{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:VEKXUQ6FPIUGPQA6YTV2WUV4PX","short_pith_number":"pith:VEKXUQ6F","schema_version":"1.0","canonical_sha256":"a9157a43c57a2867c01ec4ebab52bc7dd22afd44cd8719b16b8b4f61fc438df7","source":{"kind":"arxiv","id":"1605.07427","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Gerald Tesauro, Hugo Larochelle, Pascal Vincent, Sarath Chandar, Sungjin Ahn, Yoshua Bengio","submitted_at":"2016-05-24T12:48:19Z","abstract_excerpt":"Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which require the network to read from extremely large memories. On the other hand, it is well known that hard attention mechanisms based on reinforcement learning are challenging to train successfully. In this paper, we explore a form of hierarchical memory network, which can be consi"},"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":"1605.07427","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-24T12:48:19Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"24713d405ad80e36f25fe7f90396de258da1485a92599a543b8aa806f3b53d76","abstract_canon_sha256":"f72ef76d43f1da3827bbffb90059e473275fc456975fb6adc0de7bcc597971e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:46.102189Z","signature_b64":"nGXLzWT5Fq0SdrD77ZdyOYYkv+UsHkCll8JDf7W1QQp38Byany26LIxSpEI1zV/l1siyo15YlYgyqkbx3ZNYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9157a43c57a2867c01ec4ebab52bc7dd22afd44cd8719b16b8b4f61fc438df7","last_reissued_at":"2026-05-18T01:13:46.101569Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:46.101569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Gerald Tesauro, Hugo Larochelle, Pascal Vincent, Sarath Chandar, Sungjin Ahn, Yoshua Bengio","submitted_at":"2016-05-24T12:48:19Z","abstract_excerpt":"Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which require the network to read from extremely large memories. On the other hand, it is well known that hard attention mechanisms based on reinforcement learning are challenging to train successfully. In this paper, we explore a form of hierarchical memory network, which can be consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07427","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":"1605.07427","created_at":"2026-05-18T01:13:46.101661+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.07427v1","created_at":"2026-05-18T01:13:46.101661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07427","created_at":"2026-05-18T01:13:46.101661+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEKXUQ6FPIUG","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEKXUQ6FPIUGPQA6","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEKXUQ6F","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10602","citing_title":"Pyramid: A General Framework for Distributed Similarity Search","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":199,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX","json":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX.json","graph_json":"https://pith.science/api/pith-number/VEKXUQ6FPIUGPQA6YTV2WUV4PX/graph.json","events_json":"https://pith.science/api/pith-number/VEKXUQ6FPIUGPQA6YTV2WUV4PX/events.json","paper":"https://pith.science/paper/VEKXUQ6F"},"agent_actions":{"view_html":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX","download_json":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX.json","view_paper":"https://pith.science/paper/VEKXUQ6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.07427&json=true","fetch_graph":"https://pith.science/api/pith-number/VEKXUQ6FPIUGPQA6YTV2WUV4PX/graph.json","fetch_events":"https://pith.science/api/pith-number/VEKXUQ6FPIUGPQA6YTV2WUV4PX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX/action/storage_attestation","attest_author":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX/action/author_attestation","sign_citation":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX/action/citation_signature","submit_replication":"https://pith.science/pith/VEKXUQ6FPIUGPQA6YTV2WUV4PX/action/replication_record"}},"created_at":"2026-05-18T01:13:46.101661+00:00","updated_at":"2026-05-18T01:13:46.101661+00:00"}