{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G36A5QQG3UZMNISTBVBRP3L2IZ","short_pith_number":"pith:G36A5QQG","schema_version":"1.0","canonical_sha256":"36fc0ec206dd32c6a2530d4317ed7a464d9e6845778706448f85283c7b878f0d","source":{"kind":"arxiv","id":"1906.00695","version":4},"attestation_state":"computed","paper":{"title":"Continual learning with hypernetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin F. Grewe, Christian Henning, Jo\\~ao Sacramento, Johannes von Oswald","submitted_at":"2019-06-03T10:45:08Z","abstract_excerpt":"Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate the weights of a target model based on task identity. Continual learning (CL) is less difficult for this class of models thanks to a simple key feature: instead of recalling the input-output relations of all previously seen data, task-conditioned hypernetworks only require rehearsing task-specific weight realizations, which can be maintained in memory using"},"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":"1906.00695","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T10:45:08Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1e0ef6b8518087d79d21b3ac13b998db143545494b9264d0cd7aee8b93f9d525","abstract_canon_sha256":"6d28c6807b2a79a25e85b0f0504246b3b392d887c0c64ec724a7fd99b239f7d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:07.919841Z","signature_b64":"Pfgd29wyoCb0qhQx//7nc5vz7jSLkDVkbmZpkQoti+9Jz8sM97PVitbyMzVrV0jCBGBhJzR+1Q4WHN8NUfoWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36fc0ec206dd32c6a2530d4317ed7a464d9e6845778706448f85283c7b878f0d","last_reissued_at":"2026-07-05T04:13:07.919362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:07.919362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual learning with hypernetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin F. Grewe, Christian Henning, Jo\\~ao Sacramento, Johannes von Oswald","submitted_at":"2019-06-03T10:45:08Z","abstract_excerpt":"Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate the weights of a target model based on task identity. Continual learning (CL) is less difficult for this class of models thanks to a simple key feature: instead of recalling the input-output relations of all previously seen data, task-conditioned hypernetworks only require rehearsing task-specific weight realizations, which can be maintained in memory using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00695","kind":"arxiv","version":4},"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/1906.00695/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":"1906.00695","created_at":"2026-07-05T04:13:07.919413+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00695v4","created_at":"2026-07-05T04:13:07.919413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00695","created_at":"2026-07-05T04:13:07.919413+00:00"},{"alias_kind":"pith_short_12","alias_value":"G36A5QQG3UZM","created_at":"2026-07-05T04:13:07.919413+00:00"},{"alias_kind":"pith_short_16","alias_value":"G36A5QQG3UZMNIST","created_at":"2026-07-05T04:13:07.919413+00:00"},{"alias_kind":"pith_short_8","alias_value":"G36A5QQG","created_at":"2026-07-05T04:13:07.919413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07743","citing_title":"Architecture Generalization with MetaNCA","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07574","citing_title":"Context-Aware Force Estimation for Deformable Tool Manipulation in Robotic Environmental Swabbing via Few-Shot Continual Adaptation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22969","citing_title":"Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2211.16780","citing_title":"An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2309.09550","citing_title":"Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networks","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20247","citing_title":"CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08857","citing_title":"RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06796","citing_title":"Instance-Adaptive Parametrization for Amortized Variational Inference","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ","json":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ.json","graph_json":"https://pith.science/api/pith-number/G36A5QQG3UZMNISTBVBRP3L2IZ/graph.json","events_json":"https://pith.science/api/pith-number/G36A5QQG3UZMNISTBVBRP3L2IZ/events.json","paper":"https://pith.science/paper/G36A5QQG"},"agent_actions":{"view_html":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ","download_json":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ.json","view_paper":"https://pith.science/paper/G36A5QQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00695&json=true","fetch_graph":"https://pith.science/api/pith-number/G36A5QQG3UZMNISTBVBRP3L2IZ/graph.json","fetch_events":"https://pith.science/api/pith-number/G36A5QQG3UZMNISTBVBRP3L2IZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ/action/storage_attestation","attest_author":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ/action/author_attestation","sign_citation":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ/action/citation_signature","submit_replication":"https://pith.science/pith/G36A5QQG3UZMNISTBVBRP3L2IZ/action/replication_record"}},"created_at":"2026-07-05T04:13:07.919413+00:00","updated_at":"2026-07-05T04:13:07.919413+00:00"}