{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z34U6MVJUH3RCGU6RKXGS6H3SY","short_pith_number":"pith:Z34U6MVJ","schema_version":"1.0","canonical_sha256":"cef94f32a9a1f7111a9e8aae6978fb9631b1795009b9b6773f0c3e998f279d50","source":{"kind":"arxiv","id":"1812.00308","version":1},"attestation_state":"computed","paper":{"title":"On variation of gradients of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Dongha Kim, Yongdai Kim","submitted_at":"2018-12-02T02:37:56Z","abstract_excerpt":"We provide a theoretical explanation of the role of the number of nodes at each layer in deep neural networks. We prove that the largest variation of a deep neural network with ReLU activation function arises when the layer with the fewest nodes changes its activation pattern. An important implication is that deep neural network is a useful tool to generate functions most of whose variations are concentrated on a smaller area of the input space near the boundaries corresponding to the layer with the fewest nodes. In turn, this property makes the function more invariant to input transformation."},"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":"1812.00308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-02T02:37:56Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"8d64ee518f2111c2bbd6571a1c076d333f1d1b530e2c41ecade4b3c2631a280b","abstract_canon_sha256":"e25c09232ac88d41bf8e9c2195cd045a1479263c212cd5bf8aed8db275015d98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:47.125957Z","signature_b64":"3zFwYxUKdWz0l3AMCvHZuDUjYjGSuQgAINWCML+cV9yr9MnzSPHbfzOCIDqDmvupGo0owKl320/whkUoB5KLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef94f32a9a1f7111a9e8aae6978fb9631b1795009b9b6773f0c3e998f279d50","last_reissued_at":"2026-05-17T23:58:47.125389Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:47.125389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On variation of gradients of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Dongha Kim, Yongdai Kim","submitted_at":"2018-12-02T02:37:56Z","abstract_excerpt":"We provide a theoretical explanation of the role of the number of nodes at each layer in deep neural networks. We prove that the largest variation of a deep neural network with ReLU activation function arises when the layer with the fewest nodes changes its activation pattern. An important implication is that deep neural network is a useful tool to generate functions most of whose variations are concentrated on a smaller area of the input space near the boundaries corresponding to the layer with the fewest nodes. In turn, this property makes the function more invariant to input transformation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00308","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":"1812.00308","created_at":"2026-05-17T23:58:47.125483+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00308v1","created_at":"2026-05-17T23:58:47.125483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00308","created_at":"2026-05-17T23:58:47.125483+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z34U6MVJUH3R","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z34U6MVJUH3RCGU6","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z34U6MVJ","created_at":"2026-05-18T12:33:04.347982+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/Z34U6MVJUH3RCGU6RKXGS6H3SY","json":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY.json","graph_json":"https://pith.science/api/pith-number/Z34U6MVJUH3RCGU6RKXGS6H3SY/graph.json","events_json":"https://pith.science/api/pith-number/Z34U6MVJUH3RCGU6RKXGS6H3SY/events.json","paper":"https://pith.science/paper/Z34U6MVJ"},"agent_actions":{"view_html":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY","download_json":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY.json","view_paper":"https://pith.science/paper/Z34U6MVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00308&json=true","fetch_graph":"https://pith.science/api/pith-number/Z34U6MVJUH3RCGU6RKXGS6H3SY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z34U6MVJUH3RCGU6RKXGS6H3SY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY/action/storage_attestation","attest_author":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY/action/author_attestation","sign_citation":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY/action/citation_signature","submit_replication":"https://pith.science/pith/Z34U6MVJUH3RCGU6RKXGS6H3SY/action/replication_record"}},"created_at":"2026-05-17T23:58:47.125483+00:00","updated_at":"2026-05-17T23:58:47.125483+00:00"}