{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:U4NDJ3QMSJF67ILHHPSLOMYXIV","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":"e30c2b914891c3bb12be1cb70f8603e06b0e7a5ba9ba8da44667d0a69d0e41d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T02:49:10Z","title_canon_sha256":"18ccb982e0712047d7ac9bfdb128dd816766b4f3465723cf5a09017588742a01"},"schema_version":"1.0","source":{"id":"2002.11887","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11887","created_at":"2026-07-05T00:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11887v3","created_at":"2026-07-05T00:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11887","created_at":"2026-07-05T00:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"U4NDJ3QMSJF6","created_at":"2026-07-05T00:51:54Z"},{"alias_kind":"pith_short_16","alias_value":"U4NDJ3QMSJF67ILH","created_at":"2026-07-05T00:51:54Z"},{"alias_kind":"pith_short_8","alias_value":"U4NDJ3QM","created_at":"2026-07-05T00:51:54Z"}],"graph_snapshots":[{"event_id":"sha256:de40d4a5912bd828d55f6855f7d92ffd2608b75dfa5f26993090603d583504a4","target":"graph","created_at":"2026-07-05T00:51:54Z","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/2002.11887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present TaskSet, a dataset of tasks for use in training and evaluating optimizers. TaskSet is unique in its size and diversity, containing over a thousand tasks ranging from image classification with fully connected or convolutional neural networks, to variational autoencoders, to non-volume preserving flows on a variety of datasets. As an example application of such a dataset we explore meta-learning an ordered list of hyperparameters to try sequentially. By learning this hyperparameter list from data generated using TaskSet we achieve large speedups in sample efficiency over random search","authors_text":"Ben Poole, C. Daniel Freeman, Jascha Sohl-Dickstein, Luke Metz, Niru Maheswaranathan, Ruoxi Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T02:49:10Z","title":"Using a thousand optimization tasks to learn hyperparameter search strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11887","kind":"arxiv","version":3},"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":"sha256:80d61bd85ea0102babec364a065d018c9a7a0aace908143e9df930e188d19548","target":"record","created_at":"2026-07-05T00:51:54Z","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":"e30c2b914891c3bb12be1cb70f8603e06b0e7a5ba9ba8da44667d0a69d0e41d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T02:49:10Z","title_canon_sha256":"18ccb982e0712047d7ac9bfdb128dd816766b4f3465723cf5a09017588742a01"},"schema_version":"1.0","source":{"id":"2002.11887","kind":"arxiv","version":3}},"canonical_sha256":"a71a34ee0c924befa1673be4b733174548a3fd32d2ab91bbf33b026c17d78a01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a71a34ee0c924befa1673be4b733174548a3fd32d2ab91bbf33b026c17d78a01","first_computed_at":"2026-07-05T00:51:54.497152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:54.497152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GydH2vXizBO/cn8Mv6hLCrzJN2DeDXkpA9CR9SydX2TqFX936u4rrPDTepBdEzerMetbJmLnsbMH7gKP3AHyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:54.497533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11887","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80d61bd85ea0102babec364a065d018c9a7a0aace908143e9df930e188d19548","sha256:de40d4a5912bd828d55f6855f7d92ffd2608b75dfa5f26993090603d583504a4"],"state_sha256":"cf34db82e084433170a7ad0857427129311ba363a202da06924ed0adf8775831"}