{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KAOQYWIJ6JYLQTP4LIA2IUO3AE","short_pith_number":"pith:KAOQYWIJ","schema_version":"1.0","canonical_sha256":"501d0c5909f270b84dfc5a01a451db01069dd511c9caae197e809e68797939a9","source":{"kind":"arxiv","id":"2607.28902","version":1},"attestation_state":"computed","paper":{"title":"Adaptivity via a Parallel Architecture for Stochastic Gradient Methods Adaptivity via a Parallel Architecture for Stochastic Gradient Methods Adaptivity via a Parallel Architecture for Stochastic Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","math.OC"],"primary_cat":"cs.LG","authors_text":"Bin Fu","submitted_at":"2026-07-31T00:02:30Z","abstract_excerpt":"We develop a parallel framework that assembles static gradient methods to achieve better adaptivity. A static gradient method, denoted by $\\mathrm{GD}(x_0,T)$, takes as input an initial point $x_0\\in\\mathbb{R}^n$ and $T\\in \\mathbb{R}^+$ specifying the number $\\floor{T}$ of iterations. The step size is chosen as $s=S(T)$, where $S(\\cdot)$ is a predetermined function of $T$. The method then performs the iterations $ x_{i+1}=x_i-\\frac{\\eta}{s}\\cdot g_i,$ where $g_i$ is a stochastic gradient evaluated at $x_i$, and $\\eta$ is a scaling factor. For an integer $p\\ge1$, the $p$ processors in the propo"},"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":"2607.28902","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T00:02:30Z","cross_cats_sorted":["cs.AR","math.OC"],"title_canon_sha256":"55769bea25cb6310654aba1f4c1052a60ae86a5b8e5c6824f549d16ea62849aa","abstract_canon_sha256":"24c3d32d83c44597f50ab89c8c4d8e79477172f10f3f721231405fff18322ea0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:17:27.814852Z","signature_b64":"RwPqOXlmz+DVKar65BOk2/KkEYDEZP5mNp2R72Or/ujORYqt0yv0qmLJHJ5V3vzfDsVfDeL61RmUMkjX0m+MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"501d0c5909f270b84dfc5a01a451db01069dd511c9caae197e809e68797939a9","last_reissued_at":"2026-08-03T01:17:27.813282Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:17:27.813282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptivity via a Parallel Architecture for Stochastic Gradient Methods Adaptivity via a Parallel Architecture for Stochastic Gradient Methods Adaptivity via a Parallel Architecture for Stochastic Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","math.OC"],"primary_cat":"cs.LG","authors_text":"Bin Fu","submitted_at":"2026-07-31T00:02:30Z","abstract_excerpt":"We develop a parallel framework that assembles static gradient methods to achieve better adaptivity. A static gradient method, denoted by $\\mathrm{GD}(x_0,T)$, takes as input an initial point $x_0\\in\\mathbb{R}^n$ and $T\\in \\mathbb{R}^+$ specifying the number $\\floor{T}$ of iterations. The step size is chosen as $s=S(T)$, where $S(\\cdot)$ is a predetermined function of $T$. The method then performs the iterations $ x_{i+1}=x_i-\\frac{\\eta}{s}\\cdot g_i,$ where $g_i$ is a stochastic gradient evaluated at $x_i$, and $\\eta$ is a scaling factor. For an integer $p\\ge1$, the $p$ processors in the propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28902","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/2607.28902/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":"2607.28902","created_at":"2026-08-03T01:17:27.814206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28902v1","created_at":"2026-08-03T01:17:27.814206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28902","created_at":"2026-08-03T01:17:27.814206+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAOQYWIJ6JYL","created_at":"2026-08-03T01:17:27.814206+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAOQYWIJ6JYLQTP4","created_at":"2026-08-03T01:17:27.814206+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAOQYWIJ","created_at":"2026-08-03T01:17:27.814206+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/KAOQYWIJ6JYLQTP4LIA2IUO3AE","json":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE.json","graph_json":"https://pith.science/api/pith-number/KAOQYWIJ6JYLQTP4LIA2IUO3AE/graph.json","events_json":"https://pith.science/api/pith-number/KAOQYWIJ6JYLQTP4LIA2IUO3AE/events.json","paper":"https://pith.science/paper/KAOQYWIJ"},"agent_actions":{"view_html":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE","download_json":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE.json","view_paper":"https://pith.science/paper/KAOQYWIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28902&json=true","fetch_graph":"https://pith.science/api/pith-number/KAOQYWIJ6JYLQTP4LIA2IUO3AE/graph.json","fetch_events":"https://pith.science/api/pith-number/KAOQYWIJ6JYLQTP4LIA2IUO3AE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE/action/storage_attestation","attest_author":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE/action/author_attestation","sign_citation":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE/action/citation_signature","submit_replication":"https://pith.science/pith/KAOQYWIJ6JYLQTP4LIA2IUO3AE/action/replication_record"}},"created_at":"2026-08-03T01:17:27.814206+00:00","updated_at":"2026-08-03T01:17:27.814206+00:00"}