{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SNK7A4JQTAIX6JGF5BTPPRWN4N","short_pith_number":"pith:SNK7A4JQ","schema_version":"1.0","canonical_sha256":"9355f0713098117f24c5e866f7c6cde35ac89e159a9db2c8ccfdca8332e41cdc","source":{"kind":"arxiv","id":"2010.15487","version":1},"attestation_state":"computed","paper":{"title":"Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Andrea Migliorati, Arslan Ali, Enrico Magli, Tiziano Bianchi","submitted_at":"2020-10-29T11:15:17Z","abstract_excerpt":"Deep learning has shown outstanding performance in several applications including image classification. However, deep classifiers are known to be highly vulnerable to adversarial attacks, in that a minor perturbation of the input can easily lead to an error. Providing robustness to adversarial attacks is a very challenging task especially in problems involving a large number of classes, as it typically comes at the expense of an accuracy decrease. In this work, we propose the Gaussian class-conditional simplex (GCCS) loss: a novel approach for training deep robust multiclass classifiers that p"},"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":"2010.15487","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-29T11:15:17Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"7c5ab964a10a87b0eceebbd771b684b43c9ef41d772929311e156dbe188a67f9","abstract_canon_sha256":"91c716ed49ef4fc4f412163d3e31f57784c28df9d2a0fa72a841d188e1f04902"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:37.526017Z","signature_b64":"UpJn6AICbNlG3QMSOh3ZWZiRjmdcUlqvIhg/NdvAy+Cpcy4ob2ihfNluqP3Xyc9whc2IPFkrrhOYg79eB/s6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9355f0713098117f24c5e866f7c6cde35ac89e159a9db2c8ccfdca8332e41cdc","last_reissued_at":"2026-07-05T01:47:37.525652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:37.525652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Andrea Migliorati, Arslan Ali, Enrico Magli, Tiziano Bianchi","submitted_at":"2020-10-29T11:15:17Z","abstract_excerpt":"Deep learning has shown outstanding performance in several applications including image classification. However, deep classifiers are known to be highly vulnerable to adversarial attacks, in that a minor perturbation of the input can easily lead to an error. Providing robustness to adversarial attacks is a very challenging task especially in problems involving a large number of classes, as it typically comes at the expense of an accuracy decrease. In this work, we propose the Gaussian class-conditional simplex (GCCS) loss: a novel approach for training deep robust multiclass classifiers that p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15487","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.15487/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2010.15487","created_at":"2026-07-05T01:47:37.525706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.15487v1","created_at":"2026-07-05T01:47:37.525706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15487","created_at":"2026-07-05T01:47:37.525706+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNK7A4JQTAIX","created_at":"2026-07-05T01:47:37.525706+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNK7A4JQTAIX6JGF","created_at":"2026-07-05T01:47:37.525706+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNK7A4JQ","created_at":"2026-07-05T01:47:37.525706+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/SNK7A4JQTAIX6JGF5BTPPRWN4N","json":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N.json","graph_json":"https://pith.science/api/pith-number/SNK7A4JQTAIX6JGF5BTPPRWN4N/graph.json","events_json":"https://pith.science/api/pith-number/SNK7A4JQTAIX6JGF5BTPPRWN4N/events.json","paper":"https://pith.science/paper/SNK7A4JQ"},"agent_actions":{"view_html":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N","download_json":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N.json","view_paper":"https://pith.science/paper/SNK7A4JQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.15487&json=true","fetch_graph":"https://pith.science/api/pith-number/SNK7A4JQTAIX6JGF5BTPPRWN4N/graph.json","fetch_events":"https://pith.science/api/pith-number/SNK7A4JQTAIX6JGF5BTPPRWN4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N/action/storage_attestation","attest_author":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N/action/author_attestation","sign_citation":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N/action/citation_signature","submit_replication":"https://pith.science/pith/SNK7A4JQTAIX6JGF5BTPPRWN4N/action/replication_record"}},"created_at":"2026-07-05T01:47:37.525706+00:00","updated_at":"2026-07-05T01:47:37.525706+00:00"}