{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4W44IFKITAU6SRYJQ6OUPDPGEA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1cb3f16d08d737452acdc6a8224d7cccc93f39de7d05151b528c7ce2882225b2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-29T21:41:49Z","title_canon_sha256":"fbca416323c86c2a58605f4426606397979830a53838434813e7220e008ad746"},"schema_version":"1.0","source":{"id":"1909.13371","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.13371","created_at":"2026-07-05T05:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"1909.13371v2","created_at":"2026-07-05T05:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13371","created_at":"2026-07-05T05:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"4W44IFKITAU6","created_at":"2026-07-05T05:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"4W44IFKITAU6SRYJ","created_at":"2026-07-05T05:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"4W44IFKI","created_at":"2026-07-05T05:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:89ec4a36afc06b73c38ee78d4e33b5df1dfd37b85aa719aee65297394a6c4ce9","target":"graph","created_at":"2026-07-05T05:06:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.13371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Working with any gradient-based machine learning algorithm involves the tedious task of tuning the optimizer's hyperparameters, such as its step size. Recent work has shown how the step size can itself be optimized alongside the model parameters by manually deriving expressions for \"hypergradients\" ahead of time.\n  We show how to automatically compute hypergradients with a simple and elegant modification to backpropagation. This allows us to easily apply the method to other optimizers and hyperparameters (e.g. momentum coefficients). We can even recursively apply the method to its own hyper-hy","authors_text":"Audrey Xie, Erik Meijer, Jonathan Ragan-Kelley, Kartik Chandra","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-29T21:41:49Z","title":"Gradient Descent: The Ultimate Optimizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13371","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:08c6224a8730c2dd7475e0664a10bce7aee3ee8454d364215fb5d5dbd4e8c76a","target":"record","created_at":"2026-07-05T05:06:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1cb3f16d08d737452acdc6a8224d7cccc93f39de7d05151b528c7ce2882225b2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-29T21:41:49Z","title_canon_sha256":"fbca416323c86c2a58605f4426606397979830a53838434813e7220e008ad746"},"schema_version":"1.0","source":{"id":"1909.13371","kind":"arxiv","version":2}},"canonical_sha256":"e5b9c415489829e94709879d478de6203bc273b381686ab3e866278d79606e1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5b9c415489829e94709879d478de6203bc273b381686ab3e866278d79606e1b","first_computed_at":"2026-07-05T05:06:48.634053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:48.634053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWnVfQ145J7nE9aLHa8gcebynBSxK6/Zz571177w/LdifCY+1wZPbA2pcq58ZdTMD0F9mawyUM3zNUwQTBSlBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:48.634407Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.13371","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08c6224a8730c2dd7475e0664a10bce7aee3ee8454d364215fb5d5dbd4e8c76a","sha256:89ec4a36afc06b73c38ee78d4e33b5df1dfd37b85aa719aee65297394a6c4ce9"],"state_sha256":"80c0c7cc91bb6d1a44a21ff32566c15a39f6409dca2c2df66071b921bedc3779"}