{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OSXGCEOXS3OAUS7AEICHDZQM4U","short_pith_number":"pith:OSXGCEOX","schema_version":"1.0","canonical_sha256":"74ae6111d796dc0a4be0220471e60ce50c73e56bd720b4f3d5b8e9f774cce899","source":{"kind":"arxiv","id":"2410.11227","version":1},"attestation_state":"computed","paper":{"title":"Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"stat.ML","authors_text":"Bruce D. Lee, George J. Pappas, Ingvar Ziemann, Nikolai Matni, Thomas T. Zhang","submitted_at":"2024-10-15T03:20:19Z","abstract_excerpt":"A driving force behind the diverse applicability of modern machine learning is the ability to extract meaningful features across many sources. However, many practical domains involve data that are non-identically distributed across sources, and statistically dependent within its source, violating vital assumptions in existing theoretical studies. Toward addressing these issues, we establish statistical guarantees for learning general $\\textit{nonlinear}$ representations from multiple data sources that admit different input distributions and possibly dependent data. Specifically, we study the s"},"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":"2410.11227","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-15T03:20:19Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"a6cae28b727360ef7f638a43d4deb4c838fb3a1059eb0cb989e8b5bba3871040","abstract_canon_sha256":"65ff238fa1a6b18b307d1464dc42888bd6a5559490799c279197c47c0a1964e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:50.353676Z","signature_b64":"I/WhCITdlcr9silyxT6WYOTS/rh6nLEFTNqW7lxeTtPMBuHKKPaLi8QaeZsMVRAdXVv7o8Ftf1X5SW59C0ZFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74ae6111d796dc0a4be0220471e60ce50c73e56bd720b4f3d5b8e9f774cce899","last_reissued_at":"2026-07-05T09:20:50.352372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:50.352372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"stat.ML","authors_text":"Bruce D. Lee, George J. Pappas, Ingvar Ziemann, Nikolai Matni, Thomas T. Zhang","submitted_at":"2024-10-15T03:20:19Z","abstract_excerpt":"A driving force behind the diverse applicability of modern machine learning is the ability to extract meaningful features across many sources. However, many practical domains involve data that are non-identically distributed across sources, and statistically dependent within its source, violating vital assumptions in existing theoretical studies. Toward addressing these issues, we establish statistical guarantees for learning general $\\textit{nonlinear}$ representations from multiple data sources that admit different input distributions and possibly dependent data. Specifically, we study the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11227","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/2410.11227/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":"2410.11227","created_at":"2026-07-05T09:20:50.353174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11227v1","created_at":"2026-07-05T09:20:50.353174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11227","created_at":"2026-07-05T09:20:50.353174+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSXGCEOXS3OA","created_at":"2026-07-05T09:20:50.353174+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSXGCEOXS3OAUS7A","created_at":"2026-07-05T09:20:50.353174+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSXGCEOX","created_at":"2026-07-05T09:20:50.353174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19291","citing_title":"Factor Augmented High-Dimensional SGD","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U","json":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U.json","graph_json":"https://pith.science/api/pith-number/OSXGCEOXS3OAUS7AEICHDZQM4U/graph.json","events_json":"https://pith.science/api/pith-number/OSXGCEOXS3OAUS7AEICHDZQM4U/events.json","paper":"https://pith.science/paper/OSXGCEOX"},"agent_actions":{"view_html":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U","download_json":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U.json","view_paper":"https://pith.science/paper/OSXGCEOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11227&json=true","fetch_graph":"https://pith.science/api/pith-number/OSXGCEOXS3OAUS7AEICHDZQM4U/graph.json","fetch_events":"https://pith.science/api/pith-number/OSXGCEOXS3OAUS7AEICHDZQM4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U/action/storage_attestation","attest_author":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U/action/author_attestation","sign_citation":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U/action/citation_signature","submit_replication":"https://pith.science/pith/OSXGCEOXS3OAUS7AEICHDZQM4U/action/replication_record"}},"created_at":"2026-07-05T09:20:50.353174+00:00","updated_at":"2026-07-05T09:20:50.353174+00:00"}