{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AIKUWQ46JZKYBVM7E7SS3QNVNH","short_pith_number":"pith:AIKUWQ46","schema_version":"1.0","canonical_sha256":"02154b439e4e5580d59f27e52dc1b569c5f59e4e774e6208af51782fee5f7725","source":{"kind":"arxiv","id":"2602.06824","version":2},"attestation_state":"computed","paper":{"title":"RanSOM: Second-Order Momentum with Randomized Scaling for Constrained and Unconstrained Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"El Mahdi Chayti","submitted_at":"2026-02-06T16:09:36Z","abstract_excerpt":"Momentum methods, such as Polyak's Heavy Ball, are the standard for training deep networks but suffer from curvature-induced bias in stochastic settings, limiting convergence to suboptimal $\\mathcal{O}(\\epsilon^{-4})$ rates. Existing corrections typically require expensive auxiliary sampling or restrictive smoothness assumptions. We propose \\textbf{RanSOM}, a unified framework that eliminates this bias by replacing deterministic step sizes with randomized steps drawn from distributions with mean $\\eta_t$. This modification allows us to leverage Stein-type identities to compute an exact, unbias"},"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":"2602.06824","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-02-06T16:09:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"92a6e16e0ccb6b59815a00dd5b6464472a08ca5d52b51b70baee2af937e6d2c3","abstract_canon_sha256":"16f0ad1769ac512abf73a9b7fdea37083ccede2e1c92514703d37417161145f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:33.783447Z","signature_b64":"Efo0cQ0svQ7PEgQf7iWLIOrZcrqVITh8qWgQSq5lrwME0mkt1Hfo4F5J+qEzUbGT59DMa+9EoUdvaCLd+0UEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02154b439e4e5580d59f27e52dc1b569c5f59e4e774e6208af51782fee5f7725","last_reissued_at":"2026-05-20T00:00:33.782824Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:33.782824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RanSOM: Second-Order Momentum with Randomized Scaling for Constrained and Unconstrained Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"El Mahdi Chayti","submitted_at":"2026-02-06T16:09:36Z","abstract_excerpt":"Momentum methods, such as Polyak's Heavy Ball, are the standard for training deep networks but suffer from curvature-induced bias in stochastic settings, limiting convergence to suboptimal $\\mathcal{O}(\\epsilon^{-4})$ rates. Existing corrections typically require expensive auxiliary sampling or restrictive smoothness assumptions. We propose \\textbf{RanSOM}, a unified framework that eliminates this bias by replacing deterministic step sizes with randomized steps drawn from distributions with mean $\\eta_t$. This modification allows us to leverage Stein-type identities to compute an exact, unbias"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06824","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.06824/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":"2602.06824","created_at":"2026-05-20T00:00:33.782938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06824v2","created_at":"2026-05-20T00:00:33.782938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06824","created_at":"2026-05-20T00:00:33.782938+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIKUWQ46JZKY","created_at":"2026-05-20T00:00:33.782938+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIKUWQ46JZKYBVM7","created_at":"2026-05-20T00:00:33.782938+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIKUWQ46","created_at":"2026-05-20T00:00:33.782938+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/AIKUWQ46JZKYBVM7E7SS3QNVNH","json":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH.json","graph_json":"https://pith.science/api/pith-number/AIKUWQ46JZKYBVM7E7SS3QNVNH/graph.json","events_json":"https://pith.science/api/pith-number/AIKUWQ46JZKYBVM7E7SS3QNVNH/events.json","paper":"https://pith.science/paper/AIKUWQ46"},"agent_actions":{"view_html":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH","download_json":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH.json","view_paper":"https://pith.science/paper/AIKUWQ46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06824&json=true","fetch_graph":"https://pith.science/api/pith-number/AIKUWQ46JZKYBVM7E7SS3QNVNH/graph.json","fetch_events":"https://pith.science/api/pith-number/AIKUWQ46JZKYBVM7E7SS3QNVNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH/action/storage_attestation","attest_author":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH/action/author_attestation","sign_citation":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH/action/citation_signature","submit_replication":"https://pith.science/pith/AIKUWQ46JZKYBVM7E7SS3QNVNH/action/replication_record"}},"created_at":"2026-05-20T00:00:33.782938+00:00","updated_at":"2026-05-20T00:00:33.782938+00:00"}