{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SHSNC476V3WPSFY3OFZSWLVJ6Z","short_pith_number":"pith:SHSNC476","schema_version":"1.0","canonical_sha256":"91e4d173feaeecf9171b71732b2ea9f6726dc25a0c387cf1e3b3fbd3c58f1107","source":{"kind":"arxiv","id":"2508.11432","version":1},"attestation_state":"computed","paper":{"title":"Robust Convolution Neural ODEs via Contractivity-promoting regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Giancarlo Ferrari-Trecate, Liang Xu, Muhammad Zakwan","submitted_at":"2025-08-15T12:18:44Z","abstract_excerpt":"Neural networks can be fragile to input noise and adversarial attacks.\n  In this work, we consider Convolutional Neural Ordinary Differential Equations (NODEs), a family of continuous-depth neural networks represented by dynamical systems, and propose to use contraction theory to improve their robustness.\n  For a contractive dynamical system two trajectories starting from different initial conditions converge to each other exponentially fast.\n  Contractive Convolutional NODEs can enjoy increased robustness as slight perturbations of the features do not cause a significant change in the output."},"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":"2508.11432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T12:18:44Z","cross_cats_sorted":["cs.CV","cs.SY","eess.SY"],"title_canon_sha256":"9850f18602f4169a781a66d0b31f6b49322da5d4702dcc7191c6d1ce5f1560d9","abstract_canon_sha256":"6564685194922040b3abfe7787d96b6d684eaf660e93f174bd358cedb7b9cc0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:33.357756Z","signature_b64":"eLVNYn58zpJfqcG8PRCOMYJGVZ0dW4Ynzsu8CElGfXsyt2fmk/J2XnypZKjOBeJyIyQ5YpQp7kOdaLt5xASFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91e4d173feaeecf9171b71732b2ea9f6726dc25a0c387cf1e3b3fbd3c58f1107","last_reissued_at":"2026-07-05T11:54:33.357336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:33.357336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Convolution Neural ODEs via Contractivity-promoting regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Giancarlo Ferrari-Trecate, Liang Xu, Muhammad Zakwan","submitted_at":"2025-08-15T12:18:44Z","abstract_excerpt":"Neural networks can be fragile to input noise and adversarial attacks.\n  In this work, we consider Convolutional Neural Ordinary Differential Equations (NODEs), a family of continuous-depth neural networks represented by dynamical systems, and propose to use contraction theory to improve their robustness.\n  For a contractive dynamical system two trajectories starting from different initial conditions converge to each other exponentially fast.\n  Contractive Convolutional NODEs can enjoy increased robustness as slight perturbations of the features do not cause a significant change in the output."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11432","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.11432/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":"2508.11432","created_at":"2026-07-05T11:54:33.357394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11432v1","created_at":"2026-07-05T11:54:33.357394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11432","created_at":"2026-07-05T11:54:33.357394+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHSNC476V3WP","created_at":"2026-07-05T11:54:33.357394+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHSNC476V3WPSFY3","created_at":"2026-07-05T11:54:33.357394+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHSNC476","created_at":"2026-07-05T11:54:33.357394+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/SHSNC476V3WPSFY3OFZSWLVJ6Z","json":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z.json","graph_json":"https://pith.science/api/pith-number/SHSNC476V3WPSFY3OFZSWLVJ6Z/graph.json","events_json":"https://pith.science/api/pith-number/SHSNC476V3WPSFY3OFZSWLVJ6Z/events.json","paper":"https://pith.science/paper/SHSNC476"},"agent_actions":{"view_html":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z","download_json":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z.json","view_paper":"https://pith.science/paper/SHSNC476","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11432&json=true","fetch_graph":"https://pith.science/api/pith-number/SHSNC476V3WPSFY3OFZSWLVJ6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/SHSNC476V3WPSFY3OFZSWLVJ6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z/action/storage_attestation","attest_author":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z/action/author_attestation","sign_citation":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z/action/citation_signature","submit_replication":"https://pith.science/pith/SHSNC476V3WPSFY3OFZSWLVJ6Z/action/replication_record"}},"created_at":"2026-07-05T11:54:33.357394+00:00","updated_at":"2026-07-05T11:54:33.357394+00:00"}