{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3AK2M7JNNAAWMDTEMAVMLRCGVM","short_pith_number":"pith:3AK2M7JN","schema_version":"1.0","canonical_sha256":"d815a67d2d6801660e64602ac5c446ab22d3295fe7068ed5681e95a2068e778b","source":{"kind":"arxiv","id":"2009.06132","version":1},"attestation_state":"computed","paper":{"title":"Complexity Measures for Neural Networks with General Activation Functions Using Path-based Norms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Ma, Lei Wu, Zhong Li","submitted_at":"2020-09-14T01:15:11Z","abstract_excerpt":"A simple approach is proposed to obtain complexity controls for neural networks with general activation functions. The approach is motivated by approximating the general activation functions with one-dimensional ReLU networks, which reduces the problem to the complexity controls of ReLU networks. Specifically, we consider two-layer networks and deep residual networks, for which path-based norms are derived to control complexities. We also provide preliminary analyses of the function spaces induced by these norms and a priori estimates of the corresponding regularized estimators."},"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":"2009.06132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-14T01:15:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e4d61b7795f286317a8d5b20bab87c181da4c154ebfe7d138467576bb6e78ae","abstract_canon_sha256":"e03da4b450470a982682b48e67b3bfd2b271e00073c906d84d14209885103f01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:05.020692Z","signature_b64":"VdnK4FZOWPJWNKbBYnZYjuZjiqlPZk5b4oZNdxQicuIwSyiOOy3S+6j6q0y7XOoqzeA04aVGHRDsY2aq75vvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d815a67d2d6801660e64602ac5c446ab22d3295fe7068ed5681e95a2068e778b","last_reissued_at":"2026-07-05T01:35:05.020333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:05.020333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity Measures for Neural Networks with General Activation Functions Using Path-based Norms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Ma, Lei Wu, Zhong Li","submitted_at":"2020-09-14T01:15:11Z","abstract_excerpt":"A simple approach is proposed to obtain complexity controls for neural networks with general activation functions. The approach is motivated by approximating the general activation functions with one-dimensional ReLU networks, which reduces the problem to the complexity controls of ReLU networks. Specifically, we consider two-layer networks and deep residual networks, for which path-based norms are derived to control complexities. We also provide preliminary analyses of the function spaces induced by these norms and a priori estimates of the corresponding regularized estimators."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06132","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/2009.06132/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":"2009.06132","created_at":"2026-07-05T01:35:05.020393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.06132v1","created_at":"2026-07-05T01:35:05.020393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06132","created_at":"2026-07-05T01:35:05.020393+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AK2M7JNNAAW","created_at":"2026-07-05T01:35:05.020393+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AK2M7JNNAAWMDTE","created_at":"2026-07-05T01:35:05.020393+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AK2M7JN","created_at":"2026-07-05T01:35:05.020393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.00505","citing_title":"Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM","json":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM.json","graph_json":"https://pith.science/api/pith-number/3AK2M7JNNAAWMDTEMAVMLRCGVM/graph.json","events_json":"https://pith.science/api/pith-number/3AK2M7JNNAAWMDTEMAVMLRCGVM/events.json","paper":"https://pith.science/paper/3AK2M7JN"},"agent_actions":{"view_html":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM","download_json":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM.json","view_paper":"https://pith.science/paper/3AK2M7JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.06132&json=true","fetch_graph":"https://pith.science/api/pith-number/3AK2M7JNNAAWMDTEMAVMLRCGVM/graph.json","fetch_events":"https://pith.science/api/pith-number/3AK2M7JNNAAWMDTEMAVMLRCGVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM/action/storage_attestation","attest_author":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM/action/author_attestation","sign_citation":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM/action/citation_signature","submit_replication":"https://pith.science/pith/3AK2M7JNNAAWMDTEMAVMLRCGVM/action/replication_record"}},"created_at":"2026-07-05T01:35:05.020393+00:00","updated_at":"2026-07-05T01:35:05.020393+00:00"}