{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KZG3KZYNJL4WELWEUIYJYDU4LJ","short_pith_number":"pith:KZG3KZYN","canonical_record":{"source":{"id":"1705.07204","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T21:56:43Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"3846decdb2d345772880338ceba9c846778f0da459403ef3d4d68a8f971852b0","abstract_canon_sha256":"37da43319fe10183fad2b0bdd8c42ea5c2430fe0636c3b47ea86dc1baa65ffe5"},"schema_version":"1.0"},"canonical_sha256":"564db5670d4af9622ec4a2309c0e9c5a4928e1de69d2ab12e5b525c3cc1354a3","source":{"kind":"arxiv","id":"1705.07204","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07204","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07204v5","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07204","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"KZG3KZYNJL4W","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"pith_short_16","alias_value":"KZG3KZYNJL4WELWE","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"pith_short_8","alias_value":"KZG3KZYN","created_at":"2026-07-05T00:58:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KZG3KZYNJL4WELWEUIYJYDU4LJ","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07204","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T21:56:43Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"3846decdb2d345772880338ceba9c846778f0da459403ef3d4d68a8f971852b0","abstract_canon_sha256":"37da43319fe10183fad2b0bdd8c42ea5c2430fe0636c3b47ea86dc1baa65ffe5"},"schema_version":"1.0"},"canonical_sha256":"564db5670d4af9622ec4a2309c0e9c5a4928e1de69d2ab12e5b525c3cc1354a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:00.101356Z","signature_b64":"jce8LIE7cOW0UN1S//XAwx4BCBiFW8QZpxgruYKl+qt4TEz2tr3VxOemAy7viz995bNihRWH8PLZBKWZ7Q+UCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"564db5670d4af9622ec4a2309c0e9c5a4928e1de69d2ab12e5b525c3cc1354a3","last_reissued_at":"2026-07-05T00:58:00.100910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:00.100910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07204","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":"2026-07-05T00:58:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bJ7Aj10XyuNRKQdtbemXM0a2yASaiSupt+zoO9qTwFJi12KkxC8gSTN2jVgp8hJYKUb46/SlxCkwTP2eFe5MDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:32:19.651530Z"},"content_sha256":"ab5ec9b6ea2dab15319b51292512d57331e3bf465fb197785905cc4231f1b2b8","schema_version":"1.0","event_id":"sha256:ab5ec9b6ea2dab15319b51292512d57331e3bf465fb197785905cc4231f1b2b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KZG3KZYNJL4WELWEUIYJYDU4LJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensemble Adversarial Training: Attacks and Defenses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexey Kurakin, Dan Boneh, Florian Tram\\`er, Ian Goodfellow, Nicolas Papernot, Patrick McDaniel","submitted_at":"2017-05-19T21:56:43Z","abstract_excerpt":"Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted using fast single-step methods that maximize a linear approximation of the model's loss. We show that this form of adversarial training converges to a degenerate global minimum, wherein small curvature artifacts near the data points obfuscate a linear approximation of the loss. The model thus learns to generate weak perturbations, rather than defend against s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07204","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/1705.07204/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":"2026-07-05T00:58:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3woGWnDHIeSix7ILH0kqmx4zlyL4Rcak7B5Zw3Ak93+sy/Ho1r06yaD80Kb4QL8hdthnrTPjwFnokU2/pixiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:32:19.652173Z"},"content_sha256":"b8dc3ca6ffcc58d8a73bcb3cfaf4a2977e0dbb9599600aa1fbcb529541295f53","schema_version":"1.0","event_id":"sha256:b8dc3ca6ffcc58d8a73bcb3cfaf4a2977e0dbb9599600aa1fbcb529541295f53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZG3KZYNJL4WELWEUIYJYDU4LJ/bundle.json","state_url":"https://pith.science/pith/KZG3KZYNJL4WELWEUIYJYDU4LJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZG3KZYNJL4WELWEUIYJYDU4LJ/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":"2026-08-09T22:32:19Z","links":{"resolver":"https://pith.science/pith/KZG3KZYNJL4WELWEUIYJYDU4LJ","bundle":"https://pith.science/pith/KZG3KZYNJL4WELWEUIYJYDU4LJ/bundle.json","state":"https://pith.science/pith/KZG3KZYNJL4WELWEUIYJYDU4LJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZG3KZYNJL4WELWEUIYJYDU4LJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KZG3KZYNJL4WELWEUIYJYDU4LJ","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":"37da43319fe10183fad2b0bdd8c42ea5c2430fe0636c3b47ea86dc1baa65ffe5","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T21:56:43Z","title_canon_sha256":"3846decdb2d345772880338ceba9c846778f0da459403ef3d4d68a8f971852b0"},"schema_version":"1.0","source":{"id":"1705.07204","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07204","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07204v5","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07204","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"KZG3KZYNJL4W","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"pith_short_16","alias_value":"KZG3KZYNJL4WELWE","created_at":"2026-07-05T00:58:00Z"},{"alias_kind":"pith_short_8","alias_value":"KZG3KZYN","created_at":"2026-07-05T00:58:00Z"}],"graph_snapshots":[{"event_id":"sha256:b8dc3ca6ffcc58d8a73bcb3cfaf4a2977e0dbb9599600aa1fbcb529541295f53","target":"graph","created_at":"2026-07-05T00:58:00Z","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/1705.07204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted using fast single-step methods that maximize a linear approximation of the model's loss. We show that this form of adversarial training converges to a degenerate global minimum, wherein small curvature artifacts near the data points obfuscate a linear approximation of the loss. The model thus learns to generate weak perturbations, rather than defend against s","authors_text":"Alexey Kurakin, Dan Boneh, Florian Tram\\`er, Ian Goodfellow, Nicolas Papernot, Patrick McDaniel","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T21:56:43Z","title":"Ensemble Adversarial Training: Attacks and Defenses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07204","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:ab5ec9b6ea2dab15319b51292512d57331e3bf465fb197785905cc4231f1b2b8","target":"record","created_at":"2026-07-05T00:58:00Z","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":"37da43319fe10183fad2b0bdd8c42ea5c2430fe0636c3b47ea86dc1baa65ffe5","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T21:56:43Z","title_canon_sha256":"3846decdb2d345772880338ceba9c846778f0da459403ef3d4d68a8f971852b0"},"schema_version":"1.0","source":{"id":"1705.07204","kind":"arxiv","version":5}},"canonical_sha256":"564db5670d4af9622ec4a2309c0e9c5a4928e1de69d2ab12e5b525c3cc1354a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"564db5670d4af9622ec4a2309c0e9c5a4928e1de69d2ab12e5b525c3cc1354a3","first_computed_at":"2026-07-05T00:58:00.100910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:00.100910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jce8LIE7cOW0UN1S//XAwx4BCBiFW8QZpxgruYKl+qt4TEz2tr3VxOemAy7viz995bNihRWH8PLZBKWZ7Q+UCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:00.101356Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07204","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab5ec9b6ea2dab15319b51292512d57331e3bf465fb197785905cc4231f1b2b8","sha256:b8dc3ca6ffcc58d8a73bcb3cfaf4a2977e0dbb9599600aa1fbcb529541295f53"],"state_sha256":"bfb699c9dababbedcb0e555c3d1ddc80b49ab32cf3db70a75c6f5bbfaad77e82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GhmiG/RiKfp4oSKOeWC8wZfurL0Z1h0bNz7vl6RJZGd4a3HDTS/WnpnrXqQLjQJez1Vwmi++HPlaWUBkHGRjDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:32:19.657187Z","bundle_sha256":"1cf04840c7d618dd9546c9162fe4a5d6a943ce867e3a05a50baa24274339dc3e"}}