{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:X7ETHVVYFYL3TUJBFHVXQV2JRM","short_pith_number":"pith:X7ETHVVY","canonical_record":{"source":{"id":"1610.01934","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T16:20:45Z","cross_cats_sorted":[],"title_canon_sha256":"92df2c8c524185f928c6c62e284fda636117ea400927449cca031b02a5931f3f","abstract_canon_sha256":"c883daef3f6fb60757b7dcfe01ca138d4c1969210d60513fd9be7ea9b946a984"},"schema_version":"1.0"},"canonical_sha256":"bfc933d6b82e17b9d12129eb7857498b36878aed85e24d4bd238e54827447dfd","source":{"kind":"arxiv","id":"1610.01934","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01934","created_at":"2026-05-18T00:55:07Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01934v5","created_at":"2026-05-18T00:55:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01934","created_at":"2026-05-18T00:55:07Z"},{"alias_kind":"pith_short_12","alias_value":"X7ETHVVYFYL3","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"X7ETHVVYFYL3TUJB","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"X7ETHVVY","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:X7ETHVVYFYL3TUJBFHVXQV2JRM","target":"record","payload":{"canonical_record":{"source":{"id":"1610.01934","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T16:20:45Z","cross_cats_sorted":[],"title_canon_sha256":"92df2c8c524185f928c6c62e284fda636117ea400927449cca031b02a5931f3f","abstract_canon_sha256":"c883daef3f6fb60757b7dcfe01ca138d4c1969210d60513fd9be7ea9b946a984"},"schema_version":"1.0"},"canonical_sha256":"bfc933d6b82e17b9d12129eb7857498b36878aed85e24d4bd238e54827447dfd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:07.299751Z","signature_b64":"ts8c2Zag3wj+Kqw4PxclHX9SJau4BEcmN9OYYdXql7sna7tCi3Rir99oMUsEnfeMV/5goK0G4VLn0dmk+u+6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfc933d6b82e17b9d12129eb7857498b36878aed85e24d4bd238e54827447dfd","last_reissued_at":"2026-05-18T00:55:07.299051Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:07.299051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.01934","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":"2026-05-18T00:55:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IbJDpdlAyc+YXwT1GQEwdxyEGc4lNCcIUOJMp91ry5ZTGS+QSzDMVorhPkCfCgItmPp4kymsDJaBCMJT64QSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:31:07.826481Z"},"content_sha256":"98457254e14378ae82e12f9e6d6e2007b3379de6fae1c112b66d019bbed7e140","schema_version":"1.0","event_id":"sha256:98457254e14378ae82e12f9e6d6e2007b3379de6fae1c112b66d019bbed7e140"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:X7ETHVVYFYL3TUJBFHVXQV2JRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander G. Ororbia II, C. Lee Giles, Gang Xiong, Lin Lin, Peng Liu, Qinglong Wang, Wenbo Guo, Xinyu Xing, Xue Liu","submitted_at":"2016-10-06T16:20:45Z","abstract_excerpt":"Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior performance in many applications, these models have been recently shown to be susceptible to a particular type of attack possible through the generation of particular synthetic examples referred to as adversarial samples. These samples are constructed by manipulating real examples from the training data distribution in order to \"fool\" the original neural model, re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01934","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":""},"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":"2026-05-18T00:55:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"So7UTznI108lIQkqscJ9bQkMxUYeuo2V12Yz9Vi+1Czrv9iv1EioDjBTSe4MSYYDFJTvthcLJSVY2LGL5tNaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:31:07.826829Z"},"content_sha256":"6c39dcec8241659b26e2049b50ad54ef510ee667632cd92a2b551ef05b2ef859","schema_version":"1.0","event_id":"sha256:6c39dcec8241659b26e2049b50ad54ef510ee667632cd92a2b551ef05b2ef859"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7ETHVVYFYL3TUJBFHVXQV2JRM/bundle.json","state_url":"https://pith.science/pith/X7ETHVVYFYL3TUJBFHVXQV2JRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7ETHVVYFYL3TUJBFHVXQV2JRM/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":"2026-06-02T11:31:07Z","links":{"resolver":"https://pith.science/pith/X7ETHVVYFYL3TUJBFHVXQV2JRM","bundle":"https://pith.science/pith/X7ETHVVYFYL3TUJBFHVXQV2JRM/bundle.json","state":"https://pith.science/pith/X7ETHVVYFYL3TUJBFHVXQV2JRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7ETHVVYFYL3TUJBFHVXQV2JRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:X7ETHVVYFYL3TUJBFHVXQV2JRM","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":"c883daef3f6fb60757b7dcfe01ca138d4c1969210d60513fd9be7ea9b946a984","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T16:20:45Z","title_canon_sha256":"92df2c8c524185f928c6c62e284fda636117ea400927449cca031b02a5931f3f"},"schema_version":"1.0","source":{"id":"1610.01934","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01934","created_at":"2026-05-18T00:55:07Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01934v5","created_at":"2026-05-18T00:55:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01934","created_at":"2026-05-18T00:55:07Z"},{"alias_kind":"pith_short_12","alias_value":"X7ETHVVYFYL3","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"X7ETHVVYFYL3TUJB","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"X7ETHVVY","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:6c39dcec8241659b26e2049b50ad54ef510ee667632cd92a2b551ef05b2ef859","target":"graph","created_at":"2026-05-18T00:55:07Z","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":"Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior performance in many applications, these models have been recently shown to be susceptible to a particular type of attack possible through the generation of particular synthetic examples referred to as adversarial samples. These samples are constructed by manipulating real examples from the training data distribution in order to \"fool\" the original neural model, re","authors_text":"Alexander G. Ororbia II, C. Lee Giles, Gang Xiong, Lin Lin, Peng Liu, Qinglong Wang, Wenbo Guo, Xinyu Xing, Xue Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T16:20:45Z","title":"Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01934","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":"sha256:98457254e14378ae82e12f9e6d6e2007b3379de6fae1c112b66d019bbed7e140","target":"record","created_at":"2026-05-18T00:55:07Z","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":"c883daef3f6fb60757b7dcfe01ca138d4c1969210d60513fd9be7ea9b946a984","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-06T16:20:45Z","title_canon_sha256":"92df2c8c524185f928c6c62e284fda636117ea400927449cca031b02a5931f3f"},"schema_version":"1.0","source":{"id":"1610.01934","kind":"arxiv","version":5}},"canonical_sha256":"bfc933d6b82e17b9d12129eb7857498b36878aed85e24d4bd238e54827447dfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfc933d6b82e17b9d12129eb7857498b36878aed85e24d4bd238e54827447dfd","first_computed_at":"2026-05-18T00:55:07.299051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:07.299051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ts8c2Zag3wj+Kqw4PxclHX9SJau4BEcmN9OYYdXql7sna7tCi3Rir99oMUsEnfeMV/5goK0G4VLn0dmk+u+6CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:07.299751Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.01934","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98457254e14378ae82e12f9e6d6e2007b3379de6fae1c112b66d019bbed7e140","sha256:6c39dcec8241659b26e2049b50ad54ef510ee667632cd92a2b551ef05b2ef859"],"state_sha256":"4e680c49c95f8fd3002deed3964373a4775f21f7efc9e63d2cdc1cd494608086"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GiQwJFbBgwfaM2LPn3JFH/4wrkOupnu8I5Q7yLGL+UQf3drNR0FfZ7NcYT1qTEQCo1s8suHUln3HFAs9+p9bBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:31:07.828891Z","bundle_sha256":"ce8528de6ebfb7e44d55043d510e7b679e4878368ff14ea2ebd8e3532de10235"}}