{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:46HNA4WEA4I77VENKJGX2AMKID","short_pith_number":"pith:46HNA4WE","schema_version":"1.0","canonical_sha256":"e78ed072c40711ffd48d524d7d018a40f03df67ae46431debc4a1314ce4743ee","source":{"kind":"arxiv","id":"1806.01593","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Yang Hsueh, I-Chen Wu, Wei Li","submitted_at":"2018-06-05T10:14:01Z","abstract_excerpt":"Learning rate scheduler has been a critical issue in the deep neural network training. Several schedulers and methods have been proposed, including step decay scheduler, adaptive method, cosine scheduler and cyclical scheduler. This paper proposes a new scheduling method, named hyperbolic-tangent decay (HTD). We run experiments on several benchmarks such as: ResNet, Wide ResNet and DenseNet for CIFAR-10 and CIFAR-100 datasets, LSTM for PAMAP2 dataset, ResNet on ImageNet and Fashion-MNIST datasets. In our experiments, HTD outperforms step decay and cosine scheduler in nearly all cases, while re"},"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":"1806.01593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-05T10:14:01Z","cross_cats_sorted":[],"title_canon_sha256":"3d0d2a4b10e2cee538cefb025d6d97493d03cc1a486f281ac4425cfe964601a8","abstract_canon_sha256":"8e065bcc016088e8b652dca26df080a596bac563315fa713bd4cbc1eee766aee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:01.784963Z","signature_b64":"PxebZYZbnHANhutLVAiCr68O86amV9YmKQVpeliSKG6KORIptIz1lApuiip1FgFC0Nbvl6QyKTB4/P/l7UNtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78ed072c40711ffd48d524d7d018a40f03df67ae46431debc4a1314ce4743ee","last_reissued_at":"2026-05-18T00:01:01.784491Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:01.784491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Yang Hsueh, I-Chen Wu, Wei Li","submitted_at":"2018-06-05T10:14:01Z","abstract_excerpt":"Learning rate scheduler has been a critical issue in the deep neural network training. Several schedulers and methods have been proposed, including step decay scheduler, adaptive method, cosine scheduler and cyclical scheduler. This paper proposes a new scheduling method, named hyperbolic-tangent decay (HTD). We run experiments on several benchmarks such as: ResNet, Wide ResNet and DenseNet for CIFAR-10 and CIFAR-100 datasets, LSTM for PAMAP2 dataset, ResNet on ImageNet and Fashion-MNIST datasets. In our experiments, HTD outperforms step decay and cosine scheduler in nearly all cases, while re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01593","kind":"arxiv","version":2},"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":"1806.01593","created_at":"2026-05-18T00:01:01.784573+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01593v2","created_at":"2026-05-18T00:01:01.784573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01593","created_at":"2026-05-18T00:01:01.784573+00:00"},{"alias_kind":"pith_short_12","alias_value":"46HNA4WEA4I7","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"46HNA4WEA4I77VEN","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"46HNA4WE","created_at":"2026-05-18T12:32:05.422762+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/46HNA4WEA4I77VENKJGX2AMKID","json":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID.json","graph_json":"https://pith.science/api/pith-number/46HNA4WEA4I77VENKJGX2AMKID/graph.json","events_json":"https://pith.science/api/pith-number/46HNA4WEA4I77VENKJGX2AMKID/events.json","paper":"https://pith.science/paper/46HNA4WE"},"agent_actions":{"view_html":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID","download_json":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID.json","view_paper":"https://pith.science/paper/46HNA4WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01593&json=true","fetch_graph":"https://pith.science/api/pith-number/46HNA4WEA4I77VENKJGX2AMKID/graph.json","fetch_events":"https://pith.science/api/pith-number/46HNA4WEA4I77VENKJGX2AMKID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID/action/storage_attestation","attest_author":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID/action/author_attestation","sign_citation":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID/action/citation_signature","submit_replication":"https://pith.science/pith/46HNA4WEA4I77VENKJGX2AMKID/action/replication_record"}},"created_at":"2026-05-18T00:01:01.784573+00:00","updated_at":"2026-05-18T00:01:01.784573+00:00"}