{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XSMFIRSQ64LR547ABOJN4FPS22","short_pith_number":"pith:XSMFIRSQ","schema_version":"1.0","canonical_sha256":"bc98544650f7171ef3e00b92de15f2d6a6759837e467322500bc78e3369c221d","source":{"kind":"arxiv","id":"1706.02515","version":5},"attestation_state":"computed","paper":{"title":"Self-Normalizing Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Mayr, G\\\"unter Klambauer, Sepp Hochreiter, Thomas Unterthiner","submitted_at":"2017-06-08T11:14:24Z","abstract_excerpt":"Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot exploit many levels of abstract representations. We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations. While batch normalization requires explicit normalization, neuron activations of SNNs automatically converge towards zero mean and "},"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":"1706.02515","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-08T11:14:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2a3c9b9aece1e09afdb90d18c15fde80f840f00c848c18eb2ad7d0ec5134bf33","abstract_canon_sha256":"2bcada4a14f964c94e6eae606286b2021a52041d4cd7fec875c6f83144e87fce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:52.492351Z","signature_b64":"YDQFzTMeWyPDpuSTAafSYXTjbeGon2QzSET3YWCBLg/2JUvWNjUMxiysUJN++vkDNi0tWB3M3RW99qzfaai7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc98544650f7171ef3e00b92de15f2d6a6759837e467322500bc78e3369c221d","last_reissued_at":"2026-05-18T00:24:52.491612Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:52.491612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Normalizing Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Mayr, G\\\"unter Klambauer, Sepp Hochreiter, Thomas Unterthiner","submitted_at":"2017-06-08T11:14:24Z","abstract_excerpt":"Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot exploit many levels of abstract representations. We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations. While batch normalization requires explicit normalization, neuron activations of SNNs automatically converge towards zero mean and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02515","kind":"arxiv","version":5},"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":"1706.02515","created_at":"2026-05-18T00:24:52.491710+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.02515v5","created_at":"2026-05-18T00:24:52.491710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02515","created_at":"2026-05-18T00:24:52.491710+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSMFIRSQ64LR","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSMFIRSQ64LR547A","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSMFIRSQ","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1710.05941","citing_title":"Searching for Activation Functions","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22","json":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22.json","graph_json":"https://pith.science/api/pith-number/XSMFIRSQ64LR547ABOJN4FPS22/graph.json","events_json":"https://pith.science/api/pith-number/XSMFIRSQ64LR547ABOJN4FPS22/events.json","paper":"https://pith.science/paper/XSMFIRSQ"},"agent_actions":{"view_html":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22","download_json":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22.json","view_paper":"https://pith.science/paper/XSMFIRSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.02515&json=true","fetch_graph":"https://pith.science/api/pith-number/XSMFIRSQ64LR547ABOJN4FPS22/graph.json","fetch_events":"https://pith.science/api/pith-number/XSMFIRSQ64LR547ABOJN4FPS22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22/action/storage_attestation","attest_author":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22/action/author_attestation","sign_citation":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22/action/citation_signature","submit_replication":"https://pith.science/pith/XSMFIRSQ64LR547ABOJN4FPS22/action/replication_record"}},"created_at":"2026-05-18T00:24:52.491710+00:00","updated_at":"2026-05-18T00:24:52.491710+00:00"}