{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3P3I75JDY5SD3HKVRTIWPHMHJD","short_pith_number":"pith:3P3I75JD","schema_version":"1.0","canonical_sha256":"dbf68ff523c7643d9d558cd1679d8748dd48d55441dac6bc685886f58a9eb89a","source":{"kind":"arxiv","id":"1707.04585","version":1},"attestation_state":"computed","paper":{"title":"The Reversible Residual Network: Backpropagation Without Storing Activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse","submitted_at":"2017-07-14T03:05:43Z","abstract_excerpt":"Deep residual networks (ResNets) have significantly pushed forward the state-of-the-art on image classification, increasing in performance as networks grow both deeper and wider. However, memory consumption becomes a bottleneck, as one needs to store the activations in order to calculate gradients using backpropagation. We present the Reversible Residual Network (RevNet), a variant of ResNets where each layer's activations can be reconstructed exactly from the next layer's. Therefore, the activations for most layers need not be stored in memory during backpropagation. We demonstrate the effect"},"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":"1707.04585","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-14T03:05:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9ba15270afc5274621bac9e41bdb8b680f70b49d1046df17f0fd463c7257bbf6","abstract_canon_sha256":"f908231a031d033565df499ae5b8e355a6e1022d6611d90a815f74eb0c3feb6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:17.207872Z","signature_b64":"Nv3M1zX+hrPH6RdaWhBf7SBqTcryrUDod02iGuOpaNWWtcm32xqbDQJINAIzIj+fvvHWo1eDIgHV///KaMdcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbf68ff523c7643d9d558cd1679d8748dd48d55441dac6bc685886f58a9eb89a","last_reissued_at":"2026-05-18T00:40:17.207122Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:17.207122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Reversible Residual Network: Backpropagation Without Storing Activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse","submitted_at":"2017-07-14T03:05:43Z","abstract_excerpt":"Deep residual networks (ResNets) have significantly pushed forward the state-of-the-art on image classification, increasing in performance as networks grow both deeper and wider. However, memory consumption becomes a bottleneck, as one needs to store the activations in order to calculate gradients using backpropagation. We present the Reversible Residual Network (RevNet), a variant of ResNets where each layer's activations can be reconstructed exactly from the next layer's. Therefore, the activations for most layers need not be stored in memory during backpropagation. We demonstrate the effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04585","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":"1707.04585","created_at":"2026-05-18T00:40:17.207231+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.04585v1","created_at":"2026-05-18T00:40:17.207231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04585","created_at":"2026-05-18T00:40:17.207231+00:00"},{"alias_kind":"pith_short_12","alias_value":"3P3I75JDY5SD","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3P3I75JDY5SD3HKV","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3P3I75JD","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.03875","citing_title":"Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2208.07339","citing_title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD","json":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD.json","graph_json":"https://pith.science/api/pith-number/3P3I75JDY5SD3HKVRTIWPHMHJD/graph.json","events_json":"https://pith.science/api/pith-number/3P3I75JDY5SD3HKVRTIWPHMHJD/events.json","paper":"https://pith.science/paper/3P3I75JD"},"agent_actions":{"view_html":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD","download_json":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD.json","view_paper":"https://pith.science/paper/3P3I75JD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.04585&json=true","fetch_graph":"https://pith.science/api/pith-number/3P3I75JDY5SD3HKVRTIWPHMHJD/graph.json","fetch_events":"https://pith.science/api/pith-number/3P3I75JDY5SD3HKVRTIWPHMHJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD/action/storage_attestation","attest_author":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD/action/author_attestation","sign_citation":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD/action/citation_signature","submit_replication":"https://pith.science/pith/3P3I75JDY5SD3HKVRTIWPHMHJD/action/replication_record"}},"created_at":"2026-05-18T00:40:17.207231+00:00","updated_at":"2026-05-18T00:40:17.207231+00:00"}