{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IRQANXXOZMF4GNXBULOMWMQ4DY","short_pith_number":"pith:IRQANXXO","schema_version":"1.0","canonical_sha256":"446006deeecb0bc336e1a2dccb321c1e30f7bc5ee6e0cc5a11422b6177a59be0","source":{"kind":"arxiv","id":"1904.09959","version":2},"attestation_state":"computed","paper":{"title":"Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.PL","authors_text":"Greg Anderson, Isil Dillig, Shankara Pailoor, Swarat Chaudhuri","submitted_at":"2019-04-22T17:21:52Z","abstract_excerpt":"In recent years, the notion of local robustness (or robustness for short) has emerged as a desirable property of deep neural networks. Intuitively, robustness means that small perturbations to an input do not cause the network to perform misclassifications. In this paper, we present a novel algorithm for verifying robustness properties of neural networks. Our method synergistically combines gradient-based optimization methods for counterexample search with abstraction-based proof search to obtain a sound and ({\\delta}-)complete decision procedure. Our method also employs a data-driven approach"},"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":"1904.09959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2019-04-22T17:21:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7bc52fdb99d545d8d898af2001faf19c65092c89343f3d24451f584467fda0b0","abstract_canon_sha256":"330cf56e64643305861effe697d5a07e58f97f64f4c97c342f7d4d097e9360cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:15.465020Z","signature_b64":"G8HLQ1z51mx6HQZ4CiS0DnY24AfqvZsu9ZgpnqpzhAY9buNYBeclbkOIbf2fmrk6ZHUyMOkSc1n51ZfHuuxiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446006deeecb0bc336e1a2dccb321c1e30f7bc5ee6e0cc5a11422b6177a59be0","last_reissued_at":"2026-05-17T23:47:15.464604Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:15.464604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.PL","authors_text":"Greg Anderson, Isil Dillig, Shankara Pailoor, Swarat Chaudhuri","submitted_at":"2019-04-22T17:21:52Z","abstract_excerpt":"In recent years, the notion of local robustness (or robustness for short) has emerged as a desirable property of deep neural networks. Intuitively, robustness means that small perturbations to an input do not cause the network to perform misclassifications. In this paper, we present a novel algorithm for verifying robustness properties of neural networks. Our method synergistically combines gradient-based optimization methods for counterexample search with abstraction-based proof search to obtain a sound and ({\\delta}-)complete decision procedure. Our method also employs a data-driven approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09959","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":"1904.09959","created_at":"2026-05-17T23:47:15.464672+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09959v2","created_at":"2026-05-17T23:47:15.464672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09959","created_at":"2026-05-17T23:47:15.464672+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRQANXXOZMF4","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRQANXXOZMF4GNXB","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRQANXXO","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.06223","citing_title":"A Symbolic Neural Network Representation and its Application to Understanding, Verifying, and Patching Networks","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY","json":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY.json","graph_json":"https://pith.science/api/pith-number/IRQANXXOZMF4GNXBULOMWMQ4DY/graph.json","events_json":"https://pith.science/api/pith-number/IRQANXXOZMF4GNXBULOMWMQ4DY/events.json","paper":"https://pith.science/paper/IRQANXXO"},"agent_actions":{"view_html":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY","download_json":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY.json","view_paper":"https://pith.science/paper/IRQANXXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09959&json=true","fetch_graph":"https://pith.science/api/pith-number/IRQANXXOZMF4GNXBULOMWMQ4DY/graph.json","fetch_events":"https://pith.science/api/pith-number/IRQANXXOZMF4GNXBULOMWMQ4DY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY/action/storage_attestation","attest_author":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY/action/author_attestation","sign_citation":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY/action/citation_signature","submit_replication":"https://pith.science/pith/IRQANXXOZMF4GNXBULOMWMQ4DY/action/replication_record"}},"created_at":"2026-05-17T23:47:15.464672+00:00","updated_at":"2026-05-17T23:47:15.464672+00:00"}