{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RHFY6JNJCGJSFYDH6DOEQAH254","short_pith_number":"pith:RHFY6JNJ","canonical_record":{"source":{"id":"1808.09540","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-28T20:53:01Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"2e1bb67a4e99d8232c49468624291c6c80bfab2cb3c3cdce9323995025cad43a","abstract_canon_sha256":"1ab845dfbcf38fd874d3ddfca5c73072060c5950ad0865f68a91270dcba5b0ad"},"schema_version":"1.0"},"canonical_sha256":"89cb8f25a9119322e067f0dc4800faef2e791430d4de90cf60fc4f3c9fbd74b6","source":{"kind":"arxiv","id":"1808.09540","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09540","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09540v4","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09540","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"RHFY6JNJCGJS","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"RHFY6JNJCGJSFYDH","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"RHFY6JNJ","created_at":"2026-07-05T00:04:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RHFY6JNJCGJSFYDH6DOEQAH254","target":"record","payload":{"canonical_record":{"source":{"id":"1808.09540","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-28T20:53:01Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"2e1bb67a4e99d8232c49468624291c6c80bfab2cb3c3cdce9323995025cad43a","abstract_canon_sha256":"1ab845dfbcf38fd874d3ddfca5c73072060c5950ad0865f68a91270dcba5b0ad"},"schema_version":"1.0"},"canonical_sha256":"89cb8f25a9119322e067f0dc4800faef2e791430d4de90cf60fc4f3c9fbd74b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:06.019367Z","signature_b64":"0K33FFBetthVkDXeHJojMUEnLfu6UVjlcMaITqNi/V5NVql0OUgjgbZPDf2LiAuGEM4vyX2jezK8cQl1pRmMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89cb8f25a9119322e067f0dc4800faef2e791430d4de90cf60fc4f3c9fbd74b6","last_reissued_at":"2026-07-05T00:04:06.018920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:06.018920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.09540","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tc2XWsk1YJtJ1k2gsulb0QuixEZ+CD5ZFXtN+FoVMDu+rXgLSF9aHHaK1hLmVqzQ4KfB0Kd3kPuw1gcBwkS+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:26:18.654584Z"},"content_sha256":"da08a9ea0233945c506d7a058ee61f6e30a1816010dec37a4c8624398141c6db","schema_version":"1.0","event_id":"sha256:da08a9ea0233945c506d7a058ee61f6e30a1816010dec37a4c8624398141c6db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RHFY6JNJCGJSFYDH6DOEQAH254","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lipschitz regularized Deep Neural Networks generalize and are adversarially robust","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Oberman, Bilal Abbasi, Chris Finlay, Jeff Calder","submitted_at":"2018-08-28T20:53:01Z","abstract_excerpt":"In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the curse of dimensionality, but it is independent of the number of layers in the networks. The adversarial robustness regularization combines adversarial training, which we show to be equivalent to Total Variation regularization, with Lipschitz regularization. We demonstrate empirically that the regularized models are more robust, and that gradient norms of images "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09540","kind":"arxiv","version":4},"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/1808.09540/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":"2026-07-05T00:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmON6FK9yXti9RgQu7ebttbtoA/CbUCCg89gkEcxa7tPjqhV/9fKqMitCH3Lo+OOQQI++h9XvBYfIll5ocB6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:26:18.655084Z"},"content_sha256":"718a4d40661d29068b65de5b62e976cca470161520d24d00a31e7f267b11c93e","schema_version":"1.0","event_id":"sha256:718a4d40661d29068b65de5b62e976cca470161520d24d00a31e7f267b11c93e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHFY6JNJCGJSFYDH6DOEQAH254/bundle.json","state_url":"https://pith.science/pith/RHFY6JNJCGJSFYDH6DOEQAH254/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHFY6JNJCGJSFYDH6DOEQAH254/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":"2026-08-12T20:26:18Z","links":{"resolver":"https://pith.science/pith/RHFY6JNJCGJSFYDH6DOEQAH254","bundle":"https://pith.science/pith/RHFY6JNJCGJSFYDH6DOEQAH254/bundle.json","state":"https://pith.science/pith/RHFY6JNJCGJSFYDH6DOEQAH254/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHFY6JNJCGJSFYDH6DOEQAH254/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RHFY6JNJCGJSFYDH6DOEQAH254","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":"1ab845dfbcf38fd874d3ddfca5c73072060c5950ad0865f68a91270dcba5b0ad","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-28T20:53:01Z","title_canon_sha256":"2e1bb67a4e99d8232c49468624291c6c80bfab2cb3c3cdce9323995025cad43a"},"schema_version":"1.0","source":{"id":"1808.09540","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09540","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09540v4","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09540","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"RHFY6JNJCGJS","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"RHFY6JNJCGJSFYDH","created_at":"2026-07-05T00:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"RHFY6JNJ","created_at":"2026-07-05T00:04:06Z"}],"graph_snapshots":[{"event_id":"sha256:718a4d40661d29068b65de5b62e976cca470161520d24d00a31e7f267b11c93e","target":"graph","created_at":"2026-07-05T00:04:06Z","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/1808.09540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the curse of dimensionality, but it is independent of the number of layers in the networks. The adversarial robustness regularization combines adversarial training, which we show to be equivalent to Total Variation regularization, with Lipschitz regularization. We demonstrate empirically that the regularized models are more robust, and that gradient norms of images ","authors_text":"Adam Oberman, Bilal Abbasi, Chris Finlay, Jeff Calder","cross_cats":["cs.NA","math.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-28T20:53:01Z","title":"Lipschitz regularized Deep Neural Networks generalize and are adversarially robust"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09540","kind":"arxiv","version":4},"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:da08a9ea0233945c506d7a058ee61f6e30a1816010dec37a4c8624398141c6db","target":"record","created_at":"2026-07-05T00:04:06Z","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":"1ab845dfbcf38fd874d3ddfca5c73072060c5950ad0865f68a91270dcba5b0ad","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-28T20:53:01Z","title_canon_sha256":"2e1bb67a4e99d8232c49468624291c6c80bfab2cb3c3cdce9323995025cad43a"},"schema_version":"1.0","source":{"id":"1808.09540","kind":"arxiv","version":4}},"canonical_sha256":"89cb8f25a9119322e067f0dc4800faef2e791430d4de90cf60fc4f3c9fbd74b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89cb8f25a9119322e067f0dc4800faef2e791430d4de90cf60fc4f3c9fbd74b6","first_computed_at":"2026-07-05T00:04:06.018920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:06.018920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0K33FFBetthVkDXeHJojMUEnLfu6UVjlcMaITqNi/V5NVql0OUgjgbZPDf2LiAuGEM4vyX2jezK8cQl1pRmMCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:06.019367Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09540","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da08a9ea0233945c506d7a058ee61f6e30a1816010dec37a4c8624398141c6db","sha256:718a4d40661d29068b65de5b62e976cca470161520d24d00a31e7f267b11c93e"],"state_sha256":"bffe3608c43d50c364ea3a20108aea7524da3b03e1a243b834aa6900f0e87808"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhvPQ8XuUfz0JbVi41rigQgjBViMFw5/YdA7Kg6PTw4Bxs+KG2XL56fqqA74BUIXRQnuSZYs1JB0xxMd2Mh8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T20:26:18.658649Z","bundle_sha256":"57a079aafd3de355c3900c64557618d6d3824e8f9349494e731fa7ef81859ecb"}}