{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:F74KQGQUKPF653NOEHGGORGLXL","short_pith_number":"pith:F74KQGQU","schema_version":"1.0","canonical_sha256":"2ff8a81a1453cbeeedae21cc6744cbbaefb0f63f72085a4045168730d2aabbd3","source":{"kind":"arxiv","id":"1703.04813","version":4},"attestation_state":"computed","paper":{"title":"Learned Optimizers that Scale and Generalize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jascha Sohl-Dickstein, Matthew W. Hoffman, Misha Denil, Nando de Freitas, Niru Maheswaranathan, Olga Wichrowska, Sergio Gomez Colmenarejo","submitted_at":"2017-03-14T23:05:54Z","abstract_excerpt":"Learning to learn has emerged as an important direction for achieving artificial intelligence. Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks. We introduce a learned gradient descent optimizer that generalizes well to new tasks, and which has significantly reduced memory and computation overhead. We achieve this by introducing a novel hierarchical RNN architecture, with minimal per-parameter overhead, augmented with additional architectural features that mirror the known structure of optimization tasks. "},"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":"1703.04813","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-14T23:05:54Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"996bc100c4eb0387e7da871d9b8203723ba53ec61184cfc551b3609d96e65bc4","abstract_canon_sha256":"77515ddeec72e21f870e58f0cf76edf552a8160d1ddb2c3c1bede95f0fe76050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:46.449383Z","signature_b64":"eTZLPxxP8q6sQE69ClTcppU+DnyS0sPMlPmGQbnByRPWrugmMQSjNVgCX3QuYAnloMFBbB1jxPy/cLJZBpQODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ff8a81a1453cbeeedae21cc6744cbbaefb0f63f72085a4045168730d2aabbd3","last_reissued_at":"2026-05-18T00:35:46.448846Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:46.448846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Optimizers that Scale and Generalize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jascha Sohl-Dickstein, Matthew W. Hoffman, Misha Denil, Nando de Freitas, Niru Maheswaranathan, Olga Wichrowska, Sergio Gomez Colmenarejo","submitted_at":"2017-03-14T23:05:54Z","abstract_excerpt":"Learning to learn has emerged as an important direction for achieving artificial intelligence. Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks. We introduce a learned gradient descent optimizer that generalizes well to new tasks, and which has significantly reduced memory and computation overhead. We achieve this by introducing a novel hierarchical RNN architecture, with minimal per-parameter overhead, augmented with additional architectural features that mirror the known structure of optimization tasks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04813","kind":"arxiv","version":4},"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":"1703.04813","created_at":"2026-05-18T00:35:46.448941+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04813v4","created_at":"2026-05-18T00:35:46.448941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04813","created_at":"2026-05-18T00:35:46.448941+00:00"},{"alias_kind":"pith_short_12","alias_value":"F74KQGQUKPF6","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"F74KQGQUKPF653NO","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"F74KQGQU","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL","json":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL.json","graph_json":"https://pith.science/api/pith-number/F74KQGQUKPF653NOEHGGORGLXL/graph.json","events_json":"https://pith.science/api/pith-number/F74KQGQUKPF653NOEHGGORGLXL/events.json","paper":"https://pith.science/paper/F74KQGQU"},"agent_actions":{"view_html":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL","download_json":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL.json","view_paper":"https://pith.science/paper/F74KQGQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04813&json=true","fetch_graph":"https://pith.science/api/pith-number/F74KQGQUKPF653NOEHGGORGLXL/graph.json","fetch_events":"https://pith.science/api/pith-number/F74KQGQUKPF653NOEHGGORGLXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL/action/storage_attestation","attest_author":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL/action/author_attestation","sign_citation":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL/action/citation_signature","submit_replication":"https://pith.science/pith/F74KQGQUKPF653NOEHGGORGLXL/action/replication_record"}},"created_at":"2026-05-18T00:35:46.448941+00:00","updated_at":"2026-05-18T00:35:46.448941+00:00"}