{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7MEWCQ6NAUMO2ETFJU5PKQ2FNZ","short_pith_number":"pith:7MEWCQ6N","schema_version":"1.0","canonical_sha256":"fb096143cd0518ed12654d3af543456e61d09a0ef1372d7d29fee4dd59f099fa","source":{"kind":"arxiv","id":"1803.08203","version":1},"attestation_state":"computed","paper":{"title":"Residual Networks: Lyapunov Stability and Convex Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kamil Nar, Shankar Sastry","submitted_at":"2018-03-22T02:14:08Z","abstract_excerpt":"While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception. We show that the main reason for this is the Lyapunov stability of the gradient descent algorithm: for an arbitrarily chosen step size, the equilibria of the gradient descent are most likely to remain stable for the parametrization of residual networks. We then present an architecture with a pair of residual networks to approximate a large class of functions by decomposing them into a convex and a concave part. Some parameters of this model are shown to"},"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":"1803.08203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-22T02:14:08Z","cross_cats_sorted":["cs.NE","math.DS","math.OC","stat.ML"],"title_canon_sha256":"e26efd8b281e7416e4ed87bf02ecd7d90d3503f3a7d509fe32e14c55d1d9f617","abstract_canon_sha256":"f1c03049689c3042976796500fac5213c4c49abf8fa31d401997c91d50068d01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:23.438230Z","signature_b64":"dMKixeC3chOYn6GrWUfn7nfKt+SqpY+ZjgJYbmY5pfgAVyPPPKZXdaqOeieUBRhNH7bdH4LsG+pYrmc6jCwTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb096143cd0518ed12654d3af543456e61d09a0ef1372d7d29fee4dd59f099fa","last_reissued_at":"2026-05-18T00:20:23.437595Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:23.437595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual Networks: Lyapunov Stability and Convex Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kamil Nar, Shankar Sastry","submitted_at":"2018-03-22T02:14:08Z","abstract_excerpt":"While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception. We show that the main reason for this is the Lyapunov stability of the gradient descent algorithm: for an arbitrarily chosen step size, the equilibria of the gradient descent are most likely to remain stable for the parametrization of residual networks. We then present an architecture with a pair of residual networks to approximate a large class of functions by decomposing them into a convex and a concave part. Some parameters of this model are shown to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08203","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":"1803.08203","created_at":"2026-05-18T00:20:23.437691+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.08203v1","created_at":"2026-05-18T00:20:23.437691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08203","created_at":"2026-05-18T00:20:23.437691+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MEWCQ6NAUMO","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MEWCQ6NAUMO2ETF","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MEWCQ6N","created_at":"2026-05-18T12:32:11.075285+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/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ","json":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ.json","graph_json":"https://pith.science/api/pith-number/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/graph.json","events_json":"https://pith.science/api/pith-number/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/events.json","paper":"https://pith.science/paper/7MEWCQ6N"},"agent_actions":{"view_html":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ","download_json":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ.json","view_paper":"https://pith.science/paper/7MEWCQ6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.08203&json=true","fetch_graph":"https://pith.science/api/pith-number/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/action/storage_attestation","attest_author":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/action/author_attestation","sign_citation":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/action/citation_signature","submit_replication":"https://pith.science/pith/7MEWCQ6NAUMO2ETFJU5PKQ2FNZ/action/replication_record"}},"created_at":"2026-05-18T00:20:23.437691+00:00","updated_at":"2026-05-18T00:20:23.437691+00:00"}