{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4HLZTWWHUGLHBKEF3OX4AZLWZI","short_pith_number":"pith:4HLZTWWH","canonical_record":{"source":{"id":"2009.04923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T15:05:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"be80eacdf519dbd1bf57053625589aed898fff0b635c23c849507443cad916e3","abstract_canon_sha256":"d216a8faba91116c8041fbf13752bd5ecf951e5dc1c9c14b53a6c7ba217bf582"},"schema_version":"1.0"},"canonical_sha256":"e1d799dac7a19670a885dbafc06576ca00aacaa8f3ea14dc417f140dcb8a00a5","source":{"kind":"arxiv","id":"2009.04923","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04923","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04923v1","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04923","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"4HLZTWWHUGLH","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"pith_short_16","alias_value":"4HLZTWWHUGLHBKEF","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"pith_short_8","alias_value":"4HLZTWWH","created_at":"2026-07-05T01:34:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4HLZTWWHUGLHBKEF3OX4AZLWZI","target":"record","payload":{"canonical_record":{"source":{"id":"2009.04923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T15:05:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"be80eacdf519dbd1bf57053625589aed898fff0b635c23c849507443cad916e3","abstract_canon_sha256":"d216a8faba91116c8041fbf13752bd5ecf951e5dc1c9c14b53a6c7ba217bf582"},"schema_version":"1.0"},"canonical_sha256":"e1d799dac7a19670a885dbafc06576ca00aacaa8f3ea14dc417f140dcb8a00a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:31.305605Z","signature_b64":"VK/Rr70+xkxue7dmm0nllWUpVJazIA30M0ERcyARoanvpwsonivDOqM8U2nUd8jVWk0hUHGzDB5TKAPsJ7ReAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d799dac7a19670a885dbafc06576ca00aacaa8f3ea14dc417f140dcb8a00a5","last_reissued_at":"2026-07-05T01:34:31.305101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:31.305101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.04923","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":"2026-07-05T01:34:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/U4p5xOL2TdhnIdvxVoQryIU9yyqmrvQdqyl3wEummfo8vED98D3X6HZlJ+sNBsZoO/L65hAbY3ugBL8903bCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:07:32.531609Z"},"content_sha256":"97d2ace1c068e907feff70e9183149f7cd7b78d92ca38830d360325ac9da4268","schema_version":"1.0","event_id":"sha256:97d2ace1c068e907feff70e9183149f7cd7b78d92ca38830d360325ac9da4268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4HLZTWWHUGLHBKEF3OX4AZLWZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Second Order Optimization for Adversarial Robustness and Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jay Roberts, Theodoros Tsiligkaridis","submitted_at":"2020-09-10T15:05:14Z","abstract_excerpt":"Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense. However, the computational cost of such training can be prohibitive as the network size and input dimensions grow. Inspired by the relationship between robustness and curvature, we propose a novel regularizer which incorporates first and second order information via a quadratic approximation to the adversarial loss. The worst case quadratic loss is approximated v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04923","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.04923/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":"2026-07-05T01:34:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kv2X3hBp61BWQm/ElyfofAMXXzQr4NUil5kKl42dGyU+U+nTy1JIiLa4S6y12s0UScnECH7oGJdy48BZCJYICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:07:32.531986Z"},"content_sha256":"688e7a13a192ef5f907763dd54fc092b9df4c9eb617fe1030df474be8d1014ba","schema_version":"1.0","event_id":"sha256:688e7a13a192ef5f907763dd54fc092b9df4c9eb617fe1030df474be8d1014ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HLZTWWHUGLHBKEF3OX4AZLWZI/bundle.json","state_url":"https://pith.science/pith/4HLZTWWHUGLHBKEF3OX4AZLWZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HLZTWWHUGLHBKEF3OX4AZLWZI/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":"2026-07-07T08:07:32Z","links":{"resolver":"https://pith.science/pith/4HLZTWWHUGLHBKEF3OX4AZLWZI","bundle":"https://pith.science/pith/4HLZTWWHUGLHBKEF3OX4AZLWZI/bundle.json","state":"https://pith.science/pith/4HLZTWWHUGLHBKEF3OX4AZLWZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HLZTWWHUGLHBKEF3OX4AZLWZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4HLZTWWHUGLHBKEF3OX4AZLWZI","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":"d216a8faba91116c8041fbf13752bd5ecf951e5dc1c9c14b53a6c7ba217bf582","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T15:05:14Z","title_canon_sha256":"be80eacdf519dbd1bf57053625589aed898fff0b635c23c849507443cad916e3"},"schema_version":"1.0","source":{"id":"2009.04923","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04923","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04923v1","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04923","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"4HLZTWWHUGLH","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"pith_short_16","alias_value":"4HLZTWWHUGLHBKEF","created_at":"2026-07-05T01:34:31Z"},{"alias_kind":"pith_short_8","alias_value":"4HLZTWWH","created_at":"2026-07-05T01:34:31Z"}],"graph_snapshots":[{"event_id":"sha256:688e7a13a192ef5f907763dd54fc092b9df4c9eb617fe1030df474be8d1014ba","target":"graph","created_at":"2026-07-05T01:34:31Z","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/2009.04923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense. However, the computational cost of such training can be prohibitive as the network size and input dimensions grow. Inspired by the relationship between robustness and curvature, we propose a novel regularizer which incorporates first and second order information via a quadratic approximation to the adversarial loss. The worst case quadratic loss is approximated v","authors_text":"Jay Roberts, Theodoros Tsiligkaridis","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T15:05:14Z","title":"Second Order Optimization for Adversarial Robustness and Interpretability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04923","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":"sha256:97d2ace1c068e907feff70e9183149f7cd7b78d92ca38830d360325ac9da4268","target":"record","created_at":"2026-07-05T01:34:31Z","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":"d216a8faba91116c8041fbf13752bd5ecf951e5dc1c9c14b53a6c7ba217bf582","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T15:05:14Z","title_canon_sha256":"be80eacdf519dbd1bf57053625589aed898fff0b635c23c849507443cad916e3"},"schema_version":"1.0","source":{"id":"2009.04923","kind":"arxiv","version":1}},"canonical_sha256":"e1d799dac7a19670a885dbafc06576ca00aacaa8f3ea14dc417f140dcb8a00a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1d799dac7a19670a885dbafc06576ca00aacaa8f3ea14dc417f140dcb8a00a5","first_computed_at":"2026-07-05T01:34:31.305101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:31.305101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VK/Rr70+xkxue7dmm0nllWUpVJazIA30M0ERcyARoanvpwsonivDOqM8U2nUd8jVWk0hUHGzDB5TKAPsJ7ReAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:31.305605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.04923","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97d2ace1c068e907feff70e9183149f7cd7b78d92ca38830d360325ac9da4268","sha256:688e7a13a192ef5f907763dd54fc092b9df4c9eb617fe1030df474be8d1014ba"],"state_sha256":"99bdf22d50862e06c944c117465e5c7d33291cf9b0de6110029b58df3d4d4cb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqb1EPRhNaE492/vB3FFq+n0+pMIXL+4NHIPO3FTYrFfKcTQCTnt3XkP9I+lDzKJOi65iepJOF9EXwO33GShDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:07:32.533920Z","bundle_sha256":"2f52225715e14d35256cbc9a1bb8eca5cb2e7a9f9d65fb2439116fdbeaee4c7e"}}