{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NLCNZSKRTSDTTKSMYEMEENXCBK","short_pith_number":"pith:NLCNZSKR","schema_version":"1.0","canonical_sha256":"6ac4dcc9519c8739aa4cc1184236e20ab0a9402700da374d95f4fabf1c9b6899","source":{"kind":"arxiv","id":"2607.10959","version":1},"attestation_state":"computed","paper":{"title":"WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianhao Ma, Yuxin Chen","submitted_at":"2026-07-12T23:24:42Z","abstract_excerpt":"Standard learning rate schedules such as cosine annealing are tied to a fixed training horizon, limiting their ability to accommodate post hoc horizon extension. Warmup-stable-decay (WSD) partially addresses this issue by maintaining a long constant-rate phase before a short linear cooldown, allowing training to resume from a pre-decay checkpoint. However, its peak learning rate is still tuned based on the original training horizon and can become suboptimal when training is extended. Motivated by stochastic convex optimization, we propose WSqD (Warmup with Square-root base and linear Decay), a"},"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":"2607.10959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T23:24:42Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"834d785cdcde1bd218564e36f73fabd1c1f767618fabef73a6a3e800a5307dcb","abstract_canon_sha256":"8942e975e85201caac515167276293d464b70b3f8651e57111d94c93666ad24d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:49.560534Z","signature_b64":"c0SP+al2n+bkXJzDF23LUPhAfqIFNh7ccXf9gwsEp8iVVIoIJ/V2hSOV03ao2/HouDKmHSJ4nE1+B2VXtNZUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac4dcc9519c8739aa4cc1184236e20ab0a9402700da374d95f4fabf1c9b6899","last_reissued_at":"2026-07-14T01:21:49.559714Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:49.559714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianhao Ma, Yuxin Chen","submitted_at":"2026-07-12T23:24:42Z","abstract_excerpt":"Standard learning rate schedules such as cosine annealing are tied to a fixed training horizon, limiting their ability to accommodate post hoc horizon extension. Warmup-stable-decay (WSD) partially addresses this issue by maintaining a long constant-rate phase before a short linear cooldown, allowing training to resume from a pre-decay checkpoint. However, its peak learning rate is still tuned based on the original training horizon and can become suboptimal when training is extended. Motivated by stochastic convex optimization, we propose WSqD (Warmup with Square-root base and linear Decay), a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10959","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/2607.10959/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":"2607.10959","created_at":"2026-07-14T01:21:49.560131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10959v1","created_at":"2026-07-14T01:21:49.560131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10959","created_at":"2026-07-14T01:21:49.560131+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLCNZSKRTSDT","created_at":"2026-07-14T01:21:49.560131+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLCNZSKRTSDTTKSM","created_at":"2026-07-14T01:21:49.560131+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLCNZSKR","created_at":"2026-07-14T01:21:49.560131+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/NLCNZSKRTSDTTKSMYEMEENXCBK","json":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK.json","graph_json":"https://pith.science/api/pith-number/NLCNZSKRTSDTTKSMYEMEENXCBK/graph.json","events_json":"https://pith.science/api/pith-number/NLCNZSKRTSDTTKSMYEMEENXCBK/events.json","paper":"https://pith.science/paper/NLCNZSKR"},"agent_actions":{"view_html":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK","download_json":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK.json","view_paper":"https://pith.science/paper/NLCNZSKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10959&json=true","fetch_graph":"https://pith.science/api/pith-number/NLCNZSKRTSDTTKSMYEMEENXCBK/graph.json","fetch_events":"https://pith.science/api/pith-number/NLCNZSKRTSDTTKSMYEMEENXCBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK/action/storage_attestation","attest_author":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK/action/author_attestation","sign_citation":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK/action/citation_signature","submit_replication":"https://pith.science/pith/NLCNZSKRTSDTTKSMYEMEENXCBK/action/replication_record"}},"created_at":"2026-07-14T01:21:49.560131+00:00","updated_at":"2026-07-14T01:21:49.560131+00:00"}