{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KO7P5FEDLKUN3OL2PUP22KC2ES","short_pith_number":"pith:KO7P5FED","schema_version":"1.0","canonical_sha256":"53befe94835aa8ddb97a7d1fad285a2489b1d4bb67915e9fa39f5283d5858e20","source":{"kind":"arxiv","id":"2606.27171","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Gradient Optimization with Model-Assisted Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Jonne Pohjankukka, Jukka Heikkonen","submitted_at":"2026-06-25T15:39:19Z","abstract_excerpt":"This work addresses the problem of variance in stochastic gradient estimation for machine learning optimization. Deep learning relies on mini-batch methods such as stochastic gradient descent, which approximate full gradients but introduce noise, creating trade-offs between convergence stability, speed, and generalization. Existing methods, including variance reduction techniques (e.g., SVRG and SAG) and adaptive optimizers, aim to mitigate gradient noise but may introduce additional computational overhead. We propose a model-assisted sampling framework that interprets mini-batch gradients thr"},"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":"2606.27171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T15:39:19Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"1e6c92a6b03b74f1480efe788933fd3d65342bab0770ac8a333b4f2fc967993a","abstract_canon_sha256":"4b6dedcad191b09ef217a005416655e041623e6f78d1c441a83c2629de27105f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:12.500010Z","signature_b64":"fnur58r1TiNqdShN3q2N4qOkdgqtCzHWMEQBt4P16PV39mdK6+hZkcNWP4189TmzMmLxJaDoB5+8UK4d21sUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53befe94835aa8ddb97a7d1fad285a2489b1d4bb67915e9fa39f5283d5858e20","last_reissued_at":"2026-06-26T01:16:12.499643Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:12.499643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradient Optimization with Model-Assisted Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Jonne Pohjankukka, Jukka Heikkonen","submitted_at":"2026-06-25T15:39:19Z","abstract_excerpt":"This work addresses the problem of variance in stochastic gradient estimation for machine learning optimization. Deep learning relies on mini-batch methods such as stochastic gradient descent, which approximate full gradients but introduce noise, creating trade-offs between convergence stability, speed, and generalization. Existing methods, including variance reduction techniques (e.g., SVRG and SAG) and adaptive optimizers, aim to mitigate gradient noise but may introduce additional computational overhead. We propose a model-assisted sampling framework that interprets mini-batch gradients thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27171","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/2606.27171/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":"2606.27171","created_at":"2026-06-26T01:16:12.499697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27171v1","created_at":"2026-06-26T01:16:12.499697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27171","created_at":"2026-06-26T01:16:12.499697+00:00"},{"alias_kind":"pith_short_12","alias_value":"KO7P5FEDLKUN","created_at":"2026-06-26T01:16:12.499697+00:00"},{"alias_kind":"pith_short_16","alias_value":"KO7P5FEDLKUN3OL2","created_at":"2026-06-26T01:16:12.499697+00:00"},{"alias_kind":"pith_short_8","alias_value":"KO7P5FED","created_at":"2026-06-26T01:16:12.499697+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/KO7P5FEDLKUN3OL2PUP22KC2ES","json":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES.json","graph_json":"https://pith.science/api/pith-number/KO7P5FEDLKUN3OL2PUP22KC2ES/graph.json","events_json":"https://pith.science/api/pith-number/KO7P5FEDLKUN3OL2PUP22KC2ES/events.json","paper":"https://pith.science/paper/KO7P5FED"},"agent_actions":{"view_html":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES","download_json":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES.json","view_paper":"https://pith.science/paper/KO7P5FED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27171&json=true","fetch_graph":"https://pith.science/api/pith-number/KO7P5FEDLKUN3OL2PUP22KC2ES/graph.json","fetch_events":"https://pith.science/api/pith-number/KO7P5FEDLKUN3OL2PUP22KC2ES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES/action/storage_attestation","attest_author":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES/action/author_attestation","sign_citation":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES/action/citation_signature","submit_replication":"https://pith.science/pith/KO7P5FEDLKUN3OL2PUP22KC2ES/action/replication_record"}},"created_at":"2026-06-26T01:16:12.499697+00:00","updated_at":"2026-06-26T01:16:12.499697+00:00"}