{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TN6DIGA56DNDBCXMFS4IOVM74Q","short_pith_number":"pith:TN6DIGA5","schema_version":"1.0","canonical_sha256":"9b7c34181df0da308aec2cb887559fe438bbaf73a1790b4a67cf9bf28831109e","source":{"kind":"arxiv","id":"1810.10180","version":5},"attestation_state":"computed","paper":{"title":"Understanding and correcting pathologies in the training of learned optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.NE","authors_text":"C. Daniel Freeman, Jascha Sohl-Dickstein, Jeremy Nixon, Luke Metz, Niru Maheswaranathan","submitted_at":"2018-10-24T04:04:25Z","abstract_excerpt":"Deep learning has shown that learned functions can dramatically outperform hand-designed functions on perceptual tasks. Analogously, this suggests that learned optimizers may similarly outperform current hand-designed optimizers, especially for specific problems. However, learned optimizers are notoriously difficult to train and have yet to demonstrate wall-clock speedups over hand-designed optimizers, and thus are rarely used in practice. Typically, learned optimizers are trained by truncated backpropagation through an unrolled optimization process resulting in gradients that are either stron"},"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":"1810.10180","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-10-24T04:04:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82e19201c0c669c553b6eb014886fbb63adf6a9190771749b57471b818cdaa26","abstract_canon_sha256":"eb2f162b485f8b7278cdaee7b9cdb07618e3a1835226c484becfb59acb38e838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:50.630557Z","signature_b64":"njh3AV20SRHb0dYNDT5pRWCTMhIqMS5HFAHKCV87tYEJ98Cb5t0H3PqnqrbPvL8kGoHR55uvZUlt39DOJRlHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b7c34181df0da308aec2cb887559fe438bbaf73a1790b4a67cf9bf28831109e","last_reissued_at":"2026-05-17T23:43:50.630076Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:50.630076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding and correcting pathologies in the training of learned optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.NE","authors_text":"C. Daniel Freeman, Jascha Sohl-Dickstein, Jeremy Nixon, Luke Metz, Niru Maheswaranathan","submitted_at":"2018-10-24T04:04:25Z","abstract_excerpt":"Deep learning has shown that learned functions can dramatically outperform hand-designed functions on perceptual tasks. Analogously, this suggests that learned optimizers may similarly outperform current hand-designed optimizers, especially for specific problems. However, learned optimizers are notoriously difficult to train and have yet to demonstrate wall-clock speedups over hand-designed optimizers, and thus are rarely used in practice. Typically, learned optimizers are trained by truncated backpropagation through an unrolled optimization process resulting in gradients that are either stron"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10180","kind":"arxiv","version":5},"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":"1810.10180","created_at":"2026-05-17T23:43:50.630147+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10180v5","created_at":"2026-05-17T23:43:50.630147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10180","created_at":"2026-05-17T23:43:50.630147+00:00"},{"alias_kind":"pith_short_12","alias_value":"TN6DIGA56DND","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TN6DIGA56DNDBCXM","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TN6DIGA5","created_at":"2026-05-18T12:32:53.628368+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/TN6DIGA56DNDBCXMFS4IOVM74Q","json":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q.json","graph_json":"https://pith.science/api/pith-number/TN6DIGA56DNDBCXMFS4IOVM74Q/graph.json","events_json":"https://pith.science/api/pith-number/TN6DIGA56DNDBCXMFS4IOVM74Q/events.json","paper":"https://pith.science/paper/TN6DIGA5"},"agent_actions":{"view_html":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q","download_json":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q.json","view_paper":"https://pith.science/paper/TN6DIGA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10180&json=true","fetch_graph":"https://pith.science/api/pith-number/TN6DIGA56DNDBCXMFS4IOVM74Q/graph.json","fetch_events":"https://pith.science/api/pith-number/TN6DIGA56DNDBCXMFS4IOVM74Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q/action/storage_attestation","attest_author":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q/action/author_attestation","sign_citation":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q/action/citation_signature","submit_replication":"https://pith.science/pith/TN6DIGA56DNDBCXMFS4IOVM74Q/action/replication_record"}},"created_at":"2026-05-17T23:43:50.630147+00:00","updated_at":"2026-05-17T23:43:50.630147+00:00"}