{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H2726N3AA6PMBYG7RG5KFB32PX","short_pith_number":"pith:H2726N3A","schema_version":"1.0","canonical_sha256":"3ebfaf3760079ec0e0df89baa2877a7dee6688330904f9d53e76b11787f18d13","source":{"kind":"arxiv","id":"1812.01640","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Catastrophic Forgetting by Soft Parameter Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deng Min, Enqiang Guo, Haifeng Li, Jiang Hao, Jian Peng, Qing Zhu, Xiaohong Wan, Zhuo Li","submitted_at":"2018-12-04T19:29:04Z","abstract_excerpt":"Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint distribution of parameters shared with all tasks. This idea can be questionable because this joint distribution may not present when the number of tasks increase. On the other hand, It also leads to \"long-term\" memory issue when the network capacity is limited since adding tasks will \"eat\" the network capacity. In this paper, we proposed a Soft Parameters Pruning (SPP"},"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":"1812.01640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T19:29:04Z","cross_cats_sorted":[],"title_canon_sha256":"4ca27abfb3e4e9919a901218d6806e4d71a370fe2410ac848e5c8501e2af465d","abstract_canon_sha256":"1f178a799414a5ccdb01a454d3a392886386a0a9bd64e769c66beb3970384eaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:01.019806Z","signature_b64":"5svqQ2ekbXMr2GEFUr/Te9agbeFD9yNmzqARnhBzLKOMAPTMx1XOn18EAwTHZfVe7vLi8DTTXwQ/q2S7ruTYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ebfaf3760079ec0e0df89baa2877a7dee6688330904f9d53e76b11787f18d13","last_reissued_at":"2026-05-17T23:59:01.019362Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:01.019362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Catastrophic Forgetting by Soft Parameter Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deng Min, Enqiang Guo, Haifeng Li, Jiang Hao, Jian Peng, Qing Zhu, Xiaohong Wan, Zhuo Li","submitted_at":"2018-12-04T19:29:04Z","abstract_excerpt":"Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint distribution of parameters shared with all tasks. This idea can be questionable because this joint distribution may not present when the number of tasks increase. On the other hand, It also leads to \"long-term\" memory issue when the network capacity is limited since adding tasks will \"eat\" the network capacity. In this paper, we proposed a Soft Parameters Pruning (SPP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01640","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":"1812.01640","created_at":"2026-05-17T23:59:01.019426+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01640v1","created_at":"2026-05-17T23:59:01.019426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01640","created_at":"2026-05-17T23:59:01.019426+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2726N3AA6PM","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2726N3AA6PMBYG7","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2726N3A","created_at":"2026-05-18T12:32:25.280505+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/H2726N3AA6PMBYG7RG5KFB32PX","json":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX.json","graph_json":"https://pith.science/api/pith-number/H2726N3AA6PMBYG7RG5KFB32PX/graph.json","events_json":"https://pith.science/api/pith-number/H2726N3AA6PMBYG7RG5KFB32PX/events.json","paper":"https://pith.science/paper/H2726N3A"},"agent_actions":{"view_html":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX","download_json":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX.json","view_paper":"https://pith.science/paper/H2726N3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01640&json=true","fetch_graph":"https://pith.science/api/pith-number/H2726N3AA6PMBYG7RG5KFB32PX/graph.json","fetch_events":"https://pith.science/api/pith-number/H2726N3AA6PMBYG7RG5KFB32PX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX/action/storage_attestation","attest_author":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX/action/author_attestation","sign_citation":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX/action/citation_signature","submit_replication":"https://pith.science/pith/H2726N3AA6PMBYG7RG5KFB32PX/action/replication_record"}},"created_at":"2026-05-17T23:59:01.019426+00:00","updated_at":"2026-05-17T23:59:01.019426+00:00"}