{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JPN6OZGTJN4FENBTFF7XBS4CIU","short_pith_number":"pith:JPN6OZGT","schema_version":"1.0","canonical_sha256":"4bdbe764d34b78523433297f70cb82452b8dead6b1a6f4afaea7e46e884d159a","source":{"kind":"arxiv","id":"1810.11783","version":2},"attestation_state":"computed","paper":{"title":"RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Cho-Jui Hsieh, Huan Zhang, Pengchuan Zhang","submitted_at":"2018-10-28T09:25:08Z","abstract_excerpt":"The Jacobian matrix (or the gradient for single-output networks) is directly related to many important properties of neural networks, such as the function landscape, stationary points, (local) Lipschitz constants and robustness to adversarial attacks. In this paper, we propose a recursive algorithm, RecurJac, to compute both upper and lower bounds for each element in the Jacobian matrix of a neural network with respect to network's input, and the network can contain a wide range of activation functions. As a byproduct, we can efficiently obtain a (local) Lipschitz constant, which plays a cruci"},"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":"1810.11783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-28T09:25:08Z","cross_cats_sorted":["cs.AI","cs.LG","math.OC"],"title_canon_sha256":"43366f7e746b64924944159b28463b083d4ff2292d5f493e8fae5f6caa6d34fa","abstract_canon_sha256":"7be3e1dfe54457151672e0f30dee03d3a32efc25a96f1245af2547bb90b2d038"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:33.717389Z","signature_b64":"fafFJZDPlG9u+bGn/fH3F7tcemahu0hfvDkXhyxzXBtfYczOeII8XziFrHnNP7n0hPz3l8YgY/oGqih58sGaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bdbe764d34b78523433297f70cb82452b8dead6b1a6f4afaea7e46e884d159a","last_reissued_at":"2026-05-17T23:52:33.717001Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:33.717001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Cho-Jui Hsieh, Huan Zhang, Pengchuan Zhang","submitted_at":"2018-10-28T09:25:08Z","abstract_excerpt":"The Jacobian matrix (or the gradient for single-output networks) is directly related to many important properties of neural networks, such as the function landscape, stationary points, (local) Lipschitz constants and robustness to adversarial attacks. In this paper, we propose a recursive algorithm, RecurJac, to compute both upper and lower bounds for each element in the Jacobian matrix of a neural network with respect to network's input, and the network can contain a wide range of activation functions. As a byproduct, we can efficiently obtain a (local) Lipschitz constant, which plays a cruci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11783","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":"1810.11783","created_at":"2026-05-17T23:52:33.717073+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11783v2","created_at":"2026-05-17T23:52:33.717073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11783","created_at":"2026-05-17T23:52:33.717073+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPN6OZGTJN4F","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPN6OZGTJN4FENBT","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPN6OZGT","created_at":"2026-05-18T12:32:31.084164+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/JPN6OZGTJN4FENBTFF7XBS4CIU","json":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU.json","graph_json":"https://pith.science/api/pith-number/JPN6OZGTJN4FENBTFF7XBS4CIU/graph.json","events_json":"https://pith.science/api/pith-number/JPN6OZGTJN4FENBTFF7XBS4CIU/events.json","paper":"https://pith.science/paper/JPN6OZGT"},"agent_actions":{"view_html":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU","download_json":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU.json","view_paper":"https://pith.science/paper/JPN6OZGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11783&json=true","fetch_graph":"https://pith.science/api/pith-number/JPN6OZGTJN4FENBTFF7XBS4CIU/graph.json","fetch_events":"https://pith.science/api/pith-number/JPN6OZGTJN4FENBTFF7XBS4CIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU/action/storage_attestation","attest_author":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU/action/author_attestation","sign_citation":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU/action/citation_signature","submit_replication":"https://pith.science/pith/JPN6OZGTJN4FENBTFF7XBS4CIU/action/replication_record"}},"created_at":"2026-05-17T23:52:33.717073+00:00","updated_at":"2026-05-17T23:52:33.717073+00:00"}