{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:F645ZAEQKUZ7YSJMNEOYMOQQNB","short_pith_number":"pith:F645ZAEQ","schema_version":"1.0","canonical_sha256":"2fb9dc80905533fc492c691d863a106850e30214b5d45f31816ed0c12d1b1ae6","source":{"kind":"arxiv","id":"1805.02242","version":1},"attestation_state":"computed","paper":{"title":"Reachability Analysis of Deep Neural Networks with Provable Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marta Kwiatkowska, Wenjie Ruan, Xiaowei Huang","submitted_at":"2018-05-06T16:33:52Z","abstract_excerpt":"Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the function are Lipschitz continuous, all values in the interval between the lower and upper bound are reachable. We show how to obtain the safety verification problem, the output range analysis problem and a robustness measure by instantiating the reachability problem. We present a"},"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":"1805.02242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-06T16:33:52Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2f430979f773db0431f3458db98f762268074dabc84450da869dce13af8f0238","abstract_canon_sha256":"9beec84fcc954c246de07a7d38eb2ee6b666c8127eefb5d8c4b97e4211fd8177"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:40.465442Z","signature_b64":"yY04RmADl3RHkbxz9uGC37HcSONwVerI0nwzj21sn2QpbvWxZygDu9WIUKSIwHkN8eG4Cp1HqvY6QjcfQvQKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fb9dc80905533fc492c691d863a106850e30214b5d45f31816ed0c12d1b1ae6","last_reissued_at":"2026-05-18T00:16:40.464887Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:40.464887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reachability Analysis of Deep Neural Networks with Provable Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marta Kwiatkowska, Wenjie Ruan, Xiaowei Huang","submitted_at":"2018-05-06T16:33:52Z","abstract_excerpt":"Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the function are Lipschitz continuous, all values in the interval between the lower and upper bound are reachable. We show how to obtain the safety verification problem, the output range analysis problem and a robustness measure by instantiating the reachability problem. We present a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02242","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":""},"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":"1805.02242","created_at":"2026-05-18T00:16:40.464974+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.02242v1","created_at":"2026-05-18T00:16:40.464974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02242","created_at":"2026-05-18T00:16:40.464974+00:00"},{"alias_kind":"pith_short_12","alias_value":"F645ZAEQKUZ7","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"F645ZAEQKUZ7YSJM","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"F645ZAEQ","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10654","citing_title":"ReachNN: Reachability Analysis of Neural-Network Controlled Systems","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2203.07941","citing_title":"Reachability In Simple Neural Networks","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB","json":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB.json","graph_json":"https://pith.science/api/pith-number/F645ZAEQKUZ7YSJMNEOYMOQQNB/graph.json","events_json":"https://pith.science/api/pith-number/F645ZAEQKUZ7YSJMNEOYMOQQNB/events.json","paper":"https://pith.science/paper/F645ZAEQ"},"agent_actions":{"view_html":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB","download_json":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB.json","view_paper":"https://pith.science/paper/F645ZAEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.02242&json=true","fetch_graph":"https://pith.science/api/pith-number/F645ZAEQKUZ7YSJMNEOYMOQQNB/graph.json","fetch_events":"https://pith.science/api/pith-number/F645ZAEQKUZ7YSJMNEOYMOQQNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB/action/storage_attestation","attest_author":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB/action/author_attestation","sign_citation":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB/action/citation_signature","submit_replication":"https://pith.science/pith/F645ZAEQKUZ7YSJMNEOYMOQQNB/action/replication_record"}},"created_at":"2026-05-18T00:16:40.464974+00:00","updated_at":"2026-05-18T00:16:40.464974+00:00"}