{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2PEZSUF6LBAX6ZCBWN5LUDBAPW","short_pith_number":"pith:2PEZSUF6","canonical_record":{"source":{"id":"1711.06598","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-11-17T15:46:44Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"93f87c141cefb2fa452ab91a436ada58484a45b69ec5d3cb55ec3c2393eb4c5e","abstract_canon_sha256":"12c47bd75f29a803af7a749beaae22b6b792186ca1adcd8cd65246e9c0804183"},"schema_version":"1.0"},"canonical_sha256":"d3c99950be58417f6441b37aba0c207da744bab355fc4b20b1add99cd1ad204a","source":{"kind":"arxiv","id":"1711.06598","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06598","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06598v4","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06598","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"2PEZSUF6LBAX","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2PEZSUF6LBAX6ZCB","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2PEZSUF6","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2PEZSUF6LBAX6ZCBWN5LUDBAPW","target":"record","payload":{"canonical_record":{"source":{"id":"1711.06598","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-11-17T15:46:44Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"93f87c141cefb2fa452ab91a436ada58484a45b69ec5d3cb55ec3c2393eb4c5e","abstract_canon_sha256":"12c47bd75f29a803af7a749beaae22b6b792186ca1adcd8cd65246e9c0804183"},"schema_version":"1.0"},"canonical_sha256":"d3c99950be58417f6441b37aba0c207da744bab355fc4b20b1add99cd1ad204a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:03.199765Z","signature_b64":"ZhkDYxw48U8vAc6ukSzUmIZnxkj336xrCrelcvJwnx/V76TQyxOOVjx8o7lHve9TVIteWlqgVnnQQmBO+P7EBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3c99950be58417f6441b37aba0c207da744bab355fc4b20b1add99cd1ad204a","last_reissued_at":"2026-05-17T23:57:03.199092Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:03.199092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.06598","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gISUlMHbd4xQ2134w9iqeayXvyBm7xheW/N3BFsiFJz/k18Nar1vmox+ltxWF4dXM8GmHaB2nnVEUqAP2/S2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:38:51.331370Z"},"content_sha256":"ef43b48dfa45ed4cf5c9cfcc7223d3461f15269a09992b924b52813d922b3698","schema_version":"1.0","event_id":"sha256:ef43b48dfa45ed4cf5c9cfcc7223d3461f15269a09992b924b52813d922b3698"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2PEZSUF6LBAX6ZCBWN5LUDBAPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"David Pfaff, Kathrin Grosse, Michael Backes, Michael Thomas Smith","submitted_at":"2017-11-17T15:46:44Z","abstract_excerpt":"Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN), are primarily derived from empirical developments, and their security guarantees are often only justified retroactively. Many defenses therefore rely on hidden assumptions that are subsequently subverted by increasingly elaborate attacks. This is not surprising: deep learning notoriously lacks a comprehensive mathematical framework to provide meaningful gua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06598","kind":"arxiv","version":4},"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":"2026-05-17T23:57:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQzXJJaEjFpht8lZVG/ayOX02RWbiEScLWccZvGYgyyvKtJ8iKJqj4VjIP/6j+8BR5sF3mPljDaFnauYhJU1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:38:51.332022Z"},"content_sha256":"0ba9c3fd963d7b74ca32590f6b7b7012ac50422a981a2c6d4a47bb39279496f2","schema_version":"1.0","event_id":"sha256:0ba9c3fd963d7b74ca32590f6b7b7012ac50422a981a2c6d4a47bb39279496f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PEZSUF6LBAX6ZCBWN5LUDBAPW/bundle.json","state_url":"https://pith.science/pith/2PEZSUF6LBAX6ZCBWN5LUDBAPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PEZSUF6LBAX6ZCBWN5LUDBAPW/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":"2026-05-27T14:38:51Z","links":{"resolver":"https://pith.science/pith/2PEZSUF6LBAX6ZCBWN5LUDBAPW","bundle":"https://pith.science/pith/2PEZSUF6LBAX6ZCBWN5LUDBAPW/bundle.json","state":"https://pith.science/pith/2PEZSUF6LBAX6ZCBWN5LUDBAPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PEZSUF6LBAX6ZCBWN5LUDBAPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2PEZSUF6LBAX6ZCBWN5LUDBAPW","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":"12c47bd75f29a803af7a749beaae22b6b792186ca1adcd8cd65246e9c0804183","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-11-17T15:46:44Z","title_canon_sha256":"93f87c141cefb2fa452ab91a436ada58484a45b69ec5d3cb55ec3c2393eb4c5e"},"schema_version":"1.0","source":{"id":"1711.06598","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06598","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06598v4","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06598","created_at":"2026-05-17T23:57:03Z"},{"alias_kind":"pith_short_12","alias_value":"2PEZSUF6LBAX","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2PEZSUF6LBAX6ZCB","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2PEZSUF6","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:0ba9c3fd963d7b74ca32590f6b7b7012ac50422a981a2c6d4a47bb39279496f2","target":"graph","created_at":"2026-05-17T23:57:03Z","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":"Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN), are primarily derived from empirical developments, and their security guarantees are often only justified retroactively. Many defenses therefore rely on hidden assumptions that are subsequently subverted by increasingly elaborate attacks. This is not surprising: deep learning notoriously lacks a comprehensive mathematical framework to provide meaningful gua","authors_text":"David Pfaff, Kathrin Grosse, Michael Backes, Michael Thomas Smith","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-11-17T15:46:44Z","title":"How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06598","kind":"arxiv","version":4},"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:ef43b48dfa45ed4cf5c9cfcc7223d3461f15269a09992b924b52813d922b3698","target":"record","created_at":"2026-05-17T23:57:03Z","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":"12c47bd75f29a803af7a749beaae22b6b792186ca1adcd8cd65246e9c0804183","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-11-17T15:46:44Z","title_canon_sha256":"93f87c141cefb2fa452ab91a436ada58484a45b69ec5d3cb55ec3c2393eb4c5e"},"schema_version":"1.0","source":{"id":"1711.06598","kind":"arxiv","version":4}},"canonical_sha256":"d3c99950be58417f6441b37aba0c207da744bab355fc4b20b1add99cd1ad204a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3c99950be58417f6441b37aba0c207da744bab355fc4b20b1add99cd1ad204a","first_computed_at":"2026-05-17T23:57:03.199092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:03.199092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZhkDYxw48U8vAc6ukSzUmIZnxkj336xrCrelcvJwnx/V76TQyxOOVjx8o7lHve9TVIteWlqgVnnQQmBO+P7EBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:03.199765Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.06598","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef43b48dfa45ed4cf5c9cfcc7223d3461f15269a09992b924b52813d922b3698","sha256:0ba9c3fd963d7b74ca32590f6b7b7012ac50422a981a2c6d4a47bb39279496f2"],"state_sha256":"3b445e2a90e0a72fbe6f505b549b09530a9eb4dcd2f17b574ac360d6ef5bc735"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xptzqkE6GHYVIMSW4Lta1tx3oakTm1wcFJP5/Fc84eerBGvajgNh+JcB6/hiJTN8AOaQh7e3TAaUEdGwLKVBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:38:51.335269Z","bundle_sha256":"f0ca58baa9383509f948b14ca4ff43b683ea81b45b2ca784cc17fbb989cafcf0"}}