{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q32SFR46NB3ZXS7HJ4DTR5ETAD","short_pith_number":"pith:Q32SFR46","schema_version":"1.0","canonical_sha256":"86f522c79e68779bcbe74f0738f49300ff997bef05e624e47e0768033bee4efa","source":{"kind":"arxiv","id":"2311.00531","version":3},"attestation_state":"computed","paper":{"title":"Improved Performance of Stochastic Gradients with Gaussian Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Andrew Starnes, Clayton Webster","submitted_at":"2023-11-01T14:09:12Z","abstract_excerpt":"This paper formalizes and analyzes Gaussian smoothing applied to two prominent optimization methods: Stochastic Gradient Descent (GSmoothSGD) and Adam (GSmoothAdam) in deep learning. By attenuating small fluctuations, Gaussian smoothing lowers the risk of gradient-based algorithms converging to poor local minima. These methods simplify the loss landscape while boosting robustness to noise and improving generalization, helping base algorithms converge more effectively to global minima. Existing approaches often rely on zero-order approximations, which increase training time due to inefficiencie"},"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":"2311.00531","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-11-01T14:09:12Z","cross_cats_sorted":[],"title_canon_sha256":"7bf37de07021d959d3875cd908a628d7728128b4e6cb24dcf8cbb3607100d05a","abstract_canon_sha256":"cdc76a5d1f9bcc4bd297128bb3e3af6beb9e529d71e5ac52151f4c1f5d18ad81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:37.215106Z","signature_b64":"2Ix35o02FJzDIshHna7UEjnwWOMb+6q6b44qPn3KukGmDjfiIAE15Nah6Qzz0HAOu2og/IOZ5Rm2QWPXCcE2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86f522c79e68779bcbe74f0738f49300ff997bef05e624e47e0768033bee4efa","last_reissued_at":"2026-07-05T09:36:37.214718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:37.214718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Performance of Stochastic Gradients with Gaussian Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Andrew Starnes, Clayton Webster","submitted_at":"2023-11-01T14:09:12Z","abstract_excerpt":"This paper formalizes and analyzes Gaussian smoothing applied to two prominent optimization methods: Stochastic Gradient Descent (GSmoothSGD) and Adam (GSmoothAdam) in deep learning. By attenuating small fluctuations, Gaussian smoothing lowers the risk of gradient-based algorithms converging to poor local minima. These methods simplify the loss landscape while boosting robustness to noise and improving generalization, helping base algorithms converge more effectively to global minima. Existing approaches often rely on zero-order approximations, which increase training time due to inefficiencie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00531","kind":"arxiv","version":3},"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/2311.00531/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":"2311.00531","created_at":"2026-07-05T09:36:37.214769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00531v3","created_at":"2026-07-05T09:36:37.214769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00531","created_at":"2026-07-05T09:36:37.214769+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q32SFR46NB3Z","created_at":"2026-07-05T09:36:37.214769+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q32SFR46NB3ZXS7H","created_at":"2026-07-05T09:36:37.214769+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q32SFR46","created_at":"2026-07-05T09:36:37.214769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05382","citing_title":"How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD","json":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD.json","graph_json":"https://pith.science/api/pith-number/Q32SFR46NB3ZXS7HJ4DTR5ETAD/graph.json","events_json":"https://pith.science/api/pith-number/Q32SFR46NB3ZXS7HJ4DTR5ETAD/events.json","paper":"https://pith.science/paper/Q32SFR46"},"agent_actions":{"view_html":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD","download_json":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD.json","view_paper":"https://pith.science/paper/Q32SFR46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00531&json=true","fetch_graph":"https://pith.science/api/pith-number/Q32SFR46NB3ZXS7HJ4DTR5ETAD/graph.json","fetch_events":"https://pith.science/api/pith-number/Q32SFR46NB3ZXS7HJ4DTR5ETAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD/action/storage_attestation","attest_author":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD/action/author_attestation","sign_citation":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD/action/citation_signature","submit_replication":"https://pith.science/pith/Q32SFR46NB3ZXS7HJ4DTR5ETAD/action/replication_record"}},"created_at":"2026-07-05T09:36:37.214769+00:00","updated_at":"2026-07-05T09:36:37.214769+00:00"}