{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KYIMFSJUKGHW3RFE6TWNNUD4FH","short_pith_number":"pith:KYIMFSJU","schema_version":"1.0","canonical_sha256":"5610c2c934518f6dc4a4f4ecd6d07c29c331c0f6cfbe555bd0014c81baee9345","source":{"kind":"arxiv","id":"1812.08329","version":2},"attestation_state":"computed","paper":{"title":"PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ivan Oseledets, Lam M. Nguyen, Luca Daniel, Mark S. Squillante, Pin-Yu Chen, Tsui-Wei Weng","submitted_at":"2018-12-18T18:59:38Z","abstract_excerpt":"With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature merely focuses on the \\textit{worst-case} setting where the input of the neural network is perturbed with noises that are constrained within an $\\ell_p$ ball; and several algorithms have been proposed to compute certified lower bounds of minimum adversarial distortion based on such worst-case analysis. In this paper, we address these limitations and extend t"},"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":"1812.08329","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T18:59:38Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"78d933d8f99dde17674ad4fe760d5e26a0f81df96ee06aec872059d5f29da520","abstract_canon_sha256":"97ab019179ab51a7b93874ffdabed83b06f85659937c9ce454149f1c564aee6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:52.493339Z","signature_b64":"bqB9DpOuUbHjE35q6AA0JrBaB2VAyWm/3YZ3vLFAgsV/NTAGX/QhvLtOBYvYXahQXy0VNp+BEY6sAuEjKVqjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5610c2c934518f6dc4a4f4ecd6d07c29c331c0f6cfbe555bd0014c81baee9345","last_reissued_at":"2026-05-17T23:56:52.492813Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:52.492813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ivan Oseledets, Lam M. Nguyen, Luca Daniel, Mark S. Squillante, Pin-Yu Chen, Tsui-Wei Weng","submitted_at":"2018-12-18T18:59:38Z","abstract_excerpt":"With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature merely focuses on the \\textit{worst-case} setting where the input of the neural network is perturbed with noises that are constrained within an $\\ell_p$ ball; and several algorithms have been proposed to compute certified lower bounds of minimum adversarial distortion based on such worst-case analysis. In this paper, we address these limitations and extend t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08329","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":"1812.08329","created_at":"2026-05-17T23:56:52.492892+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08329v2","created_at":"2026-05-17T23:56:52.492892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08329","created_at":"2026-05-17T23:56:52.492892+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYIMFSJUKGHW","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYIMFSJUKGHW3RFE","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYIMFSJU","created_at":"2026-05-18T12:32:33.847187+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/KYIMFSJUKGHW3RFE6TWNNUD4FH","json":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH.json","graph_json":"https://pith.science/api/pith-number/KYIMFSJUKGHW3RFE6TWNNUD4FH/graph.json","events_json":"https://pith.science/api/pith-number/KYIMFSJUKGHW3RFE6TWNNUD4FH/events.json","paper":"https://pith.science/paper/KYIMFSJU"},"agent_actions":{"view_html":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH","download_json":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH.json","view_paper":"https://pith.science/paper/KYIMFSJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08329&json=true","fetch_graph":"https://pith.science/api/pith-number/KYIMFSJUKGHW3RFE6TWNNUD4FH/graph.json","fetch_events":"https://pith.science/api/pith-number/KYIMFSJUKGHW3RFE6TWNNUD4FH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH/action/storage_attestation","attest_author":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH/action/author_attestation","sign_citation":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH/action/citation_signature","submit_replication":"https://pith.science/pith/KYIMFSJUKGHW3RFE6TWNNUD4FH/action/replication_record"}},"created_at":"2026-05-17T23:56:52.492892+00:00","updated_at":"2026-05-17T23:56:52.492892+00:00"}