{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SY4VUVD4EKSW3XWLWEVSYMUGPQ","short_pith_number":"pith:SY4VUVD4","schema_version":"1.0","canonical_sha256":"96395a547c22a56ddecbb12b2c32867c354ea563a431dbe6b1aacde3cf57f810","source":{"kind":"arxiv","id":"1703.04200","version":3},"attestation_state":"computed","paper":{"title":"Continual Learning Through Synaptic Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Poole, Friedemann Zenke, Surya Ganguli","submitted_at":"2017-03-13T00:02:48Z","abstract_excerpt":"While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to changing domains, possibly by leveraging complex molecular machinery to solve many tasks simultaneously. In this study, we introduce intelligent synapses that bring some of this biological complexity into artificial neural networks. Each synapse accumulates task relevant information over time, and exploits this information to rapidly store new memories without f"},"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":"1703.04200","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-13T00:02:48Z","cross_cats_sorted":["q-bio.NC","stat.ML"],"title_canon_sha256":"d550c27f08799a00c3372d5c6e1f742f15b75b4488180365902a4557e00af06e","abstract_canon_sha256":"66741a76e4e6d0f912386ebc57c05b69aaea4da4c5006552f69ca97f10fc7628"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:29.306586Z","signature_b64":"yFk7BvY0stueKhIxI8HNA0a4sDzc+TLh5T9b5jEo988hh9TpM9RPXMOp7ZpT2oa7djlMfwrE4HVCL8qM5MP4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96395a547c22a56ddecbb12b2c32867c354ea563a431dbe6b1aacde3cf57f810","last_reissued_at":"2026-05-18T00:42:29.306043Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:29.306043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning Through Synaptic Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Poole, Friedemann Zenke, Surya Ganguli","submitted_at":"2017-03-13T00:02:48Z","abstract_excerpt":"While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to changing domains, possibly by leveraging complex molecular machinery to solve many tasks simultaneously. In this study, we introduce intelligent synapses that bring some of this biological complexity into artificial neural networks. Each synapse accumulates task relevant information over time, and exploits this information to rapidly store new memories without f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04200","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":""},"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":"1703.04200","created_at":"2026-05-18T00:42:29.306128+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04200v3","created_at":"2026-05-18T00:42:29.306128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04200","created_at":"2026-05-18T00:42:29.306128+00:00"},{"alias_kind":"pith_short_12","alias_value":"SY4VUVD4EKSW","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SY4VUVD4EKSW3XWL","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SY4VUVD4","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20296","citing_title":"Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09452","citing_title":"SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21927","citing_title":"Fine-Tuning Regimes Define Distinct Continual Learning Problems","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ","json":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ.json","graph_json":"https://pith.science/api/pith-number/SY4VUVD4EKSW3XWLWEVSYMUGPQ/graph.json","events_json":"https://pith.science/api/pith-number/SY4VUVD4EKSW3XWLWEVSYMUGPQ/events.json","paper":"https://pith.science/paper/SY4VUVD4"},"agent_actions":{"view_html":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ","download_json":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ.json","view_paper":"https://pith.science/paper/SY4VUVD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04200&json=true","fetch_graph":"https://pith.science/api/pith-number/SY4VUVD4EKSW3XWLWEVSYMUGPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SY4VUVD4EKSW3XWLWEVSYMUGPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ/action/storage_attestation","attest_author":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ/action/author_attestation","sign_citation":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ/action/citation_signature","submit_replication":"https://pith.science/pith/SY4VUVD4EKSW3XWLWEVSYMUGPQ/action/replication_record"}},"created_at":"2026-05-18T00:42:29.306128+00:00","updated_at":"2026-05-18T00:42:29.306128+00:00"}