{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EKKFSFQJLHCAKDWYOPRS27FCRP","short_pith_number":"pith:EKKFSFQJ","schema_version":"1.0","canonical_sha256":"229459160959c4050ed873e32d7ca28bdcf92af8f1d47409c17d05f1772e8bad","source":{"kind":"arxiv","id":"1804.11313","version":1},"attestation_state":"computed","paper":{"title":"How Robust are Deep Neural Networks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","stat.ML"],"primary_cat":"cs.NE","authors_text":"Biswa Sengupta, Karl J. Friston","submitted_at":"2018-04-30T16:39:31Z","abstract_excerpt":"Convolutional and Recurrent, deep neural networks have been successful in machine learning systems for computer vision, reinforcement learning, and other allied fields. However, the robustness of such neural networks is seldom apprised, especially after high classification accuracy has been attained. In this paper, we evaluate the robustness of three recurrent neural networks to tiny perturbations, on three widely used datasets, to argue that high accuracy does not always mean a stable and a robust (to bounded perturbations, adversarial attacks, etc.) system. Especially, normalizing the spectr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.11313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-30T16:39:31Z","cross_cats_sorted":["math.DS","stat.ML"],"title_canon_sha256":"a8b44ab164b3ce59fa54d613af913686265abbb9d9f680aa6899aad2eb857c59","abstract_canon_sha256":"167b4a813f6be657b659c3f618e734497bcedabcf6e2152fa57c8999f7be5a78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:14.021466Z","signature_b64":"SsMHMOqH4eFBmHf0UOTyezeY9WPDkfrwI3GvC7qwEIVQLCJ2uiso8MJXNtoJfeO/HWgiogpViNeanNz9SjEfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"229459160959c4050ed873e32d7ca28bdcf92af8f1d47409c17d05f1772e8bad","last_reissued_at":"2026-05-18T00:17:14.020988Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:14.020988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Robust are Deep Neural Networks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","stat.ML"],"primary_cat":"cs.NE","authors_text":"Biswa Sengupta, Karl J. Friston","submitted_at":"2018-04-30T16:39:31Z","abstract_excerpt":"Convolutional and Recurrent, deep neural networks have been successful in machine learning systems for computer vision, reinforcement learning, and other allied fields. However, the robustness of such neural networks is seldom apprised, especially after high classification accuracy has been attained. In this paper, we evaluate the robustness of three recurrent neural networks to tiny perturbations, on three widely used datasets, to argue that high accuracy does not always mean a stable and a robust (to bounded perturbations, adversarial attacks, etc.) system. Especially, normalizing the spectr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11313","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.11313","created_at":"2026-05-18T00:17:14.021051+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.11313v1","created_at":"2026-05-18T00:17:14.021051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11313","created_at":"2026-05-18T00:17:14.021051+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKKFSFQJLHCA","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKKFSFQJLHCAKDWY","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKKFSFQJ","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP","json":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP.json","graph_json":"https://pith.science/api/pith-number/EKKFSFQJLHCAKDWYOPRS27FCRP/graph.json","events_json":"https://pith.science/api/pith-number/EKKFSFQJLHCAKDWYOPRS27FCRP/events.json","paper":"https://pith.science/paper/EKKFSFQJ"},"agent_actions":{"view_html":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP","download_json":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP.json","view_paper":"https://pith.science/paper/EKKFSFQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.11313&json=true","fetch_graph":"https://pith.science/api/pith-number/EKKFSFQJLHCAKDWYOPRS27FCRP/graph.json","fetch_events":"https://pith.science/api/pith-number/EKKFSFQJLHCAKDWYOPRS27FCRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP/action/storage_attestation","attest_author":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP/action/author_attestation","sign_citation":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP/action/citation_signature","submit_replication":"https://pith.science/pith/EKKFSFQJLHCAKDWYOPRS27FCRP/action/replication_record"}},"created_at":"2026-05-18T00:17:14.021051+00:00","updated_at":"2026-05-18T00:17:14.021051+00:00"}