{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VSP7Y4MA26PUTCO6U7XI6SXV42","short_pith_number":"pith:VSP7Y4MA","schema_version":"1.0","canonical_sha256":"ac9ffc7180d79f4989dea7ee8f4af5e68752e46007b6c7e63adf07c37246702d","source":{"kind":"arxiv","id":"1807.10117","version":2},"attestation_state":"computed","paper":{"title":"Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"G. Zhang, H. Li","submitted_at":"2018-07-26T13:33:49Z","abstract_excerpt":"Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically increasing function, where it has an approximately constant negative output for large negative input. In this work, we propose a new activation function to break the monotonicity property of SELU while still preserving the self-normalizing property. Differently from SELU, the new func"},"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":"1807.10117","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T13:33:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2cbce83e650286e5b327b98501f0c8de6f8952fc5311baa31f7f61113a5c3824","abstract_canon_sha256":"a81ab61bf8f9374e22205416613ef10486e8c19381f50dde1f1a648c248338c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:41.126750Z","signature_b64":"PZeo6SrBn8WrdPk3PxGRppkw19OmmmkND8Ue0wkRCG55NDZpiQl8ilWUECVjyNSxTrymIs5K61lxrPNfDRDmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac9ffc7180d79f4989dea7ee8f4af5e68752e46007b6c7e63adf07c37246702d","last_reissued_at":"2026-05-18T00:09:41.126028Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:41.126028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"G. Zhang, H. Li","submitted_at":"2018-07-26T13:33:49Z","abstract_excerpt":"Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically increasing function, where it has an approximately constant negative output for large negative input. In this work, we propose a new activation function to break the monotonicity property of SELU while still preserving the self-normalizing property. Differently from SELU, the new func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10117","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":"1807.10117","created_at":"2026-05-18T00:09:41.126149+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.10117v2","created_at":"2026-05-18T00:09:41.126149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10117","created_at":"2026-05-18T00:09:41.126149+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSP7Y4MA26PU","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSP7Y4MA26PUTCO6","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSP7Y4MA","created_at":"2026-05-18T12:32:59.047623+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/VSP7Y4MA26PUTCO6U7XI6SXV42","json":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42.json","graph_json":"https://pith.science/api/pith-number/VSP7Y4MA26PUTCO6U7XI6SXV42/graph.json","events_json":"https://pith.science/api/pith-number/VSP7Y4MA26PUTCO6U7XI6SXV42/events.json","paper":"https://pith.science/paper/VSP7Y4MA"},"agent_actions":{"view_html":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42","download_json":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42.json","view_paper":"https://pith.science/paper/VSP7Y4MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.10117&json=true","fetch_graph":"https://pith.science/api/pith-number/VSP7Y4MA26PUTCO6U7XI6SXV42/graph.json","fetch_events":"https://pith.science/api/pith-number/VSP7Y4MA26PUTCO6U7XI6SXV42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42/action/storage_attestation","attest_author":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42/action/author_attestation","sign_citation":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42/action/citation_signature","submit_replication":"https://pith.science/pith/VSP7Y4MA26PUTCO6U7XI6SXV42/action/replication_record"}},"created_at":"2026-05-18T00:09:41.126149+00:00","updated_at":"2026-05-18T00:09:41.126149+00:00"}