{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QGROHST5AJOBT3JOOT45743T7D","short_pith_number":"pith:QGROHST5","canonical_record":{"source":{"id":"1610.02581","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-08T20:52:13Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"df292faad4b42671d067a59e24ad425a4b5d2550d973170dbc2b76b07dec8401","abstract_canon_sha256":"33be77813bd97df264046d1204fed9cd7756cfa9961a58a546204876e0d20bec"},"schema_version":"1.0"},"canonical_sha256":"81a2e3ca7d025c19ed2e74f9dff373f8cc7908f1f0b2ce9126f9361df80ef1db","source":{"kind":"arxiv","id":"1610.02581","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.02581","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"arxiv_version","alias_value":"1610.02581v3","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02581","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"pith_short_12","alias_value":"QGROHST5AJOB","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"QGROHST5AJOBT3JO","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"QGROHST5","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QGROHST5AJOBT3JOOT45743T7D","target":"record","payload":{"canonical_record":{"source":{"id":"1610.02581","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-08T20:52:13Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"df292faad4b42671d067a59e24ad425a4b5d2550d973170dbc2b76b07dec8401","abstract_canon_sha256":"33be77813bd97df264046d1204fed9cd7756cfa9961a58a546204876e0d20bec"},"schema_version":"1.0"},"canonical_sha256":"81a2e3ca7d025c19ed2e74f9dff373f8cc7908f1f0b2ce9126f9361df80ef1db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:02.657426Z","signature_b64":"g19Gxe97Doxv/YowrOnJn7O8Rs36QvXOCgfXV7k2tiUO6KfxDyowOs8B9OnarPATao9q31a/Lw8QN3U/Dm9zBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81a2e3ca7d025c19ed2e74f9dff373f8cc7908f1f0b2ce9126f9361df80ef1db","last_reissued_at":"2026-05-18T00:28:02.656731Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:02.656731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.02581","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:28:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Jljmy/pCinDMf0K9igmgP9F5ZyJLq6sa6TeqczSC5JseRpAW9PHILezYnLjWOpmqHBwMu36aP553l6YmiCCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:16:42.867763Z"},"content_sha256":"6afaf1fb5b7067f5cd6a42523613d503eac841a21ee797b7b22c05a596ebd213","schema_version":"1.0","event_id":"sha256:6afaf1fb5b7067f5cd6a42523613d503eac841a21ee797b7b22c05a596ebd213"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QGROHST5AJOBT3JOOT45743T7D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance-based regularization with convex objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Hongseok Namkoong, John Duchi","submitted_at":"2016-10-08T20:52:13Z","abstract_excerpt":"We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error. Our approach builds off of techniques for distributionally robust optimization and Owen's empirical likelihood, and we provide a number of finite-sample and asymptotic results characterizing the theoretical performance of the estimator. In particular, we show that our procedure comes with certificates of optimality, achieving (in some scenarios) faster rates of convergence t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02581","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:28:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jBRTmF/1+8dHOJvmqrd6grQ2uzQLBQSBEqPR+aSa6lg2JEv5F1wozJdDl9wZLcbUmnMPlAnjZ66SBuB+RRF8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:16:42.868222Z"},"content_sha256":"bb3a98d3b0b612b78ca4bad41cce8442b289a648a178ed39368bd6b2e9aeb215","schema_version":"1.0","event_id":"sha256:bb3a98d3b0b612b78ca4bad41cce8442b289a648a178ed39368bd6b2e9aeb215"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGROHST5AJOBT3JOOT45743T7D/bundle.json","state_url":"https://pith.science/pith/QGROHST5AJOBT3JOOT45743T7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGROHST5AJOBT3JOOT45743T7D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T19:16:42Z","links":{"resolver":"https://pith.science/pith/QGROHST5AJOBT3JOOT45743T7D","bundle":"https://pith.science/pith/QGROHST5AJOBT3JOOT45743T7D/bundle.json","state":"https://pith.science/pith/QGROHST5AJOBT3JOOT45743T7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGROHST5AJOBT3JOOT45743T7D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QGROHST5AJOBT3JOOT45743T7D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"33be77813bd97df264046d1204fed9cd7756cfa9961a58a546204876e0d20bec","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-08T20:52:13Z","title_canon_sha256":"df292faad4b42671d067a59e24ad425a4b5d2550d973170dbc2b76b07dec8401"},"schema_version":"1.0","source":{"id":"1610.02581","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.02581","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"arxiv_version","alias_value":"1610.02581v3","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02581","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"pith_short_12","alias_value":"QGROHST5AJOB","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"QGROHST5AJOBT3JO","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"QGROHST5","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:bb3a98d3b0b612b78ca4bad41cce8442b289a648a178ed39368bd6b2e9aeb215","target":"graph","created_at":"2026-05-18T00:28:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error. Our approach builds off of techniques for distributionally robust optimization and Owen's empirical likelihood, and we provide a number of finite-sample and asymptotic results characterizing the theoretical performance of the estimator. In particular, we show that our procedure comes with certificates of optimality, achieving (in some scenarios) faster rates of convergence t","authors_text":"Hongseok Namkoong, John Duchi","cross_cats":["math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-08T20:52:13Z","title":"Variance-based regularization with convex objectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02581","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6afaf1fb5b7067f5cd6a42523613d503eac841a21ee797b7b22c05a596ebd213","target":"record","created_at":"2026-05-18T00:28:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"33be77813bd97df264046d1204fed9cd7756cfa9961a58a546204876e0d20bec","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-08T20:52:13Z","title_canon_sha256":"df292faad4b42671d067a59e24ad425a4b5d2550d973170dbc2b76b07dec8401"},"schema_version":"1.0","source":{"id":"1610.02581","kind":"arxiv","version":3}},"canonical_sha256":"81a2e3ca7d025c19ed2e74f9dff373f8cc7908f1f0b2ce9126f9361df80ef1db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81a2e3ca7d025c19ed2e74f9dff373f8cc7908f1f0b2ce9126f9361df80ef1db","first_computed_at":"2026-05-18T00:28:02.656731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:02.656731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g19Gxe97Doxv/YowrOnJn7O8Rs36QvXOCgfXV7k2tiUO6KfxDyowOs8B9OnarPATao9q31a/Lw8QN3U/Dm9zBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:02.657426Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.02581","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6afaf1fb5b7067f5cd6a42523613d503eac841a21ee797b7b22c05a596ebd213","sha256:bb3a98d3b0b612b78ca4bad41cce8442b289a648a178ed39368bd6b2e9aeb215"],"state_sha256":"a95056b16bff4a1ab7e88f831efbd6637602f3f5582c8af42c637619fff6df64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5CHmFstlsHJqWxBDsPfu5FrA00XesEt+O5r0E1Dcl7kJLfS6Z8ljt9u80OaUr9qTsqM+/+A0AS4u8Y4hSeICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:16:42.870991Z","bundle_sha256":"6099fbd24ef0ab784a21fb4523e9e7579980ec73898d602b8331c067cbd8c784"}}