{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VDWL7LBSDW4KMDHO4K5DI4RH63","short_pith_number":"pith:VDWL7LBS","schema_version":"1.0","canonical_sha256":"a8ecbfac321db8a60ceee2ba347227f6c4ea798cc296946eac3190dcf167890e","source":{"kind":"arxiv","id":"2508.20326","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Gradients under Nuisances","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alex Luedtke, Facheng Yu, Ronak Mehta, Zaid Harchaoui","submitted_at":"2025-08-28T00:07:40Z","abstract_excerpt":"Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider stochastic gradient algorithms for learning problems whose objectives rely on unknown nuisance parameters, and establish non-asymptotic convergence guarantees. Our results show that, while the presence of a nuisance can alter the optimum and upset the optimization trajectory, the classical stochastic gradient algorithm may still converge under appropriate conditions, such as Neyman orthogonality. Moreover, even when Ne"},"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":"2508.20326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-28T00:07:40Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"b800188e3b9abad96c6f95f161c0adf7719ead6da819eb2a7861b0f4d7a9a9bb","abstract_canon_sha256":"5579e9cdc7c02f59369f08d2c4f772b64c62a5f50e7f7d256085ebc5f5aa2842"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:19.406424Z","signature_b64":"J/gGu31ez51tqxJP2t5/Cjkw0Or0nlkcXBSG2pUmHfZTu27hl4FT38QfQqZdbuh99AJZK3A0xifERgdmFhuQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8ecbfac321db8a60ceee2ba347227f6c4ea798cc296946eac3190dcf167890e","last_reissued_at":"2026-06-01T01:02:19.405455Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:19.405455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradients under Nuisances","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alex Luedtke, Facheng Yu, Ronak Mehta, Zaid Harchaoui","submitted_at":"2025-08-28T00:07:40Z","abstract_excerpt":"Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider stochastic gradient algorithms for learning problems whose objectives rely on unknown nuisance parameters, and establish non-asymptotic convergence guarantees. Our results show that, while the presence of a nuisance can alter the optimum and upset the optimization trajectory, the classical stochastic gradient algorithm may still converge under appropriate conditions, such as Neyman orthogonality. Moreover, even when Ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20326","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/2508.20326/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":"2508.20326","created_at":"2026-06-01T01:02:19.405572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20326v2","created_at":"2026-06-01T01:02:19.405572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20326","created_at":"2026-06-01T01:02:19.405572+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDWL7LBSDW4K","created_at":"2026-06-01T01:02:19.405572+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDWL7LBSDW4KMDHO","created_at":"2026-06-01T01:02:19.405572+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDWL7LBS","created_at":"2026-06-01T01:02:19.405572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.23805","citing_title":"Fitted $Q$ Evaluation Without Bellman Completeness via Stationary Weighting","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63","json":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63.json","graph_json":"https://pith.science/api/pith-number/VDWL7LBSDW4KMDHO4K5DI4RH63/graph.json","events_json":"https://pith.science/api/pith-number/VDWL7LBSDW4KMDHO4K5DI4RH63/events.json","paper":"https://pith.science/paper/VDWL7LBS"},"agent_actions":{"view_html":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63","download_json":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63.json","view_paper":"https://pith.science/paper/VDWL7LBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20326&json=true","fetch_graph":"https://pith.science/api/pith-number/VDWL7LBSDW4KMDHO4K5DI4RH63/graph.json","fetch_events":"https://pith.science/api/pith-number/VDWL7LBSDW4KMDHO4K5DI4RH63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63/action/storage_attestation","attest_author":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63/action/author_attestation","sign_citation":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63/action/citation_signature","submit_replication":"https://pith.science/pith/VDWL7LBSDW4KMDHO4K5DI4RH63/action/replication_record"}},"created_at":"2026-06-01T01:02:19.405572+00:00","updated_at":"2026-06-01T01:02:19.405572+00:00"}