{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FFI6POUA3TMPM7XIVIK2LIUVZC","short_pith_number":"pith:FFI6POUA","schema_version":"1.0","canonical_sha256":"2951e7ba80dcd8f67ee8aa15a5a295c885e669f12b4f59e2b35a9b6de75fde07","source":{"kind":"arxiv","id":"2401.03104","version":1},"attestation_state":"computed","paper":{"title":"When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Damith Senanayake, Denny Oetomo, Haihang Wu, Saman Halgamuge, Tamasha Malepathirana, Wei Wang","submitted_at":"2024-01-06T01:15:51Z","abstract_excerpt":"Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks. One crucial aspect of neural growth is determining the optimal growth timing. However, few studies investigate this systematically. Our study reveals that neural growth inherently exhibits a regularization effect, whose intensity is influenced by the chosen policy for growth timing. While this regularization effect may mitigate the overfitting risk of the model, it may lead to a notable accuracy drop when the model underfits. Yet, current a"},"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":"2401.03104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-06T01:15:51Z","cross_cats_sorted":[],"title_canon_sha256":"ba894b029d000511858cf974c2d7114717264f266ee838c570036b121e3aa581","abstract_canon_sha256":"f282862eb47acc451107de18057543a6757aa93bc209d979bbd9ab924b2413f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:02.357305Z","signature_b64":"GShUA3+OuHmGAL17eZZ1rh6DroMHWkDUwrNnOUMkbnGK+27qE8H+ZwRN/6n7oNb3lmMs6YiA/81MAbvCg0NsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2951e7ba80dcd8f67ee8aa15a5a295c885e669f12b4f59e2b35a9b6de75fde07","last_reissued_at":"2026-07-05T07:31:02.356868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:02.356868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Damith Senanayake, Denny Oetomo, Haihang Wu, Saman Halgamuge, Tamasha Malepathirana, Wei Wang","submitted_at":"2024-01-06T01:15:51Z","abstract_excerpt":"Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks. One crucial aspect of neural growth is determining the optimal growth timing. However, few studies investigate this systematically. Our study reveals that neural growth inherently exhibits a regularization effect, whose intensity is influenced by the chosen policy for growth timing. While this regularization effect may mitigate the overfitting risk of the model, it may lead to a notable accuracy drop when the model underfits. Yet, current a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03104","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/2401.03104/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":"2401.03104","created_at":"2026-07-05T07:31:02.356923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03104v1","created_at":"2026-07-05T07:31:02.356923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03104","created_at":"2026-07-05T07:31:02.356923+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFI6POUA3TMP","created_at":"2026-07-05T07:31:02.356923+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFI6POUA3TMPM7XI","created_at":"2026-07-05T07:31:02.356923+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFI6POUA","created_at":"2026-07-05T07:31:02.356923+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/FFI6POUA3TMPM7XIVIK2LIUVZC","json":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC.json","graph_json":"https://pith.science/api/pith-number/FFI6POUA3TMPM7XIVIK2LIUVZC/graph.json","events_json":"https://pith.science/api/pith-number/FFI6POUA3TMPM7XIVIK2LIUVZC/events.json","paper":"https://pith.science/paper/FFI6POUA"},"agent_actions":{"view_html":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC","download_json":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC.json","view_paper":"https://pith.science/paper/FFI6POUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03104&json=true","fetch_graph":"https://pith.science/api/pith-number/FFI6POUA3TMPM7XIVIK2LIUVZC/graph.json","fetch_events":"https://pith.science/api/pith-number/FFI6POUA3TMPM7XIVIK2LIUVZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC/action/storage_attestation","attest_author":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC/action/author_attestation","sign_citation":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC/action/citation_signature","submit_replication":"https://pith.science/pith/FFI6POUA3TMPM7XIVIK2LIUVZC/action/replication_record"}},"created_at":"2026-07-05T07:31:02.356923+00:00","updated_at":"2026-07-05T07:31:02.356923+00:00"}