{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2009:6JSC36HKGY6LQKKTMAESEYXFGB","short_pith_number":"pith:6JSC36HK","schema_version":"1.0","canonical_sha256":"f2642df8ea363cb8295360092262e5305d495d0f0835d531e287c6b46db390c3","source":{"kind":"arxiv","id":"0907.3740","version":1},"attestation_state":"computed","paper":{"title":"Empirical Bernstein Bounds and Sample Variance Penalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Andreas Maurer, Massimiliano Pontil","submitted_at":"2009-07-21T20:21:38Z","abstract_excerpt":"We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over classes of functionswhose growth function is polynomial in the sample size n. The bounds lead us to consider sample variance penalization, a novel learning method which takes into account the empirical variance of the loss function. We give conditions under which sample variance penalization is effective. In particular, we present a bound on the excess risk incurred by the method. Using this, we argue that there are situ"},"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":"0907.3740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2009-07-21T20:21:38Z","cross_cats_sorted":[],"title_canon_sha256":"73a9968d9bc7781880fa73269587ca640aedcce6bc602775556fc6a50e685f61","abstract_canon_sha256":"15b467633671e7749e3e3f61282811463fb82f458a9482cf1ed1044e022e359e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:46:40.967484Z","signature_b64":"Na3r3MrbWPhjrzv/nNBdynuYW+cjHUdM64shzAAJ9hL+AeXHbEqY38C/j1Rbp2DjbgjflU99wXa4UAF2LgYyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2642df8ea363cb8295360092262e5305d495d0f0835d531e287c6b46db390c3","last_reissued_at":"2026-07-04T15:46:40.967098Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:46:40.967098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Bernstein Bounds and Sample Variance Penalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Andreas Maurer, Massimiliano Pontil","submitted_at":"2009-07-21T20:21:38Z","abstract_excerpt":"We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over classes of functionswhose growth function is polynomial in the sample size n. The bounds lead us to consider sample variance penalization, a novel learning method which takes into account the empirical variance of the loss function. We give conditions under which sample variance penalization is effective. In particular, we present a bound on the excess risk incurred by the method. Using this, we argue that there are situ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0907.3740","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/0907.3740/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":"0907.3740","created_at":"2026-07-04T15:46:40.967155+00:00"},{"alias_kind":"arxiv_version","alias_value":"0907.3740v1","created_at":"2026-07-04T15:46:40.967155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0907.3740","created_at":"2026-07-04T15:46:40.967155+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JSC36HKGY6L","created_at":"2026-07-04T15:46:40.967155+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JSC36HKGY6LQKKT","created_at":"2026-07-04T15:46:40.967155+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JSC36HK","created_at":"2026-07-04T15:46:40.967155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.19147","citing_title":"Cross-Calibrated Confidence Fields for Local Risk Updates","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01407","citing_title":"Vitriflow: calibrated amorphous structure ensembles from melt-quench simulation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30866","citing_title":"A data-dependent DKW inequality for regenerative Markov chains","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2307.02719","citing_title":"Understanding Uncertainty Sampling via Equivalent Loss","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15692","citing_title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18246","citing_title":"Privacy Preserving Reinforcement Learning with One-Sided Feedback","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02939","citing_title":"Importance Sampling for Statistical Certification of Viable Initial Sets","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12316","citing_title":"Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09565","citing_title":"Online Set Learning from Precision and Recall Feedback","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB","json":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB.json","graph_json":"https://pith.science/api/pith-number/6JSC36HKGY6LQKKTMAESEYXFGB/graph.json","events_json":"https://pith.science/api/pith-number/6JSC36HKGY6LQKKTMAESEYXFGB/events.json","paper":"https://pith.science/paper/6JSC36HK"},"agent_actions":{"view_html":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB","download_json":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB.json","view_paper":"https://pith.science/paper/6JSC36HK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0907.3740&json=true","fetch_graph":"https://pith.science/api/pith-number/6JSC36HKGY6LQKKTMAESEYXFGB/graph.json","fetch_events":"https://pith.science/api/pith-number/6JSC36HKGY6LQKKTMAESEYXFGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB/action/storage_attestation","attest_author":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB/action/author_attestation","sign_citation":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB/action/citation_signature","submit_replication":"https://pith.science/pith/6JSC36HKGY6LQKKTMAESEYXFGB/action/replication_record"}},"created_at":"2026-07-04T15:46:40.967155+00:00","updated_at":"2026-07-04T15:46:40.967155+00:00"}