{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DJHBVPJ3PDSQO5Q3VD4EELJBF3","short_pith_number":"pith:DJHBVPJ3","schema_version":"1.0","canonical_sha256":"1a4e1abd3b78e507761ba8f8422d212eeb855c5518e6db031f4f93ff8ffac916","source":{"kind":"arxiv","id":"1804.10316","version":1},"attestation_state":"computed","paper":{"title":"CompNet: Neural networks growing via the compact network morphism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Boi Faltings, Jun Lu, Wei Ma","submitted_at":"2018-04-27T01:20:26Z","abstract_excerpt":"It is often the case that the performance of a neural network can be improved by adding layers. In real-world practices, we always train dozens of neural network architectures in parallel which is a wasteful process. We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact. The work of the paper makes two contributions: a). The modified network can converge fast and keep the same functionality so that we do not need to train from scratch again; b). The layer size of the added layer in the "},"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":"1804.10316","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-27T01:20:26Z","cross_cats_sorted":[],"title_canon_sha256":"7f74a1ed820895200dcf094f5b05f7f544b6f428e9ec3aca72ff3db821ae8fef","abstract_canon_sha256":"00fc435a145906b6f5f1f20eff62de54444be5e011dd61db359ce85af4b9616a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:21.140206Z","signature_b64":"Ej7ZEbuSqB/IrmmwDxH8zadgDxih8I6XB40zUG3fPnFAxGzWjE/JHcvzWRbHZ4uZPZY6UqJ133NYtLE0y9vYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4e1abd3b78e507761ba8f8422d212eeb855c5518e6db031f4f93ff8ffac916","last_reissued_at":"2026-05-18T00:17:21.139501Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:21.139501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompNet: Neural networks growing via the compact network morphism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Boi Faltings, Jun Lu, Wei Ma","submitted_at":"2018-04-27T01:20:26Z","abstract_excerpt":"It is often the case that the performance of a neural network can be improved by adding layers. In real-world practices, we always train dozens of neural network architectures in parallel which is a wasteful process. We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact. The work of the paper makes two contributions: a). The modified network can converge fast and keep the same functionality so that we do not need to train from scratch again; b). The layer size of the added layer in the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10316","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":"1804.10316","created_at":"2026-05-18T00:17:21.139618+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.10316v1","created_at":"2026-05-18T00:17:21.139618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10316","created_at":"2026-05-18T00:17:21.139618+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJHBVPJ3PDSQ","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJHBVPJ3PDSQO5Q3","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJHBVPJ3","created_at":"2026-05-18T12:32:19.392346+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/DJHBVPJ3PDSQO5Q3VD4EELJBF3","json":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3.json","graph_json":"https://pith.science/api/pith-number/DJHBVPJ3PDSQO5Q3VD4EELJBF3/graph.json","events_json":"https://pith.science/api/pith-number/DJHBVPJ3PDSQO5Q3VD4EELJBF3/events.json","paper":"https://pith.science/paper/DJHBVPJ3"},"agent_actions":{"view_html":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3","download_json":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3.json","view_paper":"https://pith.science/paper/DJHBVPJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.10316&json=true","fetch_graph":"https://pith.science/api/pith-number/DJHBVPJ3PDSQO5Q3VD4EELJBF3/graph.json","fetch_events":"https://pith.science/api/pith-number/DJHBVPJ3PDSQO5Q3VD4EELJBF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3/action/storage_attestation","attest_author":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3/action/author_attestation","sign_citation":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3/action/citation_signature","submit_replication":"https://pith.science/pith/DJHBVPJ3PDSQO5Q3VD4EELJBF3/action/replication_record"}},"created_at":"2026-05-18T00:17:21.139618+00:00","updated_at":"2026-05-18T00:17:21.139618+00:00"}