{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KEAOU4DWHUF6TUEZKKDDTFRZBB","short_pith_number":"pith:KEAOU4DW","canonical_record":{"source":{"id":"1810.03913","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T11:13:44Z","cross_cats_sorted":["cs.HC","stat.ML"],"title_canon_sha256":"1b0831ad27f2435c825b04b46d3721f625a15232e457633637d9ffe2506283f5","abstract_canon_sha256":"ef31f5bc2987882839bfdb29da41cf6a750da5f678ec265345ebd321faf6361f"},"schema_version":"1.0"},"canonical_sha256":"5100ea70763d0be9d099528639963908673aa5aa1a950f24fc176fab9176c76b","source":{"kind":"arxiv","id":"1810.03913","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03913","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03913v1","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03913","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"KEAOU4DWHUF6","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KEAOU4DWHUF6TUEZ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KEAOU4DW","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KEAOU4DWHUF6TUEZKKDDTFRZBB","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03913","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T11:13:44Z","cross_cats_sorted":["cs.HC","stat.ML"],"title_canon_sha256":"1b0831ad27f2435c825b04b46d3721f625a15232e457633637d9ffe2506283f5","abstract_canon_sha256":"ef31f5bc2987882839bfdb29da41cf6a750da5f678ec265345ebd321faf6361f"},"schema_version":"1.0"},"canonical_sha256":"5100ea70763d0be9d099528639963908673aa5aa1a950f24fc176fab9176c76b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:44.280095Z","signature_b64":"GkmB/2Jpx5rnXT44IUy4H80r4jK06m9f2Ksx982eUFzItCzMIygVGfHhHrDL4kDywcNKdOsSOJI2PG/Kg13iAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5100ea70763d0be9d099528639963908673aa5aa1a950f24fc176fab9176c76b","last_reissued_at":"2026-05-18T00:03:44.279684Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:44.279684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03913","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":"2026-05-18T00:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NlBsRLXfrmywtYVSPEXELxlgcmpYvlrSWPmGAYCxXY9UECgvC2/YgbCVW8nq0hkOw/8mT0HUJDiU2WS52dB0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:14:18.705039Z"},"content_sha256":"7fc78a5ff8f44bfa688630f065785b312f4b22397718799fb620817bef88d454","schema_version":"1.0","event_id":"sha256:7fc78a5ff8f44bfa688630f065785b312f4b22397718799fb620817bef88d454"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KEAOU4DWHUF6TUEZKKDDTFRZBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analyzing the Noise Robustness of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hang Su, Jun Zhu, Kelei Cao, Mengchen Liu, Shixia Liu","submitted_at":"2018-10-09T11:13:44Z","abstract_excerpt":"Deep neural networks (DNNs) are vulnerable to maliciously generated adversarial examples. These examples are intentionally designed by making imperceptible perturbations and often mislead a DNN into making an incorrect prediction. This phenomenon means that there is significant risk in applying DNNs to safety-critical applications, such as driverless cars. To address this issue, we present a visual analytics approach to explain the primary cause of the wrong predictions introduced by adversarial examples. The key is to analyze the datapaths of the adversarial examples and compare them with tho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03913","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":"2026-05-18T00:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ehiamcmxDJOWs/45pvD/dZXKFNz8M27kucgG77Ob8go3+2s6/56zrsNvOQMqOpSpl+YLD+GG1pdVGCUyoayCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:14:18.705397Z"},"content_sha256":"1a9cd7faa411a437a46c5ac77e887a8e2b26b61485fae13316410f30af777043","schema_version":"1.0","event_id":"sha256:1a9cd7faa411a437a46c5ac77e887a8e2b26b61485fae13316410f30af777043"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KEAOU4DWHUF6TUEZKKDDTFRZBB/bundle.json","state_url":"https://pith.science/pith/KEAOU4DWHUF6TUEZKKDDTFRZBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KEAOU4DWHUF6TUEZKKDDTFRZBB/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":"2026-06-03T07:14:18Z","links":{"resolver":"https://pith.science/pith/KEAOU4DWHUF6TUEZKKDDTFRZBB","bundle":"https://pith.science/pith/KEAOU4DWHUF6TUEZKKDDTFRZBB/bundle.json","state":"https://pith.science/pith/KEAOU4DWHUF6TUEZKKDDTFRZBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KEAOU4DWHUF6TUEZKKDDTFRZBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KEAOU4DWHUF6TUEZKKDDTFRZBB","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":"ef31f5bc2987882839bfdb29da41cf6a750da5f678ec265345ebd321faf6361f","cross_cats_sorted":["cs.HC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T11:13:44Z","title_canon_sha256":"1b0831ad27f2435c825b04b46d3721f625a15232e457633637d9ffe2506283f5"},"schema_version":"1.0","source":{"id":"1810.03913","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03913","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03913v1","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03913","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"KEAOU4DWHUF6","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KEAOU4DWHUF6TUEZ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KEAOU4DW","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:1a9cd7faa411a437a46c5ac77e887a8e2b26b61485fae13316410f30af777043","target":"graph","created_at":"2026-05-18T00:03:44Z","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 (DNNs) are vulnerable to maliciously generated adversarial examples. These examples are intentionally designed by making imperceptible perturbations and often mislead a DNN into making an incorrect prediction. This phenomenon means that there is significant risk in applying DNNs to safety-critical applications, such as driverless cars. To address this issue, we present a visual analytics approach to explain the primary cause of the wrong predictions introduced by adversarial examples. The key is to analyze the datapaths of the adversarial examples and compare them with tho","authors_text":"Hang Su, Jun Zhu, Kelei Cao, Mengchen Liu, Shixia Liu","cross_cats":["cs.HC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T11:13:44Z","title":"Analyzing the Noise Robustness of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03913","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":"sha256:7fc78a5ff8f44bfa688630f065785b312f4b22397718799fb620817bef88d454","target":"record","created_at":"2026-05-18T00:03:44Z","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":"ef31f5bc2987882839bfdb29da41cf6a750da5f678ec265345ebd321faf6361f","cross_cats_sorted":["cs.HC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T11:13:44Z","title_canon_sha256":"1b0831ad27f2435c825b04b46d3721f625a15232e457633637d9ffe2506283f5"},"schema_version":"1.0","source":{"id":"1810.03913","kind":"arxiv","version":1}},"canonical_sha256":"5100ea70763d0be9d099528639963908673aa5aa1a950f24fc176fab9176c76b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5100ea70763d0be9d099528639963908673aa5aa1a950f24fc176fab9176c76b","first_computed_at":"2026-05-18T00:03:44.279684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:44.279684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GkmB/2Jpx5rnXT44IUy4H80r4jK06m9f2Ksx982eUFzItCzMIygVGfHhHrDL4kDywcNKdOsSOJI2PG/Kg13iAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:44.280095Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03913","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fc78a5ff8f44bfa688630f065785b312f4b22397718799fb620817bef88d454","sha256:1a9cd7faa411a437a46c5ac77e887a8e2b26b61485fae13316410f30af777043"],"state_sha256":"0d58188eeb8bf27b52786500748b41a9414451391f51be96b56798b4244bcff8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7uQJNCYv3ZK37jMS6AuAJGhgpFqNK7HrEeXL9gFHGRwj3YHTWUdNBCQC8uyPsZDmc4SOS1qxTMNGjo1CyoCeDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:14:18.707341Z","bundle_sha256":"d5f5ecca1cbf32686e235e6313e10d8aab5a730420eec51c16ef2880df420765"}}