{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:F6EJHM2LD6NC4O5TFW7WXWJFUO","short_pith_number":"pith:F6EJHM2L","schema_version":"1.0","canonical_sha256":"2f8893b34b1f9a2e3bb32dbf6bd925a3b7ca3c6f2cd589d1cce5054f05f72d15","source":{"kind":"arxiv","id":"1811.03571","version":2},"attestation_state":"computed","paper":{"title":"Intrinsic Geometric Vulnerability of High-Dimensional Artificial Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guido Sanguinetti, Luca Bortolussi","submitted_at":"2018-11-08T17:51:27Z","abstract_excerpt":"The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence indicates that the high predictive performance is often paired with low robustness, making AI systems potentially vulnerable to adversarial attacks. In this report, we provide a simple intuitive argument suggesting that high performance and vulnerability are intrinsically coupled, and largely dependent on the geometry of typical, high-dimensional data sets. "},"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":"1811.03571","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-08T17:51:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ff5235fd8a5a8f59b20d6b57734f4ca8171cd60a24d125c9ab6040807252455a","abstract_canon_sha256":"90f870455274befbdc77a4a9cbed8ef1b7df846191b05f3db0ea09fce1e0fc89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:38.275362Z","signature_b64":"lDp7TvKRRYnYuOzFKYHJ3rjSWRDYWk7u2Y62CTfLtIhKo9RQMTJkBp8vRGvQf5Yq+hZcU4W+HPpHt6FkgvO4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f8893b34b1f9a2e3bb32dbf6bd925a3b7ca3c6f2cd589d1cce5054f05f72d15","last_reissued_at":"2026-05-17T23:55:38.274899Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:38.274899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Geometric Vulnerability of High-Dimensional Artificial Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guido Sanguinetti, Luca Bortolussi","submitted_at":"2018-11-08T17:51:27Z","abstract_excerpt":"The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence indicates that the high predictive performance is often paired with low robustness, making AI systems potentially vulnerable to adversarial attacks. In this report, we provide a simple intuitive argument suggesting that high performance and vulnerability are intrinsically coupled, and largely dependent on the geometry of typical, high-dimensional data sets. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03571","kind":"arxiv","version":2},"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":"1811.03571","created_at":"2026-05-17T23:55:38.274981+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.03571v2","created_at":"2026-05-17T23:55:38.274981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03571","created_at":"2026-05-17T23:55:38.274981+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6EJHM2LD6NC","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6EJHM2LD6NC4O5T","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6EJHM2L","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/F6EJHM2LD6NC4O5TFW7WXWJFUO","json":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO.json","graph_json":"https://pith.science/api/pith-number/F6EJHM2LD6NC4O5TFW7WXWJFUO/graph.json","events_json":"https://pith.science/api/pith-number/F6EJHM2LD6NC4O5TFW7WXWJFUO/events.json","paper":"https://pith.science/paper/F6EJHM2L"},"agent_actions":{"view_html":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO","download_json":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO.json","view_paper":"https://pith.science/paper/F6EJHM2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.03571&json=true","fetch_graph":"https://pith.science/api/pith-number/F6EJHM2LD6NC4O5TFW7WXWJFUO/graph.json","fetch_events":"https://pith.science/api/pith-number/F6EJHM2LD6NC4O5TFW7WXWJFUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO/action/storage_attestation","attest_author":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO/action/author_attestation","sign_citation":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO/action/citation_signature","submit_replication":"https://pith.science/pith/F6EJHM2LD6NC4O5TFW7WXWJFUO/action/replication_record"}},"created_at":"2026-05-17T23:55:38.274981+00:00","updated_at":"2026-05-17T23:55:38.274981+00:00"}