{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IN6KYS6LU5N3D4JGFTS5HPHX74","short_pith_number":"pith:IN6KYS6L","schema_version":"1.0","canonical_sha256":"437cac4bcba75bb1f1262ce5d3bcf7ff0726776ebae9f17e956a4ba1c69d50de","source":{"kind":"arxiv","id":"1708.05344","version":1},"attestation_state":"computed","paper":{"title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Brock, J.M. Ritchie, Nick Weston, Theodore Lim","submitted_at":"2017-08-17T16:03:33Z","abstract_excerpt":"Designing architectures for deep neural networks requires expert knowledge and substantial computation time. We propose a technique to accelerate architecture selection by learning an auxiliary HyperNet that generates the weights of a main model conditioned on that model's architecture. By comparing the relative validation performance of networks with HyperNet-generated weights, we can effectively search over a wide range of architectures at the cost of a single training run. To facilitate this search, we develop a flexible mechanism based on memory read-writes that allows us to define a wide "},"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":"1708.05344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-17T16:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"81570f17c2de2e407a4da3a9a5168e6eef096ea56b760d8abb10b32b80cb01ea","abstract_canon_sha256":"9c6709e08ea1afab198f7d028570e96442e506b64ba649bf3c706777708aae4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:53.200976Z","signature_b64":"BjqvplYziRKFzCsKV+T7N9fyqP4pbun2VWryPwteL/fHmXYjQlS1F1eqWaEqJFogeec8fmW/EJPfjv1+ZR6uDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"437cac4bcba75bb1f1262ce5d3bcf7ff0726776ebae9f17e956a4ba1c69d50de","last_reissued_at":"2026-05-18T00:37:53.200236Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:53.200236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Brock, J.M. Ritchie, Nick Weston, Theodore Lim","submitted_at":"2017-08-17T16:03:33Z","abstract_excerpt":"Designing architectures for deep neural networks requires expert knowledge and substantial computation time. We propose a technique to accelerate architecture selection by learning an auxiliary HyperNet that generates the weights of a main model conditioned on that model's architecture. By comparing the relative validation performance of networks with HyperNet-generated weights, we can effectively search over a wide range of architectures at the cost of a single training run. To facilitate this search, we develop a flexible mechanism based on memory read-writes that allows us to define a wide "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05344","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":"1708.05344","created_at":"2026-05-18T00:37:53.200340+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.05344v1","created_at":"2026-05-18T00:37:53.200340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05344","created_at":"2026-05-18T00:37:53.200340+00:00"},{"alias_kind":"pith_short_12","alias_value":"IN6KYS6LU5N3","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IN6KYS6LU5N3D4JG","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IN6KYS6L","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":266,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05564","citing_title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2510.14235","citing_title":"Spiking Neural Network Architecture Search: A Survey","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":284,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11278","citing_title":"Representation-Aligned Multi-Scale Personalization for Federated Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":265,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74","json":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74.json","graph_json":"https://pith.science/api/pith-number/IN6KYS6LU5N3D4JGFTS5HPHX74/graph.json","events_json":"https://pith.science/api/pith-number/IN6KYS6LU5N3D4JGFTS5HPHX74/events.json","paper":"https://pith.science/paper/IN6KYS6L"},"agent_actions":{"view_html":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74","download_json":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74.json","view_paper":"https://pith.science/paper/IN6KYS6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.05344&json=true","fetch_graph":"https://pith.science/api/pith-number/IN6KYS6LU5N3D4JGFTS5HPHX74/graph.json","fetch_events":"https://pith.science/api/pith-number/IN6KYS6LU5N3D4JGFTS5HPHX74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74/action/storage_attestation","attest_author":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74/action/author_attestation","sign_citation":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74/action/citation_signature","submit_replication":"https://pith.science/pith/IN6KYS6LU5N3D4JGFTS5HPHX74/action/replication_record"}},"created_at":"2026-05-18T00:37:53.200340+00:00","updated_at":"2026-05-18T00:37:53.200340+00:00"}