{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LB262AL74VYVVKY5KG454QZ3CB","short_pith_number":"pith:LB262AL7","canonical_record":{"source":{"id":"1811.08080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-20T05:22:55Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"8ce98ca9f44cbbb32de8600d826730e1e4b35513a2acd4c1b60c135c21f907d5","abstract_canon_sha256":"0cde650f61ebe9314707cda2bd1e9e8110ff87ec15b4aaf722cae1dc00fd2679"},"schema_version":"1.0"},"canonical_sha256":"5875ed017fe5715aab1d51b9de433b1073d333aeb1ae31020faef5a8fd8ce206","source":{"kind":"arxiv","id":"1811.08080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08080","created_at":"2026-05-18T00:00:16Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08080v1","created_at":"2026-05-18T00:00:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08080","created_at":"2026-05-18T00:00:16Z"},{"alias_kind":"pith_short_12","alias_value":"LB262AL74VYV","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LB262AL74VYVVKY5","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LB262AL7","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LB262AL74VYVVKY5KG454QZ3CB","target":"record","payload":{"canonical_record":{"source":{"id":"1811.08080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-20T05:22:55Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"8ce98ca9f44cbbb32de8600d826730e1e4b35513a2acd4c1b60c135c21f907d5","abstract_canon_sha256":"0cde650f61ebe9314707cda2bd1e9e8110ff87ec15b4aaf722cae1dc00fd2679"},"schema_version":"1.0"},"canonical_sha256":"5875ed017fe5715aab1d51b9de433b1073d333aeb1ae31020faef5a8fd8ce206","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:16.924695Z","signature_b64":"aYy6EpVG7vL9c8IzVF1NAqAJy1ZiZZnN3aaYs9F+UwqCFnJmhBm9R6DkAelLVE8Zjt4Q+43ZJLjwboQHcvqvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5875ed017fe5715aab1d51b9de433b1073d333aeb1ae31020faef5a8fd8ce206","last_reissued_at":"2026-05-18T00:00:16.924098Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:16.924098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.08080","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":"2026-05-18T00:00:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"msGKVn3Tl1i66uvHWgH5Be30lAAxA9wLnDL/x2yl1H2I1KEUtr7/mQf172te24z19Box7GqIbo4hwiAJ+P+yCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:19:58.975128Z"},"content_sha256":"ec874bdd32d4d5a2889f822951b7e71a22c7e4f354e13a6795912e492064e108","schema_version":"1.0","event_id":"sha256:ec874bdd32d4d5a2889f822951b7e71a22c7e4f354e13a6795912e492064e108"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LB262AL74VYVVKY5KG454QZ3CB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hajime Ono, Kazuya Kakizaki, Tsubasa Takahashi","submitted_at":"2018-11-20T05:22:55Z","abstract_excerpt":"How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure $\\epsilon$-robust, consume huge resources, they can only achieve small degree of robustness in practice. Lipschitz margin training (LMT) is a scalable certified defense, but it can also only achieve small robustness due to over-regularization. How can we make certified defense more efficiently? We present LC-LMT, a light weight Lipschitz margin training which solves the above problem. Our method has the following properties; (a) efficient: it can achiev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08080","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":"2026-05-18T00:00:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9QhUJ2d3wOX0QK1QRZWHOfNZ8kn43/ldcGy/w0TZ9Z82lPePaIW/03/DDbdkm820jRXIbI0geNKxFQXzLgoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:19:58.975492Z"},"content_sha256":"73726f494a954991c0884f8c60990bb73ab86c360db98875994d362d4f315026","schema_version":"1.0","event_id":"sha256:73726f494a954991c0884f8c60990bb73ab86c360db98875994d362d4f315026"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LB262AL74VYVVKY5KG454QZ3CB/bundle.json","state_url":"https://pith.science/pith/LB262AL74VYVVKY5KG454QZ3CB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LB262AL74VYVVKY5KG454QZ3CB/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":"2026-06-01T05:19:58Z","links":{"resolver":"https://pith.science/pith/LB262AL74VYVVKY5KG454QZ3CB","bundle":"https://pith.science/pith/LB262AL74VYVVKY5KG454QZ3CB/bundle.json","state":"https://pith.science/pith/LB262AL74VYVVKY5KG454QZ3CB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LB262AL74VYVVKY5KG454QZ3CB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LB262AL74VYVVKY5KG454QZ3CB","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":"0cde650f61ebe9314707cda2bd1e9e8110ff87ec15b4aaf722cae1dc00fd2679","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-20T05:22:55Z","title_canon_sha256":"8ce98ca9f44cbbb32de8600d826730e1e4b35513a2acd4c1b60c135c21f907d5"},"schema_version":"1.0","source":{"id":"1811.08080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08080","created_at":"2026-05-18T00:00:16Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08080v1","created_at":"2026-05-18T00:00:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08080","created_at":"2026-05-18T00:00:16Z"},{"alias_kind":"pith_short_12","alias_value":"LB262AL74VYV","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LB262AL74VYVVKY5","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LB262AL7","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:73726f494a954991c0884f8c60990bb73ab86c360db98875994d362d4f315026","target":"graph","created_at":"2026-05-18T00:00:16Z","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":"How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure $\\epsilon$-robust, consume huge resources, they can only achieve small degree of robustness in practice. Lipschitz margin training (LMT) is a scalable certified defense, but it can also only achieve small robustness due to over-regularization. How can we make certified defense more efficiently? We present LC-LMT, a light weight Lipschitz margin training which solves the above problem. Our method has the following properties; (a) efficient: it can achiev","authors_text":"Hajime Ono, Kazuya Kakizaki, Tsubasa Takahashi","cross_cats":["cs.CR","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-20T05:22:55Z","title":"Lightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08080","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:ec874bdd32d4d5a2889f822951b7e71a22c7e4f354e13a6795912e492064e108","target":"record","created_at":"2026-05-18T00:00:16Z","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":"0cde650f61ebe9314707cda2bd1e9e8110ff87ec15b4aaf722cae1dc00fd2679","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-20T05:22:55Z","title_canon_sha256":"8ce98ca9f44cbbb32de8600d826730e1e4b35513a2acd4c1b60c135c21f907d5"},"schema_version":"1.0","source":{"id":"1811.08080","kind":"arxiv","version":1}},"canonical_sha256":"5875ed017fe5715aab1d51b9de433b1073d333aeb1ae31020faef5a8fd8ce206","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5875ed017fe5715aab1d51b9de433b1073d333aeb1ae31020faef5a8fd8ce206","first_computed_at":"2026-05-18T00:00:16.924098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:16.924098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aYy6EpVG7vL9c8IzVF1NAqAJy1ZiZZnN3aaYs9F+UwqCFnJmhBm9R6DkAelLVE8Zjt4Q+43ZJLjwboQHcvqvBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:16.924695Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.08080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec874bdd32d4d5a2889f822951b7e71a22c7e4f354e13a6795912e492064e108","sha256:73726f494a954991c0884f8c60990bb73ab86c360db98875994d362d4f315026"],"state_sha256":"ea426da70420ed5b83af56e31e9a786cb7556152c3cd002095bb5a19a45878a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D5+GkSGYFhtpwMiimjH+KU5Zb07hd+OBdVcbUFuNnhDiMUpx0N56wQ1xCxPC4XUD1g7FsqNPscYz1XKzvus1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:19:58.977537Z","bundle_sha256":"6e58ff86ef90910049e8001315a83904331a4012fe840aaf14ba15f6cc36ccaa"}}