{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MV3W4QCBCIHG24ADFAO74MDORL","short_pith_number":"pith:MV3W4QCB","schema_version":"1.0","canonical_sha256":"65776e4041120e6d7003281dfe306e8ac89166a7da635f05273faac4b6a95536","source":{"kind":"arxiv","id":"2411.16975","version":1},"attestation_state":"computed","paper":{"title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Naoko Mizuno, Zan Chaudhry","submitted_at":"2024-11-25T22:58:22Z","abstract_excerpt":"Hyperparameter tuning remains a significant challenge for the training of deep neural networks (DNNs), requiring manual and/or time-intensive grid searches, increasing resource costs and presenting a barrier to the democratization of machine learning. The global initial learning rate for DNN training is particularly important. Several techniques have been proposed for automated learning rate tuning during training; however, they still require manual searching for the global initial learning rate. Though methods exist that do not require this initial selection, they suffer from poor performance"},"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":"2411.16975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T22:58:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4dbac082757658aa112b03a8a0cd12db0489d6fcd9fecddc21211167abf94ef2","abstract_canon_sha256":"c660530cc69c937ad938bb6d7cb86d80447c566907d54dff060d85d0e8d3f6f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:25.450478Z","signature_b64":"XMWZqVMyVdwXS1CNrH6UPq0dBdrae+PhU4BF/IqukEvby079Qpcs0E4HAtbdy4/tDPyKF2mWxmgbVcV4RliwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65776e4041120e6d7003281dfe306e8ac89166a7da635f05273faac4b6a95536","last_reissued_at":"2026-07-05T09:40:25.450061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:25.450061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Naoko Mizuno, Zan Chaudhry","submitted_at":"2024-11-25T22:58:22Z","abstract_excerpt":"Hyperparameter tuning remains a significant challenge for the training of deep neural networks (DNNs), requiring manual and/or time-intensive grid searches, increasing resource costs and presenting a barrier to the democratization of machine learning. The global initial learning rate for DNN training is particularly important. Several techniques have been proposed for automated learning rate tuning during training; however, they still require manual searching for the global initial learning rate. Though methods exist that do not require this initial selection, they suffer from poor performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16975","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/2411.16975/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":"2411.16975","created_at":"2026-07-05T09:40:25.450113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16975v1","created_at":"2026-07-05T09:40:25.450113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16975","created_at":"2026-07-05T09:40:25.450113+00:00"},{"alias_kind":"pith_short_12","alias_value":"MV3W4QCBCIHG","created_at":"2026-07-05T09:40:25.450113+00:00"},{"alias_kind":"pith_short_16","alias_value":"MV3W4QCBCIHG24AD","created_at":"2026-07-05T09:40:25.450113+00:00"},{"alias_kind":"pith_short_8","alias_value":"MV3W4QCB","created_at":"2026-07-05T09:40:25.450113+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/MV3W4QCBCIHG24ADFAO74MDORL","json":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL.json","graph_json":"https://pith.science/api/pith-number/MV3W4QCBCIHG24ADFAO74MDORL/graph.json","events_json":"https://pith.science/api/pith-number/MV3W4QCBCIHG24ADFAO74MDORL/events.json","paper":"https://pith.science/paper/MV3W4QCB"},"agent_actions":{"view_html":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL","download_json":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL.json","view_paper":"https://pith.science/paper/MV3W4QCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16975&json=true","fetch_graph":"https://pith.science/api/pith-number/MV3W4QCBCIHG24ADFAO74MDORL/graph.json","fetch_events":"https://pith.science/api/pith-number/MV3W4QCBCIHG24ADFAO74MDORL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL/action/storage_attestation","attest_author":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL/action/author_attestation","sign_citation":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL/action/citation_signature","submit_replication":"https://pith.science/pith/MV3W4QCBCIHG24ADFAO74MDORL/action/replication_record"}},"created_at":"2026-07-05T09:40:25.450113+00:00","updated_at":"2026-07-05T09:40:25.450113+00:00"}