{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TS73GDBVAULD53ND62H27RZXC5","short_pith_number":"pith:TS73GDBV","schema_version":"1.0","canonical_sha256":"9cbfb30c3505163eeda3f68fafc7371757f8349d8d9bc167e9a7f9500eb74f48","source":{"kind":"arxiv","id":"2503.03986","version":1},"attestation_state":"computed","paper":{"title":"Training neural networks faster with minimal tuning using pre-computed lists of hyperparameters for NAdamW","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"George Dahl, Naman Agarwal, Priya Kasimbeg, Shankar Krishnan, Sourabh Medapati","submitted_at":"2025-03-06T00:14:50Z","abstract_excerpt":"If we want to train a neural network using any of the most popular optimization algorithms, we are immediately faced with a dilemma: how to set the various optimization and regularization hyperparameters? When computational resources are abundant, there are a variety of methods for finding good hyperparameter settings, but when resources are limited the only realistic choices are using standard default values of uncertain quality and provenance, or tuning only a couple of the most important hyperparameters via extremely limited handdesigned sweeps. Extending the idea of default settings to a m"},"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":"2503.03986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T00:14:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2403a6585a0780445b1a0ed03577fe1b78a4242d998340e7568454d734cb7825","abstract_canon_sha256":"0f92d550289f07ce6c76c53b50858bfe580b666959cabb0baa2a439192574112"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:25.894938Z","signature_b64":"HPADeK4yTFwTMTZbHpmy6nF0qMnOlexLamNLw+U1eyRrFZCt6qlSAAHnIe4zunUfSRCTOUEHJDBH+XRvPG9sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cbfb30c3505163eeda3f68fafc7371757f8349d8d9bc167e9a7f9500eb74f48","last_reissued_at":"2026-07-05T10:25:25.894471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:25.894471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training neural networks faster with minimal tuning using pre-computed lists of hyperparameters for NAdamW","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"George Dahl, Naman Agarwal, Priya Kasimbeg, Shankar Krishnan, Sourabh Medapati","submitted_at":"2025-03-06T00:14:50Z","abstract_excerpt":"If we want to train a neural network using any of the most popular optimization algorithms, we are immediately faced with a dilemma: how to set the various optimization and regularization hyperparameters? When computational resources are abundant, there are a variety of methods for finding good hyperparameter settings, but when resources are limited the only realistic choices are using standard default values of uncertain quality and provenance, or tuning only a couple of the most important hyperparameters via extremely limited handdesigned sweeps. Extending the idea of default settings to a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03986","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.03986/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2503.03986","created_at":"2026-07-05T10:25:25.894543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03986v1","created_at":"2026-07-05T10:25:25.894543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03986","created_at":"2026-07-05T10:25:25.894543+00:00"},{"alias_kind":"pith_short_12","alias_value":"TS73GDBVAULD","created_at":"2026-07-05T10:25:25.894543+00:00"},{"alias_kind":"pith_short_16","alias_value":"TS73GDBVAULD53ND","created_at":"2026-07-05T10:25:25.894543+00:00"},{"alias_kind":"pith_short_8","alias_value":"TS73GDBV","created_at":"2026-07-05T10:25:25.894543+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/TS73GDBVAULD53ND62H27RZXC5","json":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5.json","graph_json":"https://pith.science/api/pith-number/TS73GDBVAULD53ND62H27RZXC5/graph.json","events_json":"https://pith.science/api/pith-number/TS73GDBVAULD53ND62H27RZXC5/events.json","paper":"https://pith.science/paper/TS73GDBV"},"agent_actions":{"view_html":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5","download_json":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5.json","view_paper":"https://pith.science/paper/TS73GDBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03986&json=true","fetch_graph":"https://pith.science/api/pith-number/TS73GDBVAULD53ND62H27RZXC5/graph.json","fetch_events":"https://pith.science/api/pith-number/TS73GDBVAULD53ND62H27RZXC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5/action/storage_attestation","attest_author":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5/action/author_attestation","sign_citation":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5/action/citation_signature","submit_replication":"https://pith.science/pith/TS73GDBVAULD53ND62H27RZXC5/action/replication_record"}},"created_at":"2026-07-05T10:25:25.894543+00:00","updated_at":"2026-07-05T10:25:25.894543+00:00"}