{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:D3AK5WDZ4GD2KR2K4WNHZDTDUU","short_pith_number":"pith:D3AK5WDZ","schema_version":"1.0","canonical_sha256":"1ec0aed879e187a5474ae59a7c8e63a51e28701ea1fb72c11b67dcc48c9e18b7","source":{"kind":"arxiv","id":"1606.03401","version":1},"attestation_state":"computed","paper":{"title":"Memory-Efficient Backpropagation Through Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Alex Graves, Audr\\=unas Gruslys, Ivo Danihelka, Marc Lanctot, Remi Munos","submitted_at":"2016-06-10T17:20:39Z","abstract_excerpt":"We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of intermediate results and recomputation. The algorithm is capable of tightly fitting within almost any user-set memory budget while finding an optimal execution policy minimizing the computational cost. Computational devices have limited memory capacity and maximizing a computational performance given a fixed memory budget is a practical use-case. We provide as"},"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":"1606.03401","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-10T17:20:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"572e78e2e05a02ae5bd658a7812a3eeac86f3d0886d420710928b0eb8d31c7ce","abstract_canon_sha256":"935bee9b47a5a461d2ca74273f6f62d58398edf21f42fd6afa5a74de3614858b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:36.974694Z","signature_b64":"LAKJfPdpryqASrjLECVEsL1Vx3do0gHByChTpiCCqRHM7t1oy7GSfwhsKhXGJ1SEIvdap0MqqdZYuR2mofpTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ec0aed879e187a5474ae59a7c8e63a51e28701ea1fb72c11b67dcc48c9e18b7","last_reissued_at":"2026-05-18T01:12:36.974058Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:36.974058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-Efficient Backpropagation Through Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Alex Graves, Audr\\=unas Gruslys, Ivo Danihelka, Marc Lanctot, Remi Munos","submitted_at":"2016-06-10T17:20:39Z","abstract_excerpt":"We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of intermediate results and recomputation. The algorithm is capable of tightly fitting within almost any user-set memory budget while finding an optimal execution policy minimizing the computational cost. Computational devices have limited memory capacity and maximizing a computational performance given a fixed memory budget is a practical use-case. We provide as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03401","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":"1606.03401","created_at":"2026-05-18T01:12:36.974156+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.03401v1","created_at":"2026-05-18T01:12:36.974156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03401","created_at":"2026-05-18T01:12:36.974156+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3AK5WDZ4GD2","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3AK5WDZ4GD2KR2K","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3AK5WDZ","created_at":"2026-05-18T12:30:09.641336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1701.06538","citing_title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU","json":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU.json","graph_json":"https://pith.science/api/pith-number/D3AK5WDZ4GD2KR2K4WNHZDTDUU/graph.json","events_json":"https://pith.science/api/pith-number/D3AK5WDZ4GD2KR2K4WNHZDTDUU/events.json","paper":"https://pith.science/paper/D3AK5WDZ"},"agent_actions":{"view_html":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU","download_json":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU.json","view_paper":"https://pith.science/paper/D3AK5WDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.03401&json=true","fetch_graph":"https://pith.science/api/pith-number/D3AK5WDZ4GD2KR2K4WNHZDTDUU/graph.json","fetch_events":"https://pith.science/api/pith-number/D3AK5WDZ4GD2KR2K4WNHZDTDUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU/action/storage_attestation","attest_author":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU/action/author_attestation","sign_citation":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU/action/citation_signature","submit_replication":"https://pith.science/pith/D3AK5WDZ4GD2KR2K4WNHZDTDUU/action/replication_record"}},"created_at":"2026-05-18T01:12:36.974156+00:00","updated_at":"2026-05-18T01:12:36.974156+00:00"}