{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2ZBOLIFMVC3KFQLPFBRWIRL2FE","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":"b692459447d687af556336c9c41113f3a5f0a0e6fa2e3f6da08ea35d14a9f2aa","cross_cats_sorted":["cs.CR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T17:36:15Z","title_canon_sha256":"0c167f77f3a008a965a182c488aeb133442bede7f5ddf6f6b74414e2d34a5eac"},"schema_version":"1.0","source":{"id":"2203.17209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.17209","created_at":"2026-07-05T05:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"2203.17209v2","created_at":"2026-07-05T05:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17209","created_at":"2026-07-05T05:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"2ZBOLIFMVC3K","created_at":"2026-07-05T05:34:45Z"},{"alias_kind":"pith_short_16","alias_value":"2ZBOLIFMVC3KFQLP","created_at":"2026-07-05T05:34:45Z"},{"alias_kind":"pith_short_8","alias_value":"2ZBOLIFM","created_at":"2026-07-05T05:34:45Z"}],"graph_snapshots":[{"event_id":"sha256:498af1d7fdf208b8eb526d74eaf072ced3b09d77370193feb2170f4d4cf56673","target":"graph","created_at":"2026-07-05T05:34:45Z","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/2203.17209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A substantial body of empirical work documents the lack of robustness in deep learning models to adversarial examples. Recent theoretical work proved that adversarial examples are ubiquitous in two-layers networks with sub-exponential width and ReLU or smooth activations, and multi-layer ReLU networks with sub-exponential width. We present a result of the same type, with no restriction on width and for general locally Lipschitz continuous activations.\n  More precisely, given a neural network $f(\\,\\cdot\\,;{\\boldsymbol \\theta})$ with random weights ${\\boldsymbol \\theta}$, and feature vector ${\\b","authors_text":"Andrea Montanari, Yuchen Wu","cross_cats":["cs.CR","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T17:36:15Z","title":"Adversarial Examples in Random Neural Networks with General Activations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17209","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":"sha256:6d2c4994d060597cb6f0de469370544a7d4776c4b88756bed2943f0ba557178b","target":"record","created_at":"2026-07-05T05:34:45Z","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":"b692459447d687af556336c9c41113f3a5f0a0e6fa2e3f6da08ea35d14a9f2aa","cross_cats_sorted":["cs.CR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T17:36:15Z","title_canon_sha256":"0c167f77f3a008a965a182c488aeb133442bede7f5ddf6f6b74414e2d34a5eac"},"schema_version":"1.0","source":{"id":"2203.17209","kind":"arxiv","version":2}},"canonical_sha256":"d642e5a0aca8b6a2c16f286364457a2933bff22a3f03a8be1bf36adf07a96b02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d642e5a0aca8b6a2c16f286364457a2933bff22a3f03a8be1bf36adf07a96b02","first_computed_at":"2026-07-05T05:34:45.591072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:34:45.591072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w3VWKatiRoz1Q111gUL1C9E4Cx/7/hNt782e1Akl8UDWP3Ma2+vPuerA78Qkd1bm9nlJzZ5blclQ24lPbYhMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:34:45.591558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.17209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d2c4994d060597cb6f0de469370544a7d4776c4b88756bed2943f0ba557178b","sha256:498af1d7fdf208b8eb526d74eaf072ced3b09d77370193feb2170f4d4cf56673"],"state_sha256":"df76a9b26122fb61944ba062f2edb79233179301a80a94ab9a8300bdeea6b8cd"}