{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CWIK7VY2X3IFGZUGJDNZL4Z6AG","short_pith_number":"pith:CWIK7VY2","schema_version":"1.0","canonical_sha256":"1590afd71abed053668648db95f33e01b27c350686e5faf51c13a941c420e57e","source":{"kind":"arxiv","id":"2012.05981","version":3},"attestation_state":"computed","paper":{"title":"Certifying Incremental Quadratic Constraints for Neural Networks via Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Justin Ruths, Mahyar Fazlyab, Navid Hashemi","submitted_at":"2020-12-10T21:15:00Z","abstract_excerpt":"Abstracting neural networks with constraints they impose on their inputs and outputs can be very useful in the analysis of neural network classifiers and to derive optimization-based algorithms for certification of stability and robustness of feedback systems involving neural networks. In this paper, we propose a convex program, in the form of a Linear Matrix Inequality (LMI), to certify incremental quadratic constraints on the map of neural networks over a region of interest. These certificates can capture several useful properties such as (local) Lipschitz continuity, one-sided Lipschitz con"},"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":"2012.05981","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T21:15:00Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"0ec62d96211045dd8a07594fa73f4ec44f24b03f379e22ce97de856fa569f629","abstract_canon_sha256":"37d22efdb3533897ee893d52f7e5853476c31e9d54927e69006aa6913f7d01fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:31.793596Z","signature_b64":"by2UKHhkshdcEWMMGNZNaROidCfBTkx6KME3WH9FYczfjCJz9va/9aQ08JB3LetRlvUq/55WueHJJsedZKgzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1590afd71abed053668648db95f33e01b27c350686e5faf51c13a941c420e57e","last_reissued_at":"2026-07-05T02:36:31.793011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:31.793011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certifying Incremental Quadratic Constraints for Neural Networks via Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Justin Ruths, Mahyar Fazlyab, Navid Hashemi","submitted_at":"2020-12-10T21:15:00Z","abstract_excerpt":"Abstracting neural networks with constraints they impose on their inputs and outputs can be very useful in the analysis of neural network classifiers and to derive optimization-based algorithms for certification of stability and robustness of feedback systems involving neural networks. In this paper, we propose a convex program, in the form of a Linear Matrix Inequality (LMI), to certify incremental quadratic constraints on the map of neural networks over a region of interest. These certificates can capture several useful properties such as (local) Lipschitz continuity, one-sided Lipschitz con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05981","kind":"arxiv","version":3},"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/2012.05981/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":"2012.05981","created_at":"2026-07-05T02:36:31.793072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05981v3","created_at":"2026-07-05T02:36:31.793072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05981","created_at":"2026-07-05T02:36:31.793072+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWIK7VY2X3IF","created_at":"2026-07-05T02:36:31.793072+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWIK7VY2X3IFGZUG","created_at":"2026-07-05T02:36:31.793072+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWIK7VY2","created_at":"2026-07-05T02:36:31.793072+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/CWIK7VY2X3IFGZUGJDNZL4Z6AG","json":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG.json","graph_json":"https://pith.science/api/pith-number/CWIK7VY2X3IFGZUGJDNZL4Z6AG/graph.json","events_json":"https://pith.science/api/pith-number/CWIK7VY2X3IFGZUGJDNZL4Z6AG/events.json","paper":"https://pith.science/paper/CWIK7VY2"},"agent_actions":{"view_html":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG","download_json":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG.json","view_paper":"https://pith.science/paper/CWIK7VY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05981&json=true","fetch_graph":"https://pith.science/api/pith-number/CWIK7VY2X3IFGZUGJDNZL4Z6AG/graph.json","fetch_events":"https://pith.science/api/pith-number/CWIK7VY2X3IFGZUGJDNZL4Z6AG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG/action/storage_attestation","attest_author":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG/action/author_attestation","sign_citation":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG/action/citation_signature","submit_replication":"https://pith.science/pith/CWIK7VY2X3IFGZUGJDNZL4Z6AG/action/replication_record"}},"created_at":"2026-07-05T02:36:31.793072+00:00","updated_at":"2026-07-05T02:36:31.793072+00:00"}