{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4HMZPLWJ6VP2DJZCK4O7NQRJTF","short_pith_number":"pith:4HMZPLWJ","canonical_record":{"source":{"id":"1905.10943","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T02:50:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"63576a6af9f361ae2dae0b53298d578d34403e7bcf6a59b8b42a7cfece85ce68","abstract_canon_sha256":"25f48973238c3248431c5c2236041847cb369f987e3b816953c3f4c353f80e5c"},"schema_version":"1.0"},"canonical_sha256":"e1d997aec9f55fa1a722571df6c229994aab128fec594683ae24671b56f4ebb5","source":{"kind":"arxiv","id":"1905.10943","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10943","created_at":"2026-05-17T23:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10943v1","created_at":"2026-05-17T23:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10943","created_at":"2026-05-17T23:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"4HMZPLWJ6VP2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4HMZPLWJ6VP2DJZC","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4HMZPLWJ","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4HMZPLWJ6VP2DJZCK4O7NQRJTF","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10943","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T02:50:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"63576a6af9f361ae2dae0b53298d578d34403e7bcf6a59b8b42a7cfece85ce68","abstract_canon_sha256":"25f48973238c3248431c5c2236041847cb369f987e3b816953c3f4c353f80e5c"},"schema_version":"1.0"},"canonical_sha256":"e1d997aec9f55fa1a722571df6c229994aab128fec594683ae24671b56f4ebb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:03.330152Z","signature_b64":"A1vimrDdTC3Cy4AVYypjRbRE5sDC8phtjmYfdFAkDSN0YjsmD2lTCq9H1z0XXAFQCtVBcws4U0E7ELQ0d+CvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d997aec9f55fa1a722571df6c229994aab128fec594683ae24671b56f4ebb5","last_reissued_at":"2026-05-17T23:45:03.329581Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:03.329581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10943","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STpapFTAsMg38vB0vP0yUgzNHTn0S/WP/i2KAwPYzfFKmwgnC1zVhiSFl2zW1msZZcg1FMpwDPAqj/lTazoyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:51:18.318701Z"},"content_sha256":"46b0bfe3cfe3a9ad5dd734c01c50a4d09612ef106171c77b46c5104fbedc5931","schema_version":"1.0","event_id":"sha256:46b0bfe3cfe3a9ad5dd734c01c50a4d09612ef106171c77b46c5104fbedc5931"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4HMZPLWJ6VP2DJZCK4O7NQRJTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Optimization and Generalization in Kernel Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew Staib, Stefanie Jegelka","submitted_at":"2019-05-27T02:50:15Z","abstract_excerpt":"Distributionally robust optimization (DRO) has attracted attention in machine learning due to its connections to regularization, generalization, and robustness. Existing work has considered uncertainty sets based on phi-divergences and Wasserstein distances, each of which have drawbacks. In this paper, we study DRO with uncertainty sets measured via maximum mean discrepancy (MMD). We show that MMD DRO is roughly equivalent to regularization by the Hilbert norm and, as a byproduct, reveal deep connections to classic results in statistical learning. In particular, we obtain an alternative proof "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10943","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":""},"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":"2026-05-17T23:45:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k87/44kHSbS+zI+aBKr+V75pU5vtj1ztLwd+qGPdhlMDk3jas3Ygnp30fmhS6/S+nw/L0qRkWrI8vMolb886Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:51:18.319339Z"},"content_sha256":"2bf2609b7ee7e5eff1b68009ffa5298baad0651afbb167ec423d311b388d85f4","schema_version":"1.0","event_id":"sha256:2bf2609b7ee7e5eff1b68009ffa5298baad0651afbb167ec423d311b388d85f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HMZPLWJ6VP2DJZCK4O7NQRJTF/bundle.json","state_url":"https://pith.science/pith/4HMZPLWJ6VP2DJZCK4O7NQRJTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HMZPLWJ6VP2DJZCK4O7NQRJTF/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":"2026-06-01T02:51:18Z","links":{"resolver":"https://pith.science/pith/4HMZPLWJ6VP2DJZCK4O7NQRJTF","bundle":"https://pith.science/pith/4HMZPLWJ6VP2DJZCK4O7NQRJTF/bundle.json","state":"https://pith.science/pith/4HMZPLWJ6VP2DJZCK4O7NQRJTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HMZPLWJ6VP2DJZCK4O7NQRJTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4HMZPLWJ6VP2DJZCK4O7NQRJTF","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":"25f48973238c3248431c5c2236041847cb369f987e3b816953c3f4c353f80e5c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T02:50:15Z","title_canon_sha256":"63576a6af9f361ae2dae0b53298d578d34403e7bcf6a59b8b42a7cfece85ce68"},"schema_version":"1.0","source":{"id":"1905.10943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10943","created_at":"2026-05-17T23:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10943v1","created_at":"2026-05-17T23:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10943","created_at":"2026-05-17T23:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"4HMZPLWJ6VP2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4HMZPLWJ6VP2DJZC","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4HMZPLWJ","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:2bf2609b7ee7e5eff1b68009ffa5298baad0651afbb167ec423d311b388d85f4","target":"graph","created_at":"2026-05-17T23:45:03Z","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":"Distributionally robust optimization (DRO) has attracted attention in machine learning due to its connections to regularization, generalization, and robustness. Existing work has considered uncertainty sets based on phi-divergences and Wasserstein distances, each of which have drawbacks. In this paper, we study DRO with uncertainty sets measured via maximum mean discrepancy (MMD). We show that MMD DRO is roughly equivalent to regularization by the Hilbert norm and, as a byproduct, reveal deep connections to classic results in statistical learning. In particular, we obtain an alternative proof ","authors_text":"Matthew Staib, Stefanie Jegelka","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T02:50:15Z","title":"Distributionally Robust Optimization and Generalization in Kernel Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10943","kind":"arxiv","version":1},"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":"sha256:46b0bfe3cfe3a9ad5dd734c01c50a4d09612ef106171c77b46c5104fbedc5931","target":"record","created_at":"2026-05-17T23:45:03Z","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":"25f48973238c3248431c5c2236041847cb369f987e3b816953c3f4c353f80e5c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T02:50:15Z","title_canon_sha256":"63576a6af9f361ae2dae0b53298d578d34403e7bcf6a59b8b42a7cfece85ce68"},"schema_version":"1.0","source":{"id":"1905.10943","kind":"arxiv","version":1}},"canonical_sha256":"e1d997aec9f55fa1a722571df6c229994aab128fec594683ae24671b56f4ebb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1d997aec9f55fa1a722571df6c229994aab128fec594683ae24671b56f4ebb5","first_computed_at":"2026-05-17T23:45:03.329581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:03.329581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A1vimrDdTC3Cy4AVYypjRbRE5sDC8phtjmYfdFAkDSN0YjsmD2lTCq9H1z0XXAFQCtVBcws4U0E7ELQ0d+CvBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:03.330152Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46b0bfe3cfe3a9ad5dd734c01c50a4d09612ef106171c77b46c5104fbedc5931","sha256:2bf2609b7ee7e5eff1b68009ffa5298baad0651afbb167ec423d311b388d85f4"],"state_sha256":"89afb4b8ebc69ae959dd8461fcc3c71b508b72af4c184f5bc8ebc0ff2ce0f1f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lsusJCOJmZ4xYmjUvFxwa05xdvMZP4yKANjXq95CBob1Di1JZk3Hw3SGWnJ97Mral5hzuGMfdLKm51ALD9cnDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:51:18.322187Z","bundle_sha256":"5edafa84a389914aeaca7f08f8f7f5b2aad85a9781b06089971978168641fa0e"}}