{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3Y2P4SLS7GLTWVBZF7OC74QAE3","short_pith_number":"pith:3Y2P4SLS","schema_version":"1.0","canonical_sha256":"de34fe4972f9973b54392fdc2ff20026d46dd8b9944a92949d6806967653a0c1","source":{"kind":"arxiv","id":"1905.10952","version":1},"attestation_state":"computed","paper":{"title":"Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Hongxu Yin, Niraj K. Jha, Xiaoliang Dai","submitted_at":"2019-05-27T03:12:46Z","abstract_excerpt":"Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently update them to accommodate previously unseen data. To solve these problems, we propose an incremental learning framework based on a grow-and-prune neural network synthesis paradigm. When new data arrive, the neural network first grows new connections based on the gradients to increase the network capacity to accommodate new data. Then, the framework iteratively "},"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":"1905.10952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-05-27T03:12:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7c77e4096bf4a7ef6dae7a60cfbcd82cc3db13a21f073d30e34779c33e139309","abstract_canon_sha256":"5f7507764e4b54a90c0de341331f396adeca8a1329615b0cb1ecd067f81395ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:03.300979Z","signature_b64":"r7bjU5lkbnTtGYv7J3KzW1iSqwWPKFIX+k9B1gRtjcs+Hhll1SE55tRqm+9KJUGB0EsyI3ImOgzfCxHrVE8XDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de34fe4972f9973b54392fdc2ff20026d46dd8b9944a92949d6806967653a0c1","last_reissued_at":"2026-05-17T23:45:03.300525Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:03.300525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Hongxu Yin, Niraj K. Jha, Xiaoliang Dai","submitted_at":"2019-05-27T03:12:46Z","abstract_excerpt":"Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently update them to accommodate previously unseen data. To solve these problems, we propose an incremental learning framework based on a grow-and-prune neural network synthesis paradigm. When new data arrive, the neural network first grows new connections based on the gradients to increase the network capacity to accommodate new data. Then, the framework iteratively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10952","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":"1905.10952","created_at":"2026-05-17T23:45:03.300606+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10952v1","created_at":"2026-05-17T23:45:03.300606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10952","created_at":"2026-05-17T23:45:03.300606+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Y2P4SLS7GLT","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Y2P4SLS7GLTWVBZ","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Y2P4SLS","created_at":"2026-05-18T12:33:10.108867+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/3Y2P4SLS7GLTWVBZF7OC74QAE3","json":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3.json","graph_json":"https://pith.science/api/pith-number/3Y2P4SLS7GLTWVBZF7OC74QAE3/graph.json","events_json":"https://pith.science/api/pith-number/3Y2P4SLS7GLTWVBZF7OC74QAE3/events.json","paper":"https://pith.science/paper/3Y2P4SLS"},"agent_actions":{"view_html":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3","download_json":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3.json","view_paper":"https://pith.science/paper/3Y2P4SLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10952&json=true","fetch_graph":"https://pith.science/api/pith-number/3Y2P4SLS7GLTWVBZF7OC74QAE3/graph.json","fetch_events":"https://pith.science/api/pith-number/3Y2P4SLS7GLTWVBZF7OC74QAE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3/action/storage_attestation","attest_author":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3/action/author_attestation","sign_citation":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3/action/citation_signature","submit_replication":"https://pith.science/pith/3Y2P4SLS7GLTWVBZF7OC74QAE3/action/replication_record"}},"created_at":"2026-05-17T23:45:03.300606+00:00","updated_at":"2026-05-17T23:45:03.300606+00:00"}