{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:D24GBLZ2JWYV3SDUQ5BSJYNXUI","short_pith_number":"pith:D24GBLZ2","schema_version":"1.0","canonical_sha256":"1eb860af3a4db15dc874874324e1b7a222ea661542e1a8ec1c053c4a3bd8efff","source":{"kind":"arxiv","id":"1709.03698","version":2},"attestation_state":"computed","paper":{"title":"Reversible Architectures for Arbitrarily Deep Residual Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Chang, David Begert, Eldad Haber, Elliot Holtham, Lars Ruthotto, Lili Meng","submitted_at":"2017-09-12T05:41:13Z","abstract_excerpt":"Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper and wider architectures. In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been studied in mathematics and physics with rich theoretical and empirical success. From this interpretation, we develop a theoretical framework on stability and reversibility of deep neural networks, and derive three reversible neural network architectures that can go arbitrarily dee"},"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":"1709.03698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-12T05:41:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ee0c04cbb56ecb2a8019d0e2ae66b276116a423458e5896c572ea3af49af254c","abstract_canon_sha256":"ed693cc0ccfc8727a136197aa7b0933e446d11c70cbc7fc8afce195518964206"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:16.391845Z","signature_b64":"+zZtwN+nbgTdeHNXjEg0gmykUDMYoXslIpMeffnOSNIyQ5OLXUgq+PyTg/L0p1DBXILqjZdZQMbyIgPKWy55Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eb860af3a4db15dc874874324e1b7a222ea661542e1a8ec1c053c4a3bd8efff","last_reissued_at":"2026-05-18T00:30:16.391122Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:16.391122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reversible Architectures for Arbitrarily Deep Residual Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Chang, David Begert, Eldad Haber, Elliot Holtham, Lars Ruthotto, Lili Meng","submitted_at":"2017-09-12T05:41:13Z","abstract_excerpt":"Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper and wider architectures. In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been studied in mathematics and physics with rich theoretical and empirical success. From this interpretation, we develop a theoretical framework on stability and reversibility of deep neural networks, and derive three reversible neural network architectures that can go arbitrarily dee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03698","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":"1709.03698","created_at":"2026-05-18T00:30:16.391227+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.03698v2","created_at":"2026-05-18T00:30:16.391227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03698","created_at":"2026-05-18T00:30:16.391227+00:00"},{"alias_kind":"pith_short_12","alias_value":"D24GBLZ2JWYV","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"D24GBLZ2JWYV3SDU","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"D24GBLZ2","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1806.07366","citing_title":"Neural Ordinary Differential Equations","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI","json":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI.json","graph_json":"https://pith.science/api/pith-number/D24GBLZ2JWYV3SDUQ5BSJYNXUI/graph.json","events_json":"https://pith.science/api/pith-number/D24GBLZ2JWYV3SDUQ5BSJYNXUI/events.json","paper":"https://pith.science/paper/D24GBLZ2"},"agent_actions":{"view_html":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI","download_json":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI.json","view_paper":"https://pith.science/paper/D24GBLZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.03698&json=true","fetch_graph":"https://pith.science/api/pith-number/D24GBLZ2JWYV3SDUQ5BSJYNXUI/graph.json","fetch_events":"https://pith.science/api/pith-number/D24GBLZ2JWYV3SDUQ5BSJYNXUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI/action/storage_attestation","attest_author":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI/action/author_attestation","sign_citation":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI/action/citation_signature","submit_replication":"https://pith.science/pith/D24GBLZ2JWYV3SDUQ5BSJYNXUI/action/replication_record"}},"created_at":"2026-05-18T00:30:16.391227+00:00","updated_at":"2026-05-18T00:30:16.391227+00:00"}