{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZPAFPUGYSY37GHWI7LPWTSVB4L","short_pith_number":"pith:ZPAFPUGY","schema_version":"1.0","canonical_sha256":"cbc057d0d89637f31ec8fadf69caa1e2ebfe75c1ff391dc365077d66a777f4ae","source":{"kind":"arxiv","id":"2507.07826","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil, Vladimir R. Kostic","submitted_at":"2025-07-10T14:58:28Z","abstract_excerpt":"Learning from non-independent and non-identically distributed data poses a persistent challenge in statistical learning. In this study, we introduce data-dependent Bernstein inequalities tailored for vector-valued processes in Hilbert space. Our inequalities apply to both stationary and non-stationary processes and exploit the potential rapid decay of correlations between temporally separated variables to improve estimation. We demonstrate the utility of these bounds by applying them to covariance operator estimation in the Hilbert-Schmidt norm and to operator learning in dynamical systems, ac"},"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":"2507.07826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T14:58:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0b77cb72d912a205b16acbcaa3e2660558a39b2618054f0477ad69237e53a228","abstract_canon_sha256":"6750c113c6ffe43dfdea5e33fd061f43c4b018519a3f6bd70d722dc5fb1e4e3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:05.766600Z","signature_b64":"131IRZvhGXbhUYb/TA1O00JdJrAPTsAGk8EL1D9Uampa3FbXhCUgvqW79sSNJHYwZEH5oiAOzvO+u7orX9mmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbc057d0d89637f31ec8fadf69caa1e2ebfe75c1ff391dc365077d66a777f4ae","last_reissued_at":"2026-07-05T11:35:05.765999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:05.765999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil, Vladimir R. Kostic","submitted_at":"2025-07-10T14:58:28Z","abstract_excerpt":"Learning from non-independent and non-identically distributed data poses a persistent challenge in statistical learning. In this study, we introduce data-dependent Bernstein inequalities tailored for vector-valued processes in Hilbert space. Our inequalities apply to both stationary and non-stationary processes and exploit the potential rapid decay of correlations between temporally separated variables to improve estimation. We demonstrate the utility of these bounds by applying them to covariance operator estimation in the Hilbert-Schmidt norm and to operator learning in dynamical systems, ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07826","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/2507.07826/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":"2507.07826","created_at":"2026-07-05T11:35:05.766055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07826v1","created_at":"2026-07-05T11:35:05.766055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07826","created_at":"2026-07-05T11:35:05.766055+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPAFPUGYSY37","created_at":"2026-07-05T11:35:05.766055+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPAFPUGYSY37GHWI","created_at":"2026-07-05T11:35:05.766055+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPAFPUGY","created_at":"2026-07-05T11:35:05.766055+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/ZPAFPUGYSY37GHWI7LPWTSVB4L","json":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L.json","graph_json":"https://pith.science/api/pith-number/ZPAFPUGYSY37GHWI7LPWTSVB4L/graph.json","events_json":"https://pith.science/api/pith-number/ZPAFPUGYSY37GHWI7LPWTSVB4L/events.json","paper":"https://pith.science/paper/ZPAFPUGY"},"agent_actions":{"view_html":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L","download_json":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L.json","view_paper":"https://pith.science/paper/ZPAFPUGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07826&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPAFPUGYSY37GHWI7LPWTSVB4L/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPAFPUGYSY37GHWI7LPWTSVB4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L/action/storage_attestation","attest_author":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L/action/author_attestation","sign_citation":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L/action/citation_signature","submit_replication":"https://pith.science/pith/ZPAFPUGYSY37GHWI7LPWTSVB4L/action/replication_record"}},"created_at":"2026-07-05T11:35:05.766055+00:00","updated_at":"2026-07-05T11:35:05.766055+00:00"}