{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DS7IVUPTK55CWYUGIIWWYPVO77","short_pith_number":"pith:DS7IVUPT","schema_version":"1.0","canonical_sha256":"1cbe8ad1f3577a2b6286422d6c3eaefff4be9bf22067a5fd2de613ce568098c2","source":{"kind":"arxiv","id":"1701.08734","version":1},"attestation_state":"computed","paper":{"title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Alexander Pritzel, Andrei A. Rusu, Charles Blundell, Chrisantha Fernando, Daan Wierstra, David Ha, Dylan Banarse, Yori Zwols","submitted_at":"2017-01-30T18:06:07Z","abstract_excerpt":"For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting. PathNet is a first step in this direction. It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks. Agents are pathways (views) through the network which determine the subset of parameters that are used and updated by the forwards and backwards passes of the backpropogation algorithm. During learning, a tournament "},"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":"1701.08734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-01-30T18:06:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2631d35f1af6cc51db757841f32085ef0d10e3bbc60c5dcd77451a8eab246f01","abstract_canon_sha256":"399f76b407371458a8f4e28fad01533bc7c025fe9fb275084338b09d3c3141f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:52.843378Z","signature_b64":"IKj1WMze97TkgP69lT3/bhAtLBP35U9JqPisLtk7UKBLSBuiUqQj7wAnpKaw2o4Ev827MO0sZygdXl6HLrw+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cbe8ad1f3577a2b6286422d6c3eaefff4be9bf22067a5fd2de613ce568098c2","last_reissued_at":"2026-05-18T00:51:52.842690Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:52.842690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Alexander Pritzel, Andrei A. Rusu, Charles Blundell, Chrisantha Fernando, Daan Wierstra, David Ha, Dylan Banarse, Yori Zwols","submitted_at":"2017-01-30T18:06:07Z","abstract_excerpt":"For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting. PathNet is a first step in this direction. It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks. Agents are pathways (views) through the network which determine the subset of parameters that are used and updated by the forwards and backwards passes of the backpropogation algorithm. During learning, a tournament "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.08734","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":"1701.08734","created_at":"2026-05-18T00:51:52.842791+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.08734v1","created_at":"2026-05-18T00:51:52.842791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.08734","created_at":"2026-05-18T00:51:52.842791+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS7IVUPTK55C","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS7IVUPTK55CWYUG","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS7IVUPT","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"1906.09205","citing_title":"Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2309.09550","citing_title":"Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networks","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07799","citing_title":"Learning Without Losing Identity: Capability Evolution for Embodied Agents","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04516","citing_title":"TACO: Temporal Consensus Optimization for Continual Neural Mapping","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2603.11395","citing_title":"ARROW: Augmented Replay for RObust World models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14364","citing_title":"MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14364","citing_title":"MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15435","citing_title":"On the Stability of Growth in Structural Plasticity","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2506.21872","citing_title":"A Survey of Continual Reinforcement Learning","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14364","citing_title":"MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2603.24350","citing_title":"Evidence of an Emergent \"Self\" in Continual Robot Learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03555","citing_title":"MILE: Mixture of Incremental LoRA Experts for Continual Semantic Segmentation across Domains and Modalities","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18270","citing_title":"Incremental learning for audio classification with Hebbian Deep Neural Networks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07799","citing_title":"Learning Without Losing Identity: Capability Evolution for Embodied Agents","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77","json":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77.json","graph_json":"https://pith.science/api/pith-number/DS7IVUPTK55CWYUGIIWWYPVO77/graph.json","events_json":"https://pith.science/api/pith-number/DS7IVUPTK55CWYUGIIWWYPVO77/events.json","paper":"https://pith.science/paper/DS7IVUPT"},"agent_actions":{"view_html":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77","download_json":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77.json","view_paper":"https://pith.science/paper/DS7IVUPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.08734&json=true","fetch_graph":"https://pith.science/api/pith-number/DS7IVUPTK55CWYUGIIWWYPVO77/graph.json","fetch_events":"https://pith.science/api/pith-number/DS7IVUPTK55CWYUGIIWWYPVO77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77/action/storage_attestation","attest_author":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77/action/author_attestation","sign_citation":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77/action/citation_signature","submit_replication":"https://pith.science/pith/DS7IVUPTK55CWYUGIIWWYPVO77/action/replication_record"}},"created_at":"2026-05-18T00:51:52.842791+00:00","updated_at":"2026-05-18T00:51:52.842791+00:00"}