfb987d3ad2b795217b2b3c9a445ccdf63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f5828ce1bef65fca3ef37a9181515cfb987d3ad2b795217b2b3c9a445ccdf63","first_computed_at":"2026-07-05T00:59:32.392839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:32.392839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBboEpLVVudtlXiHITz8vkx5bwIATP+9ziKogmcBTzQ2zQSfDzWtXqooyU8yq2rvEwyOwbwY1DQcCeJff4a2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:32.393258Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.10571","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b80278f51f8c71d49cc7f0e422ad9ff1e0a83d04f397a55fac5f2ed84343204","sha256:3c9cbda0f066ca2f2ef89448007b0ec95d90b27fda5ee2684271db793156cde5"],"state_sha256":"15745484b1bd2fc26128f92a4f60b028937da11188cf1f2f105bf17cfc85668e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ntmTOAhU3dftH3v6WtxX0ytoXfsKU6MXo7RDd7ZoSL1XXRu+iCjGHP+O/2Pt1mwQrpOq34Sc55+xy3Of8V0qCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:28:15.946400Z","bundle_sha256":"08e319f36576b9b75cf8d1e6564e2c039e87337b3563a7d51f4f93907e01e5d0"}}