{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OUBKUWQBFHUHE7B4HSNG5SPVTM","short_pith_number":"pith:OUBKUWQB","canonical_record":{"source":{"id":"1805.12514","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T15:25:10Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"68759d485b3c81b778d4a987cce958868045b49ce76b20cbc4269242b0ea02ff","abstract_canon_sha256":"04078b8bfc1bda9d66abe99631022928e60ed63b0273478a667a7aa4f42f35c9"},"schema_version":"1.0"},"canonical_sha256":"7502aa5a0129e8727c3c3c9a6ec9f59b2b6f7924a4e6be8cdb000de3b4a3c9a0","source":{"kind":"arxiv","id":"1805.12514","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12514","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12514v2","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12514","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"OUBKUWQBFHUH","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OUBKUWQBFHUHE7B4","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OUBKUWQB","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OUBKUWQBFHUHE7B4HSNG5SPVTM","target":"record","payload":{"canonical_record":{"source":{"id":"1805.12514","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T15:25:10Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"68759d485b3c81b778d4a987cce958868045b49ce76b20cbc4269242b0ea02ff","abstract_canon_sha256":"04078b8bfc1bda9d66abe99631022928e60ed63b0273478a667a7aa4f42f35c9"},"schema_version":"1.0"},"canonical_sha256":"7502aa5a0129e8727c3c3c9a6ec9f59b2b6f7924a4e6be8cdb000de3b4a3c9a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:08.504235Z","signature_b64":"lkYOW/QNYsOxPtljRC5KnT+yh8+cPFjsWzDD1YS30ZTxu2BzspfrgzWiqyEviTbXrLGG069n3xEvZIYYKzp5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7502aa5a0129e8727c3c3c9a6ec9f59b2b6f7924a4e6be8cdb000de3b4a3c9a0","last_reissued_at":"2026-05-18T00:00:08.503681Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:08.503681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.12514","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcRmEI+t8Wte0vg7XIR807voX7q9ewShxbZCJQoCrZw1WLvFNCj7J24bMEpECh8PU3RHYcbk7GB1ZruWuuFTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:11:32.460221Z"},"content_sha256":"8d1e285428c70c25cbf46247735dd96638063940e2d055f4fc4a194dbf691d70","schema_version":"1.0","event_id":"sha256:8d1e285428c70c25cbf46247735dd96638063940e2d055f4fc4a194dbf691d70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OUBKUWQBFHUHE7B4HSNG5SPVTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling provable adversarial defenses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Wong, Frank R. Schmidt, Jan Hendrik Metzen, J. Zico Kolter","submitted_at":"2018-05-31T15:25:10Z","abstract_excerpt":"Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this paper, in an effort to scale these approaches to substantially larger models, we extend previous work in three main directions. First, we present a technique for extending these training procedures to much more general networks, with skip connections (such as ResNets) and general nonlinearities; the approach is fully modular, and can be implemented automati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12514","kind":"arxiv","version":2},"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":"2026-05-18T00:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZqkfatPL8eQ3t03YLSpH/Ocf/eLe9ZHflXVWMcHPxJrjpArtFrd4u7Sxu5iOo4cvxGFA9nm3BpghcZQZ7109Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:11:32.460907Z"},"content_sha256":"9e9fa50df7ac49cbe044d0f9a373c8cbf888000740974769650a0e305dea6487","schema_version":"1.0","event_id":"sha256:9e9fa50df7ac49cbe044d0f9a373c8cbf888000740974769650a0e305dea6487"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUBKUWQBFHUHE7B4HSNG5SPVTM/bundle.json","state_url":"https://pith.science/pith/OUBKUWQBFHUHE7B4HSNG5SPVTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUBKUWQBFHUHE7B4HSNG5SPVTM/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":"2026-06-07T06:11:32Z","links":{"resolver":"https://pith.science/pith/OUBKUWQBFHUHE7B4HSNG5SPVTM","bundle":"https://pith.science/pith/OUBKUWQBFHUHE7B4HSNG5SPVTM/bundle.json","state":"https://pith.science/pith/OUBKUWQBFHUHE7B4HSNG5SPVTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUBKUWQBFHUHE7B4HSNG5SPVTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OUBKUWQBFHUHE7B4HSNG5SPVTM","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":"04078b8bfc1bda9d66abe99631022928e60ed63b0273478a667a7aa4f42f35c9","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T15:25:10Z","title_canon_sha256":"68759d485b3c81b778d4a987cce958868045b49ce76b20cbc4269242b0ea02ff"},"schema_version":"1.0","source":{"id":"1805.12514","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12514","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12514v2","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12514","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"OUBKUWQBFHUH","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OUBKUWQBFHUHE7B4","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OUBKUWQB","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:9e9fa50df7ac49cbe044d0f9a373c8cbf888000740974769650a0e305dea6487","target":"graph","created_at":"2026-05-18T00:00:08Z","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":"Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this paper, in an effort to scale these approaches to substantially larger models, we extend previous work in three main directions. First, we present a technique for extending these training procedures to much more general networks, with skip connections (such as ResNets) and general nonlinearities; the approach is fully modular, and can be implemented automati","authors_text":"Eric Wong, Frank R. Schmidt, Jan Hendrik Metzen, J. Zico Kolter","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T15:25:10Z","title":"Scaling provable adversarial defenses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12514","kind":"arxiv","version":2},"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":"sha256:8d1e285428c70c25cbf46247735dd96638063940e2d055f4fc4a194dbf691d70","target":"record","created_at":"2026-05-18T00:00:08Z","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":"04078b8bfc1bda9d66abe99631022928e60ed63b0273478a667a7aa4f42f35c9","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T15:25:10Z","title_canon_sha256":"68759d485b3c81b778d4a987cce958868045b49ce76b20cbc4269242b0ea02ff"},"schema_version":"1.0","source":{"id":"1805.12514","kind":"arxiv","version":2}},"canonical_sha256":"7502aa5a0129e8727c3c3c9a6ec9f59b2b6f7924a4e6be8cdb000de3b4a3c9a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7502aa5a0129e8727c3c3c9a6ec9f59b2b6f7924a4e6be8cdb000de3b4a3c9a0","first_computed_at":"2026-05-18T00:00:08.503681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:08.503681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lkYOW/QNYsOxPtljRC5KnT+yh8+cPFjsWzDD1YS30ZTxu2BzspfrgzWiqyEviTbXrLGG069n3xEvZIYYKzp5AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:08.504235Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.12514","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d1e285428c70c25cbf46247735dd96638063940e2d055f4fc4a194dbf691d70","sha256:9e9fa50df7ac49cbe044d0f9a373c8cbf888000740974769650a0e305dea6487"],"state_sha256":"e5318e26d9192df7ab4cd8230c9ce44c4865949649c34d4769e79f70abc1ef33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GOvwMuw0NFaI6e+BDH7MTKCptkXf+XhnlL0F0OpW4hqSuK6vvmxVqNVUDdtIbjauJany9/gw2EMCoWTBeHE+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:11:32.464380Z","bundle_sha256":"a511f1f15fc06698923f2d218af4e392a645ab95289899e3c9d1fd17c44a631e"}}