{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KGA673STUTX76BLOSMZG7B6ZDL","short_pith_number":"pith:KGA673ST","schema_version":"1.0","canonical_sha256":"5181efee53a4efff056e93326f87d91ae190f1687941d4cb2b589d37f33fc671","source":{"kind":"arxiv","id":"1910.02366","version":3},"attestation_state":"computed","paper":{"title":"Splitting Steepest Descent for Growing Neural Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dilin Wang, Lemeng Wu, Qiang Liu","submitted_at":"2019-10-06T04:15:23Z","abstract_excerpt":"We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs. By leveraging a functional steepest descent idea, we derive a simple criterion for deciding the best subset of neurons to split and a splitting gradient for optimally updating the off-springs. Theoretically, our splitting strategy is a second-order functional steepest descent for escaping saddle points in an $\\infty$-Wasserstein metric space, on which the standard parametric gradient descent is a first-order steepest descent. Our met"},"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":"1910.02366","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-06T04:15:23Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"8dbceba3373372173f237f0a74c099121a9bf29438afdf57c982840214503572","abstract_canon_sha256":"c3402bf55fe88f5190e0b9e01e9a0890ab7bb9ff9912657ed1772aab61da7563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:50.624165Z","signature_b64":"SfJm0YOjSc9tGPXCah4vIa9ixiKWLqoW6YKaufBAs+wqEj9U1FhnWTg4CXS+zVocdBnqPy8LUa71rHnrS6+9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5181efee53a4efff056e93326f87d91ae190f1687941d4cb2b589d37f33fc671","last_reissued_at":"2026-07-05T00:16:50.623663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:50.623663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Splitting Steepest Descent for Growing Neural Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dilin Wang, Lemeng Wu, Qiang Liu","submitted_at":"2019-10-06T04:15:23Z","abstract_excerpt":"We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs. By leveraging a functional steepest descent idea, we derive a simple criterion for deciding the best subset of neurons to split and a splitting gradient for optimally updating the off-springs. Theoretically, our splitting strategy is a second-order functional steepest descent for escaping saddle points in an $\\infty$-Wasserstein metric space, on which the standard parametric gradient descent is a first-order steepest descent. Our met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02366","kind":"arxiv","version":3},"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/1910.02366/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":"1910.02366","created_at":"2026-07-05T00:16:50.623727+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.02366v3","created_at":"2026-07-05T00:16:50.623727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02366","created_at":"2026-07-05T00:16:50.623727+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGA673STUTX7","created_at":"2026-07-05T00:16:50.623727+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGA673STUTX76BLO","created_at":"2026-07-05T00:16:50.623727+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGA673ST","created_at":"2026-07-05T00:16:50.623727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31110","citing_title":"Explaining Machine Learning and Memorization with Statistical Mechanics","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL","json":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL.json","graph_json":"https://pith.science/api/pith-number/KGA673STUTX76BLOSMZG7B6ZDL/graph.json","events_json":"https://pith.science/api/pith-number/KGA673STUTX76BLOSMZG7B6ZDL/events.json","paper":"https://pith.science/paper/KGA673ST"},"agent_actions":{"view_html":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL","download_json":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL.json","view_paper":"https://pith.science/paper/KGA673ST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.02366&json=true","fetch_graph":"https://pith.science/api/pith-number/KGA673STUTX76BLOSMZG7B6ZDL/graph.json","fetch_events":"https://pith.science/api/pith-number/KGA673STUTX76BLOSMZG7B6ZDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL/action/storage_attestation","attest_author":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL/action/author_attestation","sign_citation":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL/action/citation_signature","submit_replication":"https://pith.science/pith/KGA673STUTX76BLOSMZG7B6ZDL/action/replication_record"}},"created_at":"2026-07-05T00:16:50.623727+00:00","updated_at":"2026-07-05T00:16:50.623727+00:00"}